# Awesome Jev

The definitive community radar and directory for TypeSafe Jev and System-1 Agent architecture projects. Every listed project is verified against commit-pinned public open source code.

Website: https://logicrw.github.io/awesome-jev-projects/
Repository: https://github.com/logicrw/awesome-jev-projects
Catalog entries: 289

## Install the Agent Skill

```bash
npx skills add logicrw/awesome-jev-projects
npx skills add https://logicrw.github.io/awesome-jev-projects/
```

## Machine-readable resources
- [projects.json](https://logicrw.github.io/awesome-jev-projects/projects.json)
- [llms.txt](https://logicrw.github.io/awesome-jev-projects/llms.txt)
- [llms-full.txt](https://logicrw.github.io/awesome-jev-projects/llms-full.txt)
- [skill.md](https://logicrw.github.io/awesome-jev-projects/skill.md)
- [.well-known/skills/index.json](https://logicrw.github.io/awesome-jev-projects/.well-known/skills/index.json)
- [.well-known/agent-skills/index.json](https://logicrw.github.io/awesome-jev-projects/.well-known/agent-skills/index.json)
- [.well-known/skills/default/skill.md](https://logicrw.github.io/awesome-jev-projects/.well-known/skills/default/skill.md)
- [.well-known/skills/awesome-jev/SKILL.md](https://logicrw.github.io/awesome-jev-projects/.well-known/skills/awesome-jev/SKILL.md)
- [.well-known/agent-skills/awesome-jev/SKILL.md](https://logicrw.github.io/awesome-jev-projects/.well-known/agent-skills/awesome-jev/SKILL.md)

## Language directories
- [Chinese](https://logicrw.github.io/awesome-jev-projects/catalog/)
- [English](https://logicrw.github.io/awesome-jev-projects/en/catalog/)
- [Japanese](https://logicrw.github.io/awesome-jev-projects/ja/catalog/)
- [Korean](https://logicrw.github.io/awesome-jev-projects/ko/catalog/)

## Sponsorship · Paid placements

Founding partner slots are open. There are no paid sponsors yet.

[Plans and contact](https://github.com/logicrw/awesome-jev-projects/blob/main/SPONSORING.md) · [Sponsors](https://github.com/logicrw/awesome-jev-projects/blob/main/SPONSORS.md)

Sponsorship does not change inclusion review, project descriptions, or organic ranking.

## Complete project catalog

## jev-ultrafast

A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.

- Repository: https://github.com/browser-use/jev-ultrafast
- Category: Browser & OS Action
- Jev decision: Chooses an action and its matching DOM element in one request; a text model generates input text.
- Purpose: Separates UI choices, text generation, and browser execution so each step can be inspected.
- Review scope: The author reports a median of about 7.1 seconds on one Google Flights task, with three runs per setup. Initial navigation is excluded; this is not a general Agent benchmark and was not independently retested.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-ultrafast/
- Source evidence: https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/jev_ultrafast/model.py
- Source evidence: https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/README.md
- Source evidence: https://github.com/browser-use/jev-ultrafast/blob/1231850a0bf1a0c0341fe408ef1668dbbfdfac46/docs/performance.md

## typesafe-mcp

An MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.

- Repository: https://github.com/itsmostafa/typesafe-mcp
- Category: MCP & Integrations
- Jev decision: Submits state and Choice, Score or Noul questions and returns structured answers with probabilities.
- Purpose: Provides decisions that calling code can inspect and branch on.
- Review scope: The pinned README and client source document the interface.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/typesafe-mcp/
- Source evidence: https://github.com/itsmostafa/typesafe-mcp/blob/0c9f35d9b1859189fc7e7d01947061f311ca6dde/README.md
- Source evidence: https://github.com/itsmostafa/typesafe-mcp/blob/0c9f35d9b1859189fc7e7d01947061f311ca6dde/cmd/evaluate/client.go

## jev-mcp

Eight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.

- Repository: https://github.com/jkudish/jev-mcp
- Category: MCP & Integrations
- Jev decision: Uses typed questions to assess evidence support, content risk and candidate relevance.
- Purpose: Returns judgments and probabilities; the caller owns thresholds and enforcement.
- Review scope: The current README documents eight tools. The 150–500 ms figure is author-reported; probabilities do not guarantee factual accuracy or safety. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-mcp/
- Source evidence: https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/src/provider.ts#L127
- Source evidence: https://github.com/jkudish/jev-mcp/blob/89f88b90c3180184d56961160e7178e64c98e468/README.md

## SemDecide

A Python CLI for semantic predicates, routing, scoring and filtering over text or JSONL.

- Repository: https://github.com/sharziki/semdecide
- Category: CLI & Pipelines
- Jev decision: Sends input to Jev and applies local probability thresholds to outputs and exit codes.
- Purpose: Adds typed decisions to Bash and CI with explicit output and failure states.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/semdecide/
- Source evidence: https://github.com/sharziki/semdecide/blob/33cf5c03c50e02e59df3f3ea81f0650f6b791545/README.md
- Source evidence: https://github.com/sharziki/semdecide/blob/33cf5c03c50e02e59df3f3ea81f0650f6b791545/src/reflex_guard/providers/typesafe.py
- Source evidence: https://github.com/sharziki/semdecide/blob/33cf5c03c50e02e59df3f3ea81f0650f6b791545/src/reflex_guard/policy.py

## jev-codex-router

Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.

- Repository: https://github.com/0xNatoshi/jev-codex-router
- Category: Routing & Cost Optimization
- Jev decision: Classifies task difficulty and reasoning needs before local policy selects a model configuration.
- Purpose: Keeps routing policy and decision logs local for inspection and tuning.
- Review scope: The roughly 60% saving is the author’s list-price replay estimate over 237 turns with fixed Token counts, excluding cross-model cache invalidation. It is not a reduction in a paid bill and was not independently retested.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-codex-router/
- Source evidence: https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/server/jev_server.py
- Source evidence: https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/README.md
- Source evidence: https://github.com/0xNatoshi/jev-codex-router/blob/8292b519659280884627a962c826ac7721136a64/BACKTEST.md

## Winnow

A context filter for Claude Code that hides irrelevant tool-output blocks and keeps the original text available for recall.

- Repository: https://github.com/GhalebDweikat/winnow
- Category: Context GC & Filter
- Jev decision: Jev scores whether Read, Bash and Grep output blocks are needed; local thresholds keep relevant or uncertain blocks.
- Purpose: Reduces visible output while retaining a way to retrieve hidden text.
- Review scope: Jev is the default judge, with a Haiku adapter available. Benefits and false-removal risks depend on workload and thresholds; not retested here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/winnow/
- Source evidence: https://github.com/GhalebDweikat/winnow/blob/51d80b945c74c8384bc47fa817179f668289afd8/README.md
- Source evidence: https://github.com/GhalebDweikat/winnow/blob/51d80b945c74c8384bc47fa817179f668289afd8/docs/experiments/jevlike_experiment.py
- Source evidence: https://github.com/GhalebDweikat/winnow/blob/51d80b945c74c8384bc47fa817179f668289afd8/sidecar/src/winnow/judge.py

## Jev Review

Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.

- Repository: https://github.com/devagrawal09/jev-review
- Category: Codebase & Graph Pathfinding
- Jev decision: Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.
- Purpose: Connects review leads to concrete code for human inspection.
- Review scope: The implementation does not route only high-risk changes to a larger model. Findings are review leads, not proof of defects; compute savings were not established. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-review/
- Source evidence: https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/src/review/judgments.ts#L38
- Source evidence: https://github.com/devagrawal09/jev-review/blob/31f89602797fb7bea007f8a480bf368bf564954e/README.md

## Blink

Finds files from a natural-language query using multiple walkers through the directory tree.

- Repository: https://github.com/ellipsis-dev/blink
- Category: Codebase & Graph Pathfinding
- Jev decision: Jev scores file and directory names; code distributes walkers using those probabilities.
- Purpose: Searches without a vector index and reports the share of walkers reaching each path.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/blink/
- Source evidence: https://github.com/ellipsis-dev/blink/blob/a621ede75649303a933828c18c27ad800bb43ef0/README.md
- Source evidence: https://github.com/ellipsis-dev/blink/blob/a621ede75649303a933828c18c27ad800bb43ef0/src/search.ts
- Source evidence: https://github.com/ellipsis-dev/blink/blob/a621ede75649303a933828c18c27ad800bb43ef0/src/walkers.ts

## neo4jev

Navigates a Neo4j graph one hop at a time, asking Jev which relationship to follow next.

- Repository: https://github.com/jexp/neo4jev
- Category: Codebase & Graph Pathfinding
- Jev decision: Choice scores neighboring relationships and Noul checks goal completion; local beam search retains candidate paths.
- Purpose: Connects a natural-language goal to inspectable graph paths.
- Review scope: A graph-navigation demo with explicitly labeled substitute answers when no API key is available. Large-graph speedup claims have not been verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/neo4jev/
- Source evidence: https://github.com/jexp/neo4jev/blob/d157bbe496eb91813475156942bef1c6badfb342/src/neo4jev/navigator.py
- Source evidence: https://github.com/jexp/neo4jev/blob/d157bbe496eb91813475156942bef1c6badfb342/README.md

## jev-desktop

An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.

- Repository: https://github.com/lahfir/agent-desktop
- Category: Browser & OS Action
- Jev decision: Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.
- Purpose: Keeps the full UI tree out of the main Agent context while exposing the selected action.
- Review scope: The separate Jev scripts were inspected; desktop behavior and end-to-end latency were not tested here.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jev-desktop/
- Source evidence: https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/README.md
- Source evidence: https://github.com/lahfir/agent-desktop/blob/7a8e4a10281c7319733aa200fd79501f34529716/scripts/jev/act.mjs

## TypeSafe AI Playground

Rust CLI experiments for health-information screening, comment review, tone analysis and business or occupation classification.

- Repository: https://github.com/markjaquith/typesafe-ai-playground
- Category: CLI & Pipelines
- Jev decision: Sends text to Jev for separate Noul probabilities, scores or category choices.
- Purpose: Offers a terminal interface for inspecting structured judgments.
- Review scope: Health-information scores are screening signals, not a legal PHI determination. The previous sub-millisecond claim had no supporting evidence. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/typesafe-ai-playground/
- Source evidence: https://github.com/markjaquith/typesafe-ai-playground/blob/344d77450e1cf3d7aebd2c9566b362b9c693b8e2/src/typesafe.rs#L57
- Source evidence: https://github.com/markjaquith/typesafe-ai-playground/blob/344d77450e1cf3d7aebd2c9566b362b9c693b8e2/README.md
- Source evidence: https://github.com/markjaquith/typesafe-ai-playground/blob/344d77450e1cf3d7aebd2c9566b362b9c693b8e2/data/README.md

## Prism

A Solana liquidity Agent with Jev shadow judgments compared against rule-based decisions.

- Repository: https://github.com/irfndi/prism-liquidity-agent
- Category: Domain & Vertical Tools
- Jev decision: Evaluates entry distribution, toxic flow, holding and stress signals for calibration logs.
- Purpose: Adds comparable advisory signals to deterministic trading rules without claiming returns.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/prism-liquidity-agent/
- Source evidence: https://github.com/irfndi/prism-liquidity-agent/blob/22c67bdbe30bab608226832256a5013ad826b707/README.md
- Source evidence: https://github.com/irfndi/prism-liquidity-agent/blob/22c67bdbe30bab608226832256a5013ad826b707/engine/jev-service.ts
- Source evidence: https://github.com/irfndi/prism-liquidity-agent/blob/22c67bdbe30bab608226832256a5013ad826b707/engine/jev-gate.ts

## OneVOneJev

A browser-based 1v1 shooter where Jev reads structured match state and chooses movement, aim, and firing.

- Repository: https://github.com/emrickgarrett/OneVOneJev
- Category: High-Frequency & Simulation
- Jev decision: Each decision tick asks about movement, view, aiming, firing, and jumping, with a heuristic fallback on API failure.
- Purpose: Makes structured decisions visible in an interactive game loop.
- Review scope: The README’s roughly 9 Hz refers to the configured decision tick, not independently measured sustained API throughput. A heuristic fallback exists; this site has not retested it.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/one-v-one-jev/
- Source evidence: https://github.com/emrickgarrett/OneVOneJev/blob/365b339d04446836352687b3650762106ea37f17/server/src/jev.ts
- Source evidence: https://github.com/emrickgarrett/OneVOneJev/blob/365b339d04446836352687b3650762106ea37f17/README.md

## safer-with-jev

An HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.

- Repository: https://github.com/andrelandgraf/safer-with-jev
- Category: Security & Guardrails
- Jev decision: Jev judges prompt injection or unsafe content; local rules forward, flag or block the request.
- Purpose: Adds an inspectable content check ahead of an existing HTTP service.
- Review scope: Renamed to safer-with-jev. The code implements content checks, not a guarantee of safety or zero latency.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/typesafe-on-neon/
- Source evidence: https://github.com/andrelandgraf/safer-with-jev/blob/b4fb82b129caa46480de6a66387ea2ff053c6511/README.md
- Source evidence: https://github.com/andrelandgraf/safer-with-jev/blob/b4fb82b129caa46480de6a66387ea2ff053c6511/web/src/components/JevIntro.tsx
- Source evidence: https://github.com/andrelandgraf/safer-with-jev/blob/b4fb82b129caa46480de6a66387ea2ff053c6511/src/lib/judge.ts

## fast-jev-compaction

Prunes old tool calls and outputs for Claude Code while retaining surviving text verbatim.

- Repository: https://github.com/tamaratran/fast-jev-compaction
- Category: Context GC & Filter
- Jev decision: Separately judges whether a tool call and its full output are still needed; code keeps, truncates or drops them.
- Purpose: Avoids rewriting paths, commands and errors into a new summary.
- Review scope: Requests are split to fit budgets, rather than always using one call. Pruning can remove useful context; the animation is not a live API benchmark. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tamaratran/fast-jev-compaction/
- Source evidence: https://github.com/tamaratran/fast-jev-compaction/blob/e3f262a7f4d42bd8dd32ced30d26176f7cb545b0/src/client.ts#L1
- Source evidence: https://github.com/tamaratran/fast-jev-compaction/blob/e3f262a7f4d42bd8dd32ced30d26176f7cb545b0/README.md
- Source evidence: https://github.com/tamaratran/fast-jev-compaction/blob/e3f262a7f4d42bd8dd32ced30d26176f7cb545b0/hooks/README.md

## jev-review

A local MCP code-quality reviewer returning structured scores to coding Agents.

- Repository: https://github.com/NiazMorshed2007/jev-review
- Category: Evaluation & Observability
- Jev decision: Jev scores correctness, complexity, tests and security; code ranks areas to improve.
- Purpose: Compares scores across checkpoints while leaving code changes to the primary Agent.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/niazmorshed2007/jev-review/
- Source evidence: https://github.com/NiazMorshed2007/jev-review/blob/57690af54ef7d862c2483342c1e61c14dffcf727/README.md
- Source evidence: https://github.com/NiazMorshed2007/jev-review/blob/57690af54ef7d862c2483342c1e61c14dffcf727/src/jev/client.ts
- Source evidence: https://github.com/NiazMorshed2007/jev-review/blob/57690af54ef7d862c2483342c1e61c14dffcf727/src/evaluation/review.ts
- Source evidence: https://github.com/NiazMorshed2007/jev-review/blob/57690af54ef7d862c2483342c1e61c14dffcf727/src/evaluation/transform.ts

## pg-jev

Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.

- Repository: https://github.com/realZachi/pg-jev
- Category: Data & Search
- Jev decision: Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.
- Purpose: Combines semantic conditions with existing SQL and reuses cached results.
- Review scope: Row content is sent to an external API. The author’s small-sample timing and cache-hit timing are not general model-inference benchmarks.
- License: PostgreSQL
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/realzachi/pg-jev/
- Source evidence: https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/sql/jev--0.2.0.sql
- Source evidence: https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/README.md
- Source evidence: https://github.com/realZachi/pg-jev/blob/afd11fa856d7a2b831a1bfd8ee7f869ce8efcd62/LICENSE

## jevpilot

A browser driving simulator where Jev chooses among locally generated paths and speeds.

- Repository: https://github.com/standardagents/jevpilot
- Category: High-Frequency & Simulation
- Jev decision: Jev reads road and traffic state and selects motion; geometry, collision prediction and braking remain local.
- Purpose: Makes candidate trajectories and decision probabilities visible during a simulation.
- Review scope: A driving simulation demo. Request frequency describes the author’s scheduler, not real-world autonomous-driving capability; not retested here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/standardagents/jevpilot/
- Source evidence: https://github.com/standardagents/jevpilot/blob/e1beeb13b9a928fb76f167f86af584f4ce9cf180/README.md
- Source evidence: https://github.com/standardagents/jevpilot/blob/e1beeb13b9a928fb76f167f86af584f4ce9cf180/src/jev-request.js
- Source evidence: https://github.com/standardagents/jevpilot/blob/e1beeb13b9a928fb76f167f86af584f4ce9cf180/server/jev.js

## jev-browser

Drives a browser from a task and URL, returning the final page, screenshot and action trace.

- Repository: https://github.com/jkudish/jev-browser
- Category: Browser & OS Action
- Jev decision: Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.
- Purpose: Records proposed actions, execution and stop reasons for inspection.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jkudish/jev-browser/
- Source evidence: https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/src/navigate.ts#L1
- Source evidence: https://github.com/jkudish/jev-browser/blob/8d90c51bedbe7cd07596bfaa532ded019a31d2a8/README.md

## pi-jev

A Pi extension that flags tool risks before execution and checks output for secrets and failure types.

- Repository: https://github.com/y0usaf/pi-jev
- Category: Security & Guardrails
- Jev decision: Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.
- Purpose: Defaults to shadow mode and fails open on API errors; it is not a standalone security boundary.
- Review scope: Defaults to shadow mode and fails open on API errors; source review is not a security validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/y0usaf/pi-jev/
- Source evidence: https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/README.md
- Source evidence: https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/src/client.ts
- Source evidence: https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/src/gate.ts
- Source evidence: https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/src/index.ts
- Source evidence: https://github.com/y0usaf/pi-jev/blob/b3478fd4ca1ac8ffcb703f6dc8d6069b555f531e/src/output.ts

## pi-jev-auto-mode

Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.

- Repository: https://github.com/jomatsu/pi-jev-auto-mode
- Category: Security & Guardrails
- Jev decision: Local rules handle explicit denies and allows before Jev assesses authorization and risk for bash, write, and edit.
- Purpose: Keeps policy and decision records available for adjusting operation gates.
- Review scope: Uncertain cases are denied by default, but uncertain=allow can be configured. Model judgments and thresholds do not guarantee protection; this site has not verified effectiveness.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jomatsu/pi-jev-auto-mode/
- Source evidence: https://github.com/jomatsu/pi-jev-auto-mode/blob/06a56043088124ed650471a8589fddd8139708f4/src/jev/transport.ts
- Source evidence: https://github.com/jomatsu/pi-jev-auto-mode/blob/06a56043088124ed650471a8589fddd8139708f4/README.md

## Jev-Trades

A dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.

- Repository: https://github.com/zadescoxp/Jev-Trades
- Category: Domain & Vertical Tools
- Jev decision: Jev reviews completed minute candles and indicators; Python applies confidence and position limits to a simulated portfolio.
- Purpose: Shows market inputs, model judgments and paper positions together.
- Review scope: The README explicitly describes paper trading with shared in-memory portfolio state, not evidence of profitability or live-trading readiness.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/zadescoxp/jev-trades/
- Source evidence: https://github.com/zadescoxp/Jev-Trades/blob/01fb18e4484d626f03345eaff2b93b641677b786/README.md
- Source evidence: https://github.com/zadescoxp/Jev-Trades/blob/01fb18e4484d626f03345eaff2b93b641677b786/app/page.tsx
- Source evidence: https://github.com/zadescoxp/Jev-Trades/blob/01fb18e4484d626f03345eaff2b93b641677b786/pipeline/paper_trader.py

## jev

Integrates Jev as an asynchronous Elixir/OTP process whose replies are handled with GenServer pattern matching.

- Repository: https://github.com/dannote/jev
- Category: SDK & Decision Frameworks
- Jev decision: Sends state and typed questions to TypeSafe, then delivers answers as messages.
- Purpose: Fits decision calls into existing message-handling and supervision patterns.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/dannote/jev/
- Source evidence: https://github.com/dannote/jev/blob/09fbb6cbaf32257924c08ba993ca8631adc16056/lib/jev/http.ex#L3
- Source evidence: https://github.com/dannote/jev/blob/09fbb6cbaf32257924c08ba993ca8631adc16056/README.md

## jev-mcp

Wraps Jev classification, scoring, yes/no judgments and candidate matching as MCP tools.

- Repository: https://github.com/blakestone-x/jev-mcp
- Category: MCP & Integrations
- Jev decision: The MCP server calls the TypeSafe SDK and returns choices, probabilities and scores.
- Purpose: Provides a shared decision interface for MCP-compatible clients.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/blakestone-x/jev-mcp/
- Source evidence: https://github.com/blakestone-x/jev-mcp/blob/59289a0b472a3ebc3e9abfebba2d59ec2c881863/README.md
- Source evidence: https://github.com/blakestone-x/jev-mcp/blob/59289a0b472a3ebc3e9abfebba2d59ec2c881863/jev_mcp/client.py
- Source evidence: https://github.com/blakestone-x/jev-mcp/blob/59289a0b472a3ebc3e9abfebba2d59ec2c881863/jev_mcp/server.py

## HA-Jev

Turns Jev judgments into Home Assistant sensors, such as checking whether finished laundry has been left unattended.

- Repository: https://github.com/AboveColin/HA-Jev
- Category: Domain & Vertical Tools
- Jev decision: Reads selected entity states and returns probabilities, choices, or scores that configured thresholds can use in automations.
- Purpose: Connects natural-language conditions to existing sensors, notifications, and scenes.
- Review scope: The author explicitly advises against safety-critical controls such as locks, heaters, or smoke alarms. This site has not verified latency or judgment accuracy.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abovecolin/ha-jev/
- Source evidence: https://github.com/AboveColin/HA-Jev/blob/1b48f2fa1e94d076b54082f889f04b0083bcd1a8/custom_components/jev/coordinator.py
- Source evidence: https://github.com/AboveColin/HA-Jev/blob/1b48f2fa1e94d076b54082f889f04b0083bcd1a8/README.md

## jev-benchmarks

A benchmark comparing Jev and GLiNER on text classification, probability calibration and selective automation.

- Repository: https://github.com/AbdelStark/jev-benchmarks
- Category: Evaluation & Observability
- Jev decision: Runs the same labeled text tasks through both backends and records probabilities, latency and failures.
- Purpose: Helps examine task-specific accuracy and whether confidence scores support chosen thresholds.
- Review scope: The author reports a 300-example pilot. Hosted Jev and local GLiNER timings are not hardware-normalized; this site did not rerun it.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abdelstark/jev-benchmarks/
- Source evidence: https://github.com/AbdelStark/jev-benchmarks/blob/0d610cc53e79bcbec691312b0c4adb4a0e371642/README.md
- Source evidence: https://github.com/AbdelStark/jev-benchmarks/blob/0d610cc53e79bcbec691312b0c4adb4a0e371642/src/jev_benchmarks/io.py
- Source evidence: https://github.com/AbdelStark/jev-benchmarks/blob/0d610cc53e79bcbec691312b0c4adb4a0e371642/src/jev_benchmarks/adapters/jev.py

## Jevbridge

Exposes a shared structured-decision interface for Jev and other models through ACP, MCP and a CLI.

- Repository: https://github.com/gamesonrblx/Jevbridge
- Category: MCP & Integrations
- Jev decision: Sends state and bounded questions to the chosen backend, with an offline rule backend also available.
- Purpose: Lets agents compare or replace decision backends through one interface.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/gamesonrblx/jevbridge/
- Source evidence: https://github.com/gamesonrblx/Jevbridge/blob/54c5587565cb346788d67805ef2412f46a21bb33/src/client.ts#L1
- Source evidence: https://github.com/gamesonrblx/Jevbridge/blob/54c5587565cb346788d67805ef2412f46a21bb33/README.md
- Source evidence: https://github.com/gamesonrblx/Jevbridge/blob/54c5587565cb346788d67805ef2412f46a21bb33/brand/README.md
- Source evidence: https://github.com/gamesonrblx/Jevbridge/blob/54c5587565cb346788d67805ef2412f46a21bb33/src/types.ts

## jev-playground

A MoonBit and TypeScript Jev playground covering games, browsers, command risk and small languages.

- Repository: https://github.com/mizchi/jev-playground
- Category: Evaluation & Observability
- Jev decision: Experiments send action candidates or typed questions to Jev, then execute or record the answers.
- Purpose: Includes source, experiment notes and some offline replays for comparing decision designs.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/mizchi/jev-playground/
- Source evidence: https://github.com/mizchi/jev-playground/blob/92701bb053ffcec7bb77f23f26b6b1b01ad83f8b/README.md
- Source evidence: https://github.com/mizchi/jev-playground/blob/92701bb053ffcec7bb77f23f26b6b1b01ad83f8b/lib/client.mbt
- Source evidence: https://github.com/mizchi/jev-playground/blob/92701bb053ffcec7bb77f23f26b6b1b01ad83f8b/cmd/gomoku/main.mbt
- Source evidence: https://github.com/mizchi/jev-playground/blob/92701bb053ffcec7bb77f23f26b6b1b01ad83f8b/cmd/jev/main.mbt

## zod-jev

Adds semantic rules to Zod validation, such as checking whether text matches a description or contains personal information.

- Repository: https://github.com/jomatsu/zod-jev
- Category: SDK & Decision Frameworks
- Jev decision: Combines semantic conditions from one parse into Jev Noul questions and maps probabilities to validation results.
- Purpose: Uses Zod’s error structure to attach semantic validation issues to fields.
- Review scope: This is a semantic validation library for Zod, not an MCP server. Uncertainty or service unavailability fails validation, but privacy detection and business judgments are not guaranteed accurate.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jomatsu/zod-jev/
- Source evidence: https://github.com/jomatsu/zod-jev/blob/700bd256fe94541a2d21044027cc2dbf5036b396/src/judge.ts
- Source evidence: https://github.com/jomatsu/zod-jev/blob/700bd256fe94541a2d21044027cc2dbf5036b396/README.md

## jev-lm

A word-level generation experiment that asks Jev to select words or verify locally drafted continuations.

- Repository: https://github.com/y0usaf/jev-lm
- Category: Evaluation & Observability
- Jev decision: Choice selects the next word; Noul evaluates candidate chunks and stopping conditions.
- Purpose: Exposes the limitations of using a decision model as a text generator.
- Review scope: A research prototype whose reported small-vocabulary evaluation did not beat a unigram baseline; not a general language-model replacement or independently retested here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/y0usaf/jev-lm/
- Source evidence: https://github.com/y0usaf/jev-lm/blob/05e7f03bf447073a0bed3255d4de154f953e533d/README.md
- Source evidence: https://github.com/y0usaf/jev-lm/blob/05e7f03bf447073a0bed3255d4de154f953e533d/python/jev_lm/api.py

## jev-search

Searches the web with Jev choosing sources and time ranges, then ranking returned links.

- Repository: https://github.com/superagents-lab/jev-search
- Category: Data & Search
- Jev decision: Judges search intent, source and time settings, and relevance of individual results.
- Purpose: Keeps links, snippets, editable filters and source-failure warnings visible.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/superagents-lab/jev-search/
- Source evidence: https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/src/lib/typesafe.ts#L48
- Source evidence: https://github.com/superagents-lab/jev-search/blob/522868762f0637b20bf533f136e930cceb83b9f3/README.md

## live-jev

A browser-based top-down driving simulator using Jev for lane and speed choices, with an optional chat-model comparison.

- Repository: https://github.com/vinilana/live-jev
- Category: High-Frequency & Simulation
- Jev decision: Jev answers lane, speed, hazard and pedestrian-yield questions; local rules apply the actions.
- Purpose: Runs controllers on the same seeded course, with separate local emergency-braking logic.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vinilana/live-jev/
- Source evidence: https://github.com/vinilana/live-jev/blob/cd13ab0a7b58ca9b6749a78aed2a729153fa6910/README.md
- Source evidence: https://github.com/vinilana/live-jev/blob/cd13ab0a7b58ca9b6749a78aed2a729153fa6910/server.js
- Source evidence: https://github.com/vinilana/live-jev/blob/cd13ab0a7b58ca9b6749a78aed2a729153fa6910/public/js/brain.js
- Source evidence: https://github.com/vinilana/live-jev/blob/cd13ab0a7b58ca9b6749a78aed2a729153fa6910/public/js/car.js

## jev-code

Helps coding Agents locate code, check change intent, triage test failures, and organize review findings.

- Repository: https://github.com/devagrawal09/jev-code
- Category: Codebase & Graph Pathfinding
- Jev decision: Selects a fixed workflow and makes structured judgments over bounded diffs, code, or log excerpts.
- Purpose: Returns inspectable leads and states which parts were not checked.
- Review scope: Outputs are advisory reports, not pass or approval certificates. Source and npm release status may differ.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/devagrawal09/jev-code/
- Source evidence: https://github.com/devagrawal09/jev-code/blob/fd092558ebea389c81d44f9b10e826d9a72afaa3/src/adapters/jev.ts
- Source evidence: https://github.com/devagrawal09/jev-code/blob/fd092558ebea389c81d44f9b10e826d9a72afaa3/README.md

## daf-jev

A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.

- Repository: https://github.com/docxology/daf-jev
- Category: SDK & Decision Frameworks
- Jev decision: Builds Noul, Choice and Score questions, then combines returned probabilities through local functions.
- Purpose: Reuses request, failure-recording and evaluation interfaces across experiments.
- Review scope: Source and docs cover the client, Evaluator and MCP tools; the author’s batch-performance results were not reproduced here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/docxology/daf-jev/
- Source evidence: https://github.com/docxology/daf-jev/blob/ff7b28515d7f60c9f7182b128b76b90fbfcba66f/README.md
- Source evidence: https://github.com/docxology/daf-jev/blob/ff7b28515d7f60c9f7182b128b76b90fbfcba66f/src/daf_jev/client.py

## jev-chat

A research chat decoder that repeatedly asks Jev to choose words or phrases and assembles them in code.

- Repository: https://github.com/adhyaay-karnwal/jev-chat
- Category: Evaluation & Observability
- Jev decision: Compares stepwise Choice decoding with selection from complete candidate replies.
- Purpose: Provides decoder methods, experiment traces and documented failure cases.
- Review scope: The author states that autoregressive decoding is not Jev’s intended use and documents repetitions and grammatical errors. This is a research decoder. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/adhyaay-karnwal/jev-chat/
- Source evidence: https://github.com/adhyaay-karnwal/jev-chat/blob/fb92fd33ddd6603aa544fe4988dd8e918f91d6ca/src/jevchat/client.py#L40
- Source evidence: https://github.com/adhyaay-karnwal/jev-chat/blob/fb92fd33ddd6603aa544fe4988dd8e918f91d6ca/README.md
- Source evidence: https://github.com/adhyaay-karnwal/jev-chat/blob/fb92fd33ddd6603aa544fe4988dd8e918f91d6ca/experiments/README.md

## jev-cli

A CLI and stdio MCP server for typed Jev judgments over text or JSON.

- Repository: https://github.com/tumf/jev-cli
- Category: CLI & Pipelines
- Jev decision: Submits noul, choice and score questions and emits JSON or a primary value.
- Purpose: Accepts files and stdin for use in shell scripts and MCP clients.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tumf/jev-cli/
- Source evidence: https://github.com/tumf/jev-cli/blob/60441de4f96870686a5388bd6ed714f36eed646b/README.md
- Source evidence: https://github.com/tumf/jev-cli/blob/60441de4f96870686a5388bd6ed714f36eed646b/src/jev_cli/__init__.py
- Source evidence: https://github.com/tumf/jev-cli/blob/60441de4f96870686a5388bd6ed714f36eed646b/src/jev_cli/mcp_server.py

## AskJev

Connects Agents to a browser over MCP, using Jev to choose page actions with confirmation gates for actions such as payment or deletion.

- Repository: https://github.com/ranjan2829/AskJev
- Category: Browser & OS Action
- Jev decision: Selects actions from current page controls and assesses risk and irreversibility.
- Purpose: Combines automated page actions with user confirmation in one workflow.
- Review scope: Confirmation logic is an additional check, not a guarantee against all dangerous actions. This site has not tested it in a browser.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ranjan2829/askjev/
- Source evidence: https://github.com/ranjan2829/AskJev/blob/7beec5eba7c4a294d21013c158cd884e1c24f08b/mcp/src/jev-client.ts
- Source evidence: https://github.com/ranjan2829/AskJev/blob/7beec5eba7c4a294d21013c158cd884e1c24f08b/README.md

## jev-for-engineers

Eight mechanical and electrical engineering experiments using Jev for task routing, log checks and component selection.

- Repository: https://github.com/Foadsf/jev-for-engineers
- Category: Domain & Vertical Tools
- Jev decision: Jev classifies engineering text and candidates; calculations and final actions stay in Python rules.
- Purpose: Shows how to connect judgments to engineering workflows using synthetic examples.
- Review scope: Inputs are synthetic and do not establish production thresholds or engineering safety.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/foadsf/jev-for-engineers/
- Source evidence: https://github.com/Foadsf/jev-for-engineers/blob/181e75208ac3b982c80889267a28a1ed718452a9/README.md
- Source evidence: https://github.com/Foadsf/jev-for-engineers/blob/181e75208ac3b982c80889267a28a1ed718452a9/jev.py

## jev-system-one

A terminal Q&A app where OpenAI writes answers and Jev sets response policy and reviews drafts.

- Repository: https://github.com/haseeb-heaven/jev-system-one
- Category: Voice & Conversation
- Jev decision: Judges response mode, depth, uncertainty and draft quality inside a LangGraph workflow.
- Purpose: Displays the answer alongside a structured decision report.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/haseeb-heaven/jev-system-one/
- Source evidence: https://github.com/haseeb-heaven/jev-system-one/blob/66bbfb66556e6daa0f091a04b4e33c3a314eec28/src/jev_system_one/jev.py#L164
- Source evidence: https://github.com/haseeb-heaven/jev-system-one/blob/66bbfb66556e6daa0f091a04b4e33c3a314eec28/README.md

## JevBird

A Python Flappy Bird game where code simulates candidate routes and Jev picks one.

- Repository: https://github.com/leftspace89/JevBird
- Category: High-Frequency & Simulation
- Jev decision: For each new pipe, Jev selects a route and the game executes its scheduled flaps.
- Purpose: Visualizes candidate trajectories, probabilities and the selected path.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/leftspace89/jevbird/
- Source evidence: https://github.com/leftspace89/JevBird/blob/1e5fd1397382be91ce74ed0ab0cba86027c3470a/README.md
- Source evidence: https://github.com/leftspace89/JevBird/blob/1e5fd1397382be91ce74ed0ab0cba86027c3470a/jev_pilot.py
- Source evidence: https://github.com/leftspace89/JevBird/blob/1e5fd1397382be91ce74ed0ab0cba86027c3470a/flappy_bird.py

## jev-judgment

Adds judgment checks for authorization, operation risk, and failure causes to coding Agents.

- Repository: https://github.com/HyunjunJeon/jev-judgment
- Category: Security & Guardrails
- Jev decision: Uses conversation and command results to assess whether to ask the user, whether an action exceeds scope, and whether to retry.
- Purpose: Makes checkpoints that may require user confirmation explicit.
- Review scope: Model probabilities do not replace user authorization. Missing keys or network failures may leave the original workflow running.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hyunjunjeon/jev-judgment/
- Source evidence: https://github.com/HyunjunJeon/jev-judgment/blob/f6056e7cd31d467d6773a0737731c85939499e5e/skills/jev-judgment/scripts/jev.py
- Source evidence: https://github.com/HyunjunJeon/jev-judgment/blob/f6056e7cd31d467d6773a0737731c85939499e5e/README.md

## jev-cli

A CLI for asking Jev classification, yes/no and scoring questions over text or JSON input.

- Repository: https://github.com/jtsang4/jev-cli
- Category: CLI & Pipelines
- Jev decision: Evaluates typed questions over one input and returns choices and probabilities as JSON.
- Purpose: Accepts standard input and supports direct TypeSafe calls or a Vercel gateway.
- Review scope: The CLI and provider interfaces were inspected; latency, accuracy and cost were not measured here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jtsang4/jev-cli/
- Source evidence: https://github.com/jtsang4/jev-cli/blob/6ea8abdf702d2fc28bfffd979e83db8c32f3ceb5/README.md
- Source evidence: https://github.com/jtsang4/jev-cli/blob/6ea8abdf702d2fc28bfffd979e83db8c32f3ceb5/src/providers/jev.ts

## claude-jev

Adds Jev checks to Claude Code review findings, debugging hypotheses, design options and search results.

- Repository: https://github.com/buchmark/claude-jev
- Category: Codebase & Graph Pathfinding
- Jev decision: Scores candidate defects, explanations or options against preset questions and local policies.
- Purpose: Keeps a second judgment and its probabilities available for comparison.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/buchmark/claude-jev/
- Source evidence: https://github.com/buchmark/claude-jev/blob/06fe407f2894bc5c44f2dfc41e05d3592e5215a5/src/infrastructure/typesafe-jev.ts#L114
- Source evidence: https://github.com/buchmark/claude-jev/blob/06fe407f2894bc5c44f2dfc41e05d3592e5215a5/README.md

## jev-browser

Playwright browser automation with Jev decisions through a shared CLI, MCP server and TypeScript SDK.

- Repository: https://github.com/tontoko/jev-browser
- Category: Browser & OS Action
- Jev decision: Jev chooses actions, matches form fields or extracts structured content from page observations; Playwright executes.
- Purpose: Supports persistent sessions and UI readback, which does not by itself prove database persistence.
- Review scope: Reviewed the fixed-version README and call path.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tontoko/jev-browser/
- Source evidence: https://github.com/tontoko/jev-browser/blob/05b8257db8d7df77a82274016de84d965a38214f/README.ja.md
- Source evidence: https://github.com/tontoko/jev-browser/blob/05b8257db8d7df77a82274016de84d965a38214f/README.md
- Source evidence: https://github.com/tontoko/jev-browser/blob/05b8257db8d7df77a82274016de84d965a38214f/src/decision.ts
- Source evidence: https://github.com/tontoko/jev-browser/blob/05b8257db8d7df77a82274016de84d965a38214f/src/browser.ts
- Source evidence: https://github.com/tontoko/jev-browser/blob/05b8257db8d7df77a82274016de84d965a38214f/src/actions.ts

## pi-jev

Helps Pi Agents find tools and skills for a task, with structured evaluation and optional history filtering.

- Repository: https://github.com/TheoOliveira/pi-jev
- Category: MCP & Integrations
- Jev decision: Judges how candidate tools, skills, and history relate to the task so local rules can load or retain them.
- Purpose: Lets capabilities enter an Agent workflow on demand.
- Review scope: This is a Pi extension; exposing tools does not by itself make it an MCP server. Automatic modes require configuration.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/theooliveira/pi-jev/
- Source evidence: https://github.com/TheoOliveira/pi-jev/blob/0c3ac04bb5e039e7a334e8e79c8ad471a7a1b67c/src/jev.ts
- Source evidence: https://github.com/TheoOliveira/pi-jev/blob/0c3ac04bb5e039e7a334e8e79c8ad471a7a1b67c/README.md

## jev-tree

A hierarchical selector that asks Jev to traverse branches when a catalog has too many options for one question.

- Repository: https://github.com/reachjalil/jev-tree
- Category: Classification & Taxonomy
- Jev decision: Selects one branch at each level and continues until it reaches a final candidate.
- Purpose: Returns the selected path without silently truncating the tail of a large catalog.
- Review scope: The hierarchical selection implementation is inspectable; reported evaluations use synthetic data and were not rerun on real workloads here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/reachjalil/jev-tree/
- Source evidence: https://github.com/reachjalil/jev-tree/blob/95bff63bd653fee4dc71f33f9431dce0f81e2ca3/README.md
- Source evidence: https://github.com/reachjalil/jev-tree/blob/95bff63bd653fee4dc71f33f9431dce0f81e2ca3/src/index.ts

## jev-starter

TypeScript patterns for thresholds, fallbacks, human review and evaluation on top of the TypeSafe SDK.

- Repository: https://github.com/hamakyo/jev-starter
- Category: SDK & Decision Frameworks
- Jev decision: Jev returns judgments; application policies choose automatic handling, fallback or human review.
- Purpose: Separates model calls, execution policy and evaluation.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hamakyo/jev-starter/
- Source evidence: https://github.com/hamakyo/jev-starter/blob/fb0fae07d1f3052f28af630b942c16b2a7bd8c88/src/providers/jev-provider.ts#L43
- Source evidence: https://github.com/hamakyo/jev-starter/blob/fb0fae07d1f3052f28af630b942c16b2a7bd8c88/README.md
- Source evidence: https://github.com/hamakyo/jev-starter/blob/fb0fae07d1f3052f28af630b942c16b2a7bd8c88/README.ja.md

## aside-jev

An MCP server and skill adding Jev decisions to Aside browser Agents.

- Repository: https://github.com/himomohi/aside-jev
- Category: Browser & OS Action
- Jev decision: The Agent supplies action candidates; Jev picks an ID, then the Agent executes and verifies it through Aside.
- Purpose: Keeps choices within an application-owned action table while requiring separate outcome verification.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/himomohi/aside-jev/
- Source evidence: https://github.com/himomohi/aside-jev/blob/d2923f7949a9576e82b51d2c5e5514c17d80d60b/README.md
- Source evidence: https://github.com/himomohi/aside-jev/blob/d2923f7949a9576e82b51d2c5e5514c17d80d60b/src/aside_jev/jev.py
- Source evidence: https://github.com/himomohi/aside-jev/blob/d2923f7949a9576e82b51d2c5e5514c17d80d60b/src/aside_jev/loop.py

## jev-skill-gate

Ranks Claude Code skills for the current project to reduce the descriptions loaded by default.

- Repository: https://github.com/ShivamPansuriya/jev-skill-gate
- Category: Context GC & Filter
- Jev decision: Assesses skills against the project stack, directory, and README before adjusting description visibility.
- Purpose: Keeps relevant descriptions while preserving manual access to other skills.
- Review scope: Local scoring is available without a key. The author reports only partial Jev evaluation coverage; this site has not verified Token savings or effectiveness.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/shivampansuriya/jev-skill-gate/
- Source evidence: https://github.com/ShivamPansuriya/jev-skill-gate/blob/1ab4c9a7cd117e1c7e129021303416bb7c2f5328/src/jev.mjs
- Source evidence: https://github.com/ShivamPansuriya/jev-skill-gate/blob/1ab4c9a7cd117e1c7e129021303416bb7c2f5328/README.md

## jev-guard

Tool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.

- Repository: https://github.com/leepokai/jev-guard
- Category: Security & Guardrails
- Jev decision: Jev evaluates tool inputs or outputs in session context; local rules allow, warn or block.
- Purpose: Adds review points around Agent tools, with behavior depending on the host client.
- Review scope: Not a sandbox replacement. API failures allow operations by default and confirmation support varies by client; no penetration or end-to-end testing here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/leepokai/jev-guard/
- Source evidence: https://github.com/leepokai/jev-guard/blob/94996ea80b6b308327ac2077706a29ce6abd3ba0/README.md
- Source evidence: https://github.com/leepokai/jev-guard/blob/94996ea80b6b308327ac2077706a29ce6abd3ba0/src/jev.js

## jev-mcp

An MCP server and Claude Code plugin for Jev classification, scoring, checks and batched questions.

- Repository: https://github.com/rashedInt32/jev-mcp
- Category: MCP & Integrations
- Jev decision: Calls TypeSafe with Choice, Score and Noul questions and returns structured answers.
- Purpose: Makes the typed decision primitives available to MCP clients.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/rashedint32/jev-mcp/
- Source evidence: https://github.com/rashedInt32/jev-mcp/blob/27603c12d06cd7899d93c0fbb8ce9331040b8a8c/src/index.ts#L230
- Source evidence: https://github.com/rashedInt32/jev-mcp/blob/27603c12d06cd7899d93c0fbb8ce9331040b8a8c/README.md

## jevclient

An asynchronous Python Jev client that batches typed questions in one request.

- Repository: https://github.com/AboveColin/jevclient
- Category: SDK & Decision Frameworks
- Jev decision: Calls TypeSafe through aiohttp and parses choices, scores and probabilities into objects.
- Purpose: Fits existing async applications without parsing generated prose.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abovecolin/jevclient/
- Source evidence: https://github.com/AboveColin/jevclient/blob/d568f25717c5b956022f5dc0fcfcb905c7533a05/README.md
- Source evidence: https://github.com/AboveColin/jevclient/blob/d568f25717c5b956022f5dc0fcfcb905c7533a05/jevclient/client.py
- Source evidence: https://github.com/AboveColin/jevclient/blob/d568f25717c5b956022f5dc0fcfcb905c7533a05/jevclient/models.py

## jev-workbench

Defines, tests, and publishes Jev decision functions in a local UI so backends and Agents can call fixed versions.

- Repository: https://github.com/molis-ai/jev-workbench
- Category: MCP & Integrations
- Jev decision: Encodes classification or evidence checks as Noul, Choice, or Score questions sent to TypeSafe.
- Purpose: Lets multiple callers reuse the same versioned decision function.
- Review scope: The demo uses simulated answers; actual TypeSafe calls follow a separate path. This site has not verified each Agent integration or production behavior.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/molis-ai/jev-workbench/
- Source evidence: https://github.com/molis-ai/jev-workbench/blob/3d7d6f673d629a046f2e3d9b2f277095133a65c7/apps/server/src/provider.ts
- Source evidence: https://github.com/molis-ai/jev-workbench/blob/3d7d6f673d629a046f2e3d9b2f277095133a65c7/README.md

## jev-got

A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene.

- Repository: https://github.com/phureewat29/jev-got
- Category: Creative Tools
- Jev decision: Classifies location, narrative beat, mood, danger and whether text remains in fiction.
- Purpose: Uses explicit scene state to drive backgrounds, music and the next turn.
- Review scope: A noncommercial technical demo: Jev labels scenes rather than generating the story. The game was not run here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/phureewat29/got-jev/
- Source evidence: https://github.com/phureewat29/jev-got/blob/232fc0ad0cc6f4d4e095df71ac5f05b0f49033a9/README.md
- Source evidence: https://github.com/phureewat29/jev-got/blob/232fc0ad0cc6f4d4e095df71ac5f05b0f49033a9/src/core/providers/TypeSafe.ts

## pi-fast-jev-compaction

A Pi extension that prunes stale tool history verbatim and falls back to Pi summary compaction when needed.

- Repository: https://github.com/joelhooks/pi-fast-jev-compaction
- Category: Context GC & Filter
- Jev decision: Judges whether calls and outputs should survive in the context sent to the model.
- Purpose: Retains the original session file and records pruning decisions.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/joelhooks/pi-fast-jev-compaction/
- Source evidence: https://github.com/joelhooks/pi-fast-jev-compaction/blob/eb83f533f4fd10a08728b02c062c249afda5a4dc/src/core/request.ts#L8
- Source evidence: https://github.com/joelhooks/pi-fast-jev-compaction/blob/eb83f533f4fd10a08728b02c062c249afda5a4dc/README.md
- Source evidence: https://github.com/joelhooks/pi-fast-jev-compaction/blob/eb83f533f4fd10a08728b02c062c249afda5a4dc/src/core/decide.ts

## hermes-jev-approvals

An experimental Hermes command-approval provider for the auxiliary.approval task only.

- Repository: https://github.com/anpicasso/hermes-jev-approvals
- Category: Security & Guardrails
- Jev decision: Jev returns APPROVE, DENY or ESCALATE, with local thresholds and policy determining handling.
- Purpose: Demonstrates an approval integration; the author labels it a proof of concept, not production assurance.
- Review scope: The author labels this a proof of concept with offline benchmarks.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/anpicasso/hermes-jev-approvals/
- Source evidence: https://github.com/anpicasso/hermes-jev-approvals/blob/c41d81de23a79d8d69397cef81c4de99b3f987c5/README.md
- Source evidence: https://github.com/anpicasso/hermes-jev-approvals/blob/c41d81de23a79d8d69397cef81c4de99b3f987c5/plugin/__init__.py

## jev-research

A Jev and Herdr integration guide with a prototype for routing tasks to different Agents.

- Repository: https://github.com/sherajdev/jev-research
- Category: Routing & Cost Optimization
- Jev decision: Uses task and repository state to choose an executor and assess risk and dispatch readiness.
- Purpose: Provides a readable, editable example of multi-Agent task routing.
- Review scope: Primarily documentation and a dry-run routing prototype, not a verified operational orchestration platform.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/sherajdev/jev-research/
- Source evidence: https://github.com/sherajdev/jev-research/blob/23da0defeebe5dae232ba1aaa7ee3c0c3842cb8e/jev-router.ts
- Source evidence: https://github.com/sherajdev/jev-research/blob/23da0defeebe5dae232ba1aaa7ee3c0c3842cb8e/README.md

## jev-resilience

A Spring WebFlux integration that detects error messages hidden in HTTP 200 response bodies.

- Repository: https://github.com/Vicente-MD/jev-resilience
- Category: SDK & Integrations
- Jev decision: Jev checks for hidden errors or maintenance notices; a local threshold raises a business exception.
- Purpose: Lets existing error-handling code see failures concealed by the HTTP status.
- Review scope: Jev API integration is present. API errors fail open, and nonblocking code still incurs network latency.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vicente-md/jev-resilience/
- Source evidence: https://github.com/Vicente-MD/jev-resilience/blob/c490e0dc7830758f84bd9d5acb806655e327113e/README.md
- Source evidence: https://github.com/Vicente-MD/jev-resilience/blob/c490e0dc7830758f84bd9d5acb806655e327113e/src/main/java/ai/jev/resilience/client/dto/JevRequest.java
- Source evidence: https://github.com/Vicente-MD/jev-resilience/blob/c490e0dc7830758f84bd9d5acb806655e327113e/src/main/java/ai/jev/resilience/client/JevEvaluationService.java

## jev-go

A community Go SDK and CLI supporting TypeSafe directly and Vercel AI Gateway.

- Repository: https://github.com/Stumble/jev-go
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/stumble/jev-go/
- Source evidence: https://github.com/Stumble/jev-go/blob/a475dc925ba68602be93f4478e1381cf5ec27ee4/client.go#L23
- Source evidence: https://github.com/Stumble/jev-go/blob/a475dc925ba68602be93f4478e1381cf5ec27ee4/README.md

## jev-agent-failure-benchmark

A benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type.

- Repository: https://github.com/TokenTrim/jev-agent-failure-benchmark
- Category: Evaluation & Observability
- Jev decision: Builds candidate sets from traces and submits three choice questions.
- Purpose: Provides evaluation scripts and author results; some baselines generate answers while Jev selects candidates.
- Review scope: Some Jev benchmark axes use constrained choices while paper baselines generate freely; not every metric is a like-for-like comparison.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tokentrim/jev-agent-failure-benchmark/
- Source evidence: https://github.com/TokenTrim/jev-agent-failure-benchmark/blob/4d46af795a4a4409940a65857da73e45abaea2db/README.md
- Source evidence: https://github.com/TokenTrim/jev-agent-failure-benchmark/blob/4d46af795a4a4409940a65857da73e45abaea2db/src/jevbench/backends/jev.py
- Source evidence: https://github.com/TokenTrim/jev-agent-failure-benchmark/blob/4d46af795a4a4409940a65857da73e45abaea2db/RESULTS.md

## computer-use-jev

A Go-based macOS controller that asks Jev to choose controls and actions from the accessibility tree.

- Repository: https://github.com/paulsmith/computer-use-jev
- Category: Browser & OS Action
- Jev decision: Uses window state to select an action, target, text-input need, and completion status.
- Purpose: Grounds candidate controls in UI snapshots so choices can be inspected.
- Review scope: Requires macOS permissions and a TypeSafe key. Offline fake-worker and HTTP tests are not real desktop validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/paulsmith/computer-use-jev/
- Source evidence: https://github.com/paulsmith/computer-use-jev/blob/ff0ad8ba8e25755d37fb8d93718144c4568a596b/typesafe/client.go
- Source evidence: https://github.com/paulsmith/computer-use-jev/blob/ff0ad8ba8e25755d37fb8d93718144c4568a596b/README.md

## jev-broadcast-lab

A Jev experiment workbench centered on chess, with additional classification and matching exercises.

- Repository: https://github.com/4anti/jev-broadcast-lab
- Category: High-Frequency & Simulation
- Jev decision: Chooses from locally generated legal chess moves; Stockfish scores are shown to the operator rather than Jev.
- Purpose: Lets users compare model move choices with a separate local chess evaluation.
- Review scope: An experiment with local heuristic candidate filtering; displayed Elo is not a certified playing strength. Not run here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/4anti/jev-broadcast-lab/
- Source evidence: https://github.com/4anti/jev-broadcast-lab/blob/90ebea44467489e03c1fd2ab0416b54e32c25c13/README.md
- Source evidence: https://github.com/4anti/jev-broadcast-lab/blob/90ebea44467489e03c1fd2ab0416b54e32c25c13/web/shared/jev-client.js

## jevgo

A community Go client with a standard-library core and optional Langfuse tracing.

- Repository: https://github.com/fgn/jevgo
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/fgn/jevgo/
- Source evidence: https://github.com/fgn/jevgo/blob/ff7a543dda89cbd93e44d6d6535b1a7a62ffb882/client.go#L18
- Source evidence: https://github.com/fgn/jevgo/blob/ff7a543dda89cbd93e44d6d6535b1a7a62ffb882/README.md
- Source evidence: https://github.com/fgn/jevgo/blob/ff7a543dda89cbd93e44d6d6535b1a7a62ffb882/contrib/langfuse/README.md

## jev-little-airways

An island-airport simulator using Jev for routes, yielding, emergency broadcasts and landing order.

- Repository: https://github.com/lbotinelly/jev-little-airways
- Category: High-Frequency & Simulation
- Jev decision: Turns aircraft and nearby traffic state into questions whose answers drive simulated actions.
- Purpose: Shows requests, answers and simulation state, with a separate mock path available.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/lbotinelly/jev-little-airways/
- Source evidence: https://github.com/lbotinelly/jev-little-airways/blob/d6ec286c7821f41228bce9b33381546e4fca9bff/README.md
- Source evidence: https://github.com/lbotinelly/jev-little-airways/blob/d6ec286c7821f41228bce9b33381546e4fca9bff/demo/server.mjs
- Source evidence: https://github.com/lbotinelly/jev-little-airways/blob/d6ec286c7821f41228bce9b33381546e4fca9bff/demo/js/jev-provider.mjs
- Source evidence: https://github.com/lbotinelly/jev-little-airways/blob/d6ec286c7821f41228bce9b33381546e4fca9bff/demo/js/browser.mjs

## jev-playground

A web playground for entering state and decision questions, then inspecting Jev answers and probability distributions.

- Repository: https://github.com/Little-Planet-Labs/jev-playground
- Category: Decision Tools
- Jev decision: Submits multiple Noul, Choice, and Score questions in one request.
- Purpose: Lets users try questions and answer options before writing application code.
- Review scope: A real TypeSafe key is required for model calls. This site has not run inference or verified throughput or accuracy.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/little-planet-labs/jev-playground/
- Source evidence: https://github.com/Little-Planet-Labs/jev-playground/blob/418b723779569b1cb1f21a4f7f34c546d44c7e34/src/app/api/evaluate/route.ts
- Source evidence: https://github.com/Little-Planet-Labs/jev-playground/blob/418b723779569b1cb1f21a4f7f34c546d44c7e34/README.md

## laravel-typesafe-jev

A Laravel adapter for Jev with configuration, dependency injection, a Facade and a request-recording test fake.

- Repository: https://github.com/Butochnikov/laravel-typesafe-jev
- Category: SDK & Integrations
- Jev decision: Wraps a community PHP SDK for typed judgments and preserves promises and exceptions.
- Purpose: Fits Jev calls into Laravel services, queues and existing tests.
- Review scope: An unofficial framework adapter. Its fake makes no network calls, so mock tests do not validate the live API.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/butochnikov/laravel-typesafe-jev/
- Source evidence: https://github.com/Butochnikov/laravel-typesafe-jev/blob/4d70f5e1b059aac2f63105e72626802247a51f45/README.md
- Source evidence: https://github.com/Butochnikov/laravel-typesafe-jev/blob/4d70f5e1b059aac2f63105e72626802247a51f45/src/JevServiceProvider.php
- Source evidence: https://github.com/Butochnikov/laravel-typesafe-jev/blob/4d70f5e1b059aac2f63105e72626802247a51f45/src/Jev.php

## jev-go

A small unofficial Go SDK for Jev calls and model listing.

- Repository: https://github.com/guillemus/jev-go
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/guillemus/jev-go/
- Source evidence: https://github.com/guillemus/jev-go/blob/06df95fe081e8b05bf4c0db8292ceefd995fee84/jev.go#L18
- Source evidence: https://github.com/guillemus/jev-go/blob/06df95fe081e8b05bf4c0db8292ceefd995fee84/README.md
- Source evidence: https://github.com/guillemus/jev-go/blob/06df95fe081e8b05bf4c0db8292ceefd995fee84/examples/README.md

## ask-jev

A Windows PowerShell tool for auditing recorded Codex execution evidence with :jev.

- Repository: https://github.com/omni-/ask-jev
- Category: Evaluation & Observability
- Jev decision: Sends selected records to Jev for judgments about execution claims and evidence sufficiency.
- Purpose: Only reads and sends records on explicit invocation; judgments do not replace real tests.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/omni-/ask-jev/
- Source evidence: https://github.com/omni-/ask-jev/blob/74199ef94098f4e79e5251ffc5a770cda17e2be3/README.md
- Source evidence: https://github.com/omni-/ask-jev/blob/74199ef94098f4e79e5251ffc5a770cda17e2be3/lib/Jev.psm1
- Source evidence: https://github.com/omni-/ask-jev/blob/74199ef94098f4e79e5251ffc5a770cda17e2be3/lib/Report.psm1

## jev-code

An experimental coding CLI where Jev selects AST productions for Python or Bash, with a separate command-line decision mode.

- Repository: https://github.com/rhighs/jev-code
- Category: CLI & Pipelines
- Jev decision: Chooses from bounded syntax and action options; local code constructs programs or invokes tools.
- Purpose: Shows coding choices and command-line judgments in inspectable traces.
- Review scope: Reviewed the README and integration code at a fixed commit. This site has not run the project or independently verified performance, security, or business outcomes.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/rhighs/jev-code/
- Source evidence: https://github.com/rhighs/jev-code/blob/51bf5c1242a51feba8c5a4e18b61e379a9e94e5e/src/provider.ts
- Source evidence: https://github.com/rhighs/jev-code/blob/51bf5c1242a51feba8c5a4e18b61e379a9e94e5e/README.md

## jev-doom-agent

A browser Doom experiment comparing Jev-controlled players from the same initial state.

- Repository: https://github.com/lukaske/jev-doom-agent
- Category: High-Frequency & Simulation
- Jev decision: Jev reads structured health, ammunition and targets and selects tactical controls executed by a local controller.
- Purpose: Exposes model decisions alongside explicitly labeled offline and fallback policies.
- Review scope: The demo uses Freedoom. Jev receives structured state, not pixels, and fallback paths are labeled.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/lukaske/jev-doom-agent/
- Source evidence: https://github.com/lukaske/jev-doom-agent/blob/318c32a24851444c1170bf083671c38723f3a35a/README.md
- Source evidence: https://github.com/lukaske/jev-doom-agent/blob/318c32a24851444c1170bf083671c38723f3a35a/server/typesafe.ts

## jev-rerank-bench

Compares Jev, dedicated rerankers and chat models on the same retrieved passages.

- Repository: https://github.com/anessbelbati/jev-rerank-bench
- Category: Evaluation & Observability
- Jev decision: Ranks candidate passages with Choice, Noul and rubric scores, then computes retrieval metrics.
- Purpose: Publishes raw responses, scoring code and per-dataset results for inspection.
- Review scope: The author reports equal-dataset nDCG@10 of 0.692 for Jev and 0.691 for Cohere on eight English datasets, without establishing a winner. Query weighting changes the comparison. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/anessbelbati/jev-rerank-bench/
- Source evidence: https://github.com/anessbelbati/jev-rerank-bench/blob/cd9a35b22aeb4187334f7018a0ee1960a7470586/rerankers/jev.py#L28
- Source evidence: https://github.com/anessbelbati/jev-rerank-bench/blob/cd9a35b22aeb4187334f7018a0ee1960a7470586/README.md

## jev-predict-skill

An Agent skill recipe that predicts another skill’s closed-set outcome from its rules and evidence.

- Repository: https://github.com/DanielKillenberger/jev-predict-skill
- Category: Decision Tools
- Jev decision: Jev first assesses whether a closed decision is possible, then selects among the target skill’s outcomes.
- Purpose: Includes API-call and response-check examples; it predicts the outcome without executing the target skill.
- Review scope: Reviewed the API-call and response-validation recipe in the skill; the skill was not executed.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/danielkillenberger/jev-predict-skill/
- Source evidence: https://github.com/DanielKillenberger/jev-predict-skill/blob/c80051db825de4a0af6efb03803e682daa466996/README.md
- Source evidence: https://github.com/DanielKillenberger/jev-predict-skill/blob/c80051db825de4a0af6efb03803e682daa466996/SKILL.md

## jev-trade

An experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.

- Repository: https://github.com/aowang-ai/jev-trade
- Category: Domain & Vertical Tools
- Jev decision: Each asset account sends market state to Jev; execution code places or cancels orders based on the decisions.
- Purpose: Separately records model decisions, order execution, and dashboard state.
- Review scope: Adapts jarrodwatts/jev-trader to Hyperliquid with substantive venue changes. Default mock and dry-run modes are not live trading. Real keys can place orders; this site has not verified profitability or live performance.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/aowang-ai/jev-trade/
- Source evidence: https://github.com/aowang-ai/jev-trade/blob/df2c9656324a8a75996eb0612de7adcfe3ce6f89/src/model.ts
- Source evidence: https://github.com/aowang-ai/jev-trade/blob/df2c9656324a8a75996eb0612de7adcfe3ce6f89/README.md
- Source evidence: https://github.com/aowang-ai/jev-trade/blob/df2c9656324a8a75996eb0612de7adcfe3ce6f89/LICENSE

## jevsume

A resume-review app that checks general writing and structure or compares a resume with a specific job description.

- Repository: https://github.com/unownone/jevsume
- Category: Domain & Vertical Tools
- Jev decision: Jev evaluates extracted resume text against typed questions; a Worker combines the results into review output.
- Purpose: Records inputs and judgments so individual reviews can be inspected later.
- Review scope: Without an API key it uses mock results. Resume scores do not establish hiring outcomes.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/unownone/jevsume/
- Source evidence: https://github.com/unownone/jevsume/blob/650a96a4c90da129cf745687d25abca36120c470/readme.md
- Source evidence: https://github.com/unownone/jevsume/blob/650a96a4c90da129cf745687d25abca36120c470/packages/jev/index.ts
- Source evidence: https://github.com/unownone/jevsume/blob/650a96a4c90da129cf745687d25abca36120c470/packages/jev/http.ts

## jev\_ampcode

An Amp plugin for comparing supplied alternatives against supplied evidence and priorities.

- Repository: https://github.com/thesammykins/jev_ampcode
- Category: MCP & Integrations
- Jev decision: Uses Jev Choice to compare bounded options and return probabilities for further review.
- Purpose: Keeps alternatives and decision inputs explicit.
- Review scope: The author limits this V1 tool to advisory comparisons. It does not supply research, authorization, correctness or safety guarantees. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/thesammykins/jev_ampcode/
- Source evidence: https://github.com/thesammykins/jev_ampcode/blob/8741655927f4ae8ea476f833795d3bdfa6e8f293/decision.ts#L74
- Source evidence: https://github.com/thesammykins/jev_ampcode/blob/8741655927f4ae8ea476f833795d3bdfa6e8f293/README.md

## jev-tool-permissions

Adds tool-call approval and tool-list pruning to the Vercel AI SDK.

- Repository: https://github.com/NicolasMontone/jev-tool-permissions
- Category: Security & Guardrails
- Jev decision: Deterministic rules run first; Jev assesses remaining call risks and tool relevance for threshold-based handling.
- Purpose: Approval-call failures request human review; model judgments cannot guarantee detection of every risk.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/nicolasmontone/jev-tool-permissions/
- Source evidence: https://github.com/NicolasMontone/jev-tool-permissions/blob/4c57dd6b0251213353ca01ec74e2a44e04fa42e0/README.md
- Source evidence: https://github.com/NicolasMontone/jev-tool-permissions/blob/4c57dd6b0251213353ca01ec74e2a44e04fa42e0/src/gate.ts
- Source evidence: https://github.com/NicolasMontone/jev-tool-permissions/blob/4c57dd6b0251213353ca01ec74e2a44e04fa42e0/src/prune.ts

## jevthoven

Turns a music prompt into editable multitrack MIDI by asking Jev to choose instruments, harmony, and bar patterns.

- Repository: https://github.com/cocktailpeanut/jevthoven
- Category: Creative Tools
- Jev decision: Selects form, instruments, chords, and rhythm candidates; local code renders the choices as notes.
- Purpose: Preserves editable tracks and decision receipts with playback and MIDI export.
- Review scope: Fixture mode uses simulated decisions; live generation requires a TypeSafe key. This is a symbolic music/MIDI tool, not an audio-generation model.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/cocktailpeanut/jevthoven/
- Source evidence: https://github.com/cocktailpeanut/jevthoven/blob/e5e0c67d8bae92f96c9ce05138f55c3ab72c6aac/app/server/provider.ts
- Source evidence: https://github.com/cocktailpeanut/jevthoven/blob/e5e0c67d8bae92f96c9ce05138f55c3ab72c6aac/README.md

## doom-jev

A ViZDoom Agent that uses Jev to choose movement, targets and firing from structured game state.

- Repository: https://github.com/AmoghCreator/doom-jev
- Category: High-Frequency & Simulation
- Jev decision: Jev selects tactical goals and actions while local geometry handles fine aiming.
- Purpose: Separates game ticks from network inference so the engine need not wait on every frame.
- Review scope: The README’s inference-rate and no-dropped-frame claims are author reports; sustained rates and game completion were not verified here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/amoghcreator/doom-jev/
- Source evidence: https://github.com/AmoghCreator/doom-jev/blob/b27663fc0fa386f9d15ad6ea3c8f15374b855479/README.md
- Source evidence: https://github.com/AmoghCreator/doom-jev/blob/b27663fc0fa386f9d15ad6ea3c8f15374b855479/agent/jev_client.py

## jev-context

A Codex search plugin that filters ripgrep passages through Jev before returning relevant code.

- Repository: https://github.com/zbush/jev-context
- Category: Context GC & Filter
- Jev decision: Judges passage relevance and withholds No and Unknown results.
- Purpose: Records paired payloads for measuring returned text under a named tokenizer.
- Review scope: Filtering can omit relevant passages. Returned-text token savings do not establish full-task, context-window or billing savings. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/zbush/jev-context/
- Source evidence: https://github.com/zbush/jev-context/blob/2be700faebe862c259a16ac9f78266b728874ef6/src/jev.mjs#L46
- Source evidence: https://github.com/zbush/jev-context/blob/2be700faebe862c259a16ac9f78266b728874ef6/README.md

## ui-generator-instinct-jev

Turns UI descriptions into selections from existing shadcn/ui components, fields and styles.

- Repository: https://github.com/joevidev/ui-generator-instinct-jev
- Category: Creative Tools
- Jev decision: Breaks requests into choice and score questions and maps answers to a bounded component catalog.
- Purpose: Demonstrates UI composition through decisions; Jev itself does not generate page code or copy.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/joevidev/ui-generator-instinct-jev/
- Source evidence: https://github.com/joevidev/ui-generator-instinct-jev/blob/9a81c2dc23b561980c7a6d4302c71f34e5ab4ae6/README.md
- Source evidence: https://github.com/joevidev/ui-generator-instinct-jev/blob/9a81c2dc23b561980c7a6d4302c71f34e5ab4ae6/lib/decide.ts
- Source evidence: https://github.com/joevidev/ui-generator-instinct-jev/blob/9a81c2dc23b561980c7a6d4302c71f34e5ab4ae6/lib/typesafe-client.ts

## mobile-jev

Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.

- Repository: https://github.com/droidrun/mobile-jev
- Category: Browser & OS Action
- Jev decision: Chooses apps, controls and next actions from phone state; Mobilerun executes them.
- Purpose: Records action traces and request latency for inspection.
- Review scope: The author’s demo shows nine actions in about 21 seconds, ending at payment selection; it does not demonstrate a completed booking. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/droidrun/mobile-jev/
- Source evidence: https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/policy.mjs#L224
- Source evidence: https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/README.md
- Source evidence: https://github.com/droidrun/mobile-jev/blob/395fc222beac4f059f9a0beb337d114a2b066e99/scripts/mobile-agent/http.mjs

## jev-demo

A customer-service routing demo that batches Jev questions before following the resulting route.

- Repository: https://github.com/minghanminghan/jev-demo
- Category: Routing & Cost Optimization
- Jev decision: Assesses classification levels, human-handoff intent and frustration, with low-confidence escalation.
- Purpose: Combines routing and human handoff while leaving response generation to the application.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/minghanminghan/jev-demo/
- Source evidence: https://github.com/minghanminghan/jev-demo/blob/b6892294f97384bca86d68af9b56e0ea705d7893/README.md
- Source evidence: https://github.com/minghanminghan/jev-demo/blob/b6892294f97384bca86d68af9b56e0ea705d7893/app/api/jev/[...path]/route.ts
- Source evidence: https://github.com/minghanminghan/jev-demo/blob/b6892294f97384bca86d68af9b56e0ea705d7893/lib/oracle.ts
- Source evidence: https://github.com/minghanminghan/jev-demo/blob/b6892294f97384bca86d68af9b56e0ea705d7893/lib/route-engine.ts

## jev-music-theory-1

Explores Jev on harmony exercises and music-theory questions, alongside a piano demo driven by chord choices.

- Repository: https://github.com/adammichaelwood/jev-music-theory-1
- Category: Creative Tools
- Jev decision: Chooses voices, pitches, durations, or chords; code grades exercises or synthesizes playback.
- Purpose: Puts music-theory tests and an audible composition experiment in one project.
- Review scope: The author reports failures in relational music theory and discloses AI-assisted experimentation. Results should not be generalized into broad music-theory capability or an independent benchmark.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/adammichaelwood/jev-music-theory-1/
- Source evidence: https://github.com/adammichaelwood/jev-music-theory-1/blob/7c5b4b8b7e40309f87388c3c5c4d3ed6a3872928/core/decide/jev.ts
- Source evidence: https://github.com/adammichaelwood/jev-music-theory-1/blob/7c5b4b8b7e40309f87388c3c5c4d3ed6a3872928/README.md

## jev-macos-loop

A native macOS automation loop using local OCR and accessibility information with Jev action selection.

- Repository: https://github.com/jcpsimmons/jev-macos-loop
- Category: Browser & OS Action
- Jev decision: Jev selects controls or groups from locally observed candidates; coordinates and input execution stay on the Mac.
- Purpose: Makes candidate controls and execution checks inspectable, including Finder workflows.
- Review scope: The author provides small Finder and settings demos, not broad reliability evidence for arbitrary desktop tasks; not retested here.
- License: AGPL-3.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jcpsimmons/jev-macos-loop/
- Source evidence: https://github.com/jcpsimmons/jev-macos-loop/blob/1aadc01ef262c3b01460909c5dd102f0d9616ba5/README.md
- Source evidence: https://github.com/jcpsimmons/jev-macos-loop/blob/1aadc01ef262c3b01460909c5dd102f0d9616ba5/src/providers.mjs

## jev-router-playground

A model-routing playground where Jev picks a candidate and users compare the resulting answers.

- Repository: https://github.com/hugo-alves/jev-router-playground
- Category: Routing & Cost Optimization
- Jev decision: Selects a model from the task and candidate profiles and records probabilities and runs.
- Purpose: Exports observations for checking routing choices against user preferences.
- Review scope: The default Jev connection passes through an author-provided CORS proxy. It should not be described as a private local-only execution path. No credentials were entered in this audit. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hugo-alves/jev-router-playground/
- Source evidence: https://github.com/hugo-alves/jev-router-playground/blob/c2eb6ccf68b793d4ad99fb0ff1cc29edf11d9a93/app.js#L56
- Source evidence: https://github.com/hugo-alves/jev-router-playground/blob/c2eb6ccf68b793d4ad99fb0ff1cc29edf11d9a93/README.md

## jevscript

An early language experiment whose current implementation is a Jev request-batching spike.

- Repository: https://github.com/amberwhitehead/jevscript
- Category: CLI & Pipelines
- Jev decision: The script compares separate and batched answers, usage and latency; the full language engine remains a design goal.
- Purpose: Useful for studying batching, not a completed compiler or interpreter.
- Review scope: The checked version implements an M0 request experiment; the full language engine remains planned and performance was not independently retested.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/amberwhitehead/jevscript/
- Source evidence: https://github.com/amberwhitehead/jevscript/blob/a01032218d8d57f84c5f310f585cd2da17671c9a/README.md
- Source evidence: https://github.com/amberwhitehead/jevscript/blob/a01032218d8d57f84c5f310f585cd2da17671c9a/spike/m0.mjs
- Source evidence: https://github.com/amberwhitehead/jevscript/blob/a01032218d8d57f84c5f310f585cd2da17671c9a/PLAN.md

## jev-trade

A simulated crypto trading loop that sends BTC and ETH market features to Jev and models execution costs and latency.

- Repository: https://github.com/Waxmell114514/jev-trade
- Category: Domain & Vertical Tools
- Jev decision: Jev answers bounded direction and risk questions; local policy decides simulated positions.
- Purpose: Records judgments, delay and trading costs in the same experiment.
- Review scope: A trading simulation study. Backtest or simulated P&L does not establish future profitability or live readiness.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/waxmell114514/jev-trade/
- Source evidence: https://github.com/Waxmell114514/jev-trade/blob/df43b9636e34096f83457fe58bfe3f038879614c/README.md
- Source evidence: https://github.com/Waxmell114514/jev-trade/blob/df43b9636e34096f83457fe58bfe3f038879614c/jevtrade/jev/client.py

## jev-demos

Maze experiments comparing Jev single-step choices with multi-step lookahead.

- Repository: https://github.com/Bud-ro/jev-demos
- Category: Evaluation & Observability
- Jev decision: Chooses moves from direction candidates, then checks collisions, paths and completion.
- Purpose: Keeps experiment settings and failures visible for studying limitations.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bud-ro/jev-demos/
- Source evidence: https://github.com/Bud-ro/jev-demos/blob/37470f96bc4cb91c5f10703caa7460bf0c20f23a/packages/jev_common/lib/src/client.dart#L232
- Source evidence: https://github.com/Bud-ro/jev-demos/blob/37470f96bc4cb91c5f10703caa7460bf0c20f23a/packages/maze_lookahead/README.md
- Source evidence: https://github.com/Bud-ro/jev-demos/blob/37470f96bc4cb91c5f10703caa7460bf0c20f23a/README.md

## jevex

An Agent experiment where Jev directs a tool loop, a chat model fills arguments and prose, and MCP tools execute.

- Repository: https://github.com/jvsteiner/jevex
- Category: SDK & Decision Frameworks
- Jev decision: Jev selects the next action and approves the concrete call; tool results feed the next state.
- Purpose: Separates decisions, content generation and execution, with author-run comparisons.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jvsteiner/jevex/
- Source evidence: https://github.com/jvsteiner/jevex/blob/dd22ffd958d56ad118bb6dd585f1c913c96c5fd3/README.md
- Source evidence: https://github.com/jvsteiner/jevex/blob/dd22ffd958d56ad118bb6dd585f1c913c96c5fd3/src/jevex/jev.py
- Source evidence: https://github.com/jvsteiner/jevex/blob/dd22ffd958d56ad118bb6dd585f1c913c96c5fd3/src/jevex/agent.py

## jev-experiments

Uses Jev to play Chrome Dino and a local shooter arena while Python executes structured decisions.

- Repository: https://github.com/mittal-parth/jev-experiments
- Category: High-Frequency & Simulation
- Jev decision: Chooses jumping, ducking, movement, aim, or firing from game state, with local execution rules.
- Purpose: An inspector lets users compare state, model answers, and executed actions.
- Review scope: Includes an explicitly labeled heuristic fallback. The model reads structured state rather than game screenshots; this site has not verified decision rate or scores.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/mittal-parth/jev-experiments/
- Source evidence: https://github.com/mittal-parth/jev-experiments/blob/2c8272ea13e2e4cee53f44dc8c6123b0c600edd6/dino_jev/client.py
- Source evidence: https://github.com/mittal-parth/jev-experiments/blob/2c8272ea13e2e4cee53f44dc8c6123b0c600edd6/README.md

## foreman-jev

An experimental Jev supervisor for Codex workers with programmer-selected acceptance commands.

- Repository: https://github.com/Shifty-Eye-Games/foreman-jev
- Category: Evaluation & Observability
- Jev decision: Jev assesses progress and completion signals; deterministic acceptance checks still decide whether the work passes.
- Purpose: Separates a model’s assessment from executable completion checks.
- Review scope: An experimental derivative of foreman. The author’s pilot does not establish reliability across all platforms or tasks; not rerun here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/shifty-eye-games/foreman-jev/
- Source evidence: https://github.com/Shifty-Eye-Games/foreman-jev/blob/3cb97e6051cb5764c50d3a0155f4d1483934fb25/README.md
- Source evidence: https://github.com/Shifty-Eye-Games/foreman-jev/blob/3cb97e6051cb5764c50d3a0155f4d1483934fb25/src/foreman/foreman/jev.py

## jevlogs

Adds Jev diagnostic-value, priority and routing signals to OpenTelemetry logs before deeper analysis.

- Repository: https://github.com/reachjalil/jevlogs
- Category: Context GC & Filter
- Jev decision: Scores log records and judges whether they merit further model analysis.
- Purpose: Can annotate records while preserving the existing archive path.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/reachjalil/jevlogs/
- Source evidence: https://github.com/reachjalil/jevlogs/blob/b1ff60079c30d50a7f93dbfa09848f9539665d44/src/index.ts#L52
- Source evidence: https://github.com/reachjalil/jevlogs/blob/b1ff60079c30d50a7f93dbfa09848f9539665d44/README.md
- Source evidence: https://github.com/reachjalil/jevlogs/blob/b1ff60079c30d50a7f93dbfa09848f9539665d44/examples/receiver/README.md

## ha-conversation-jev

A Home Assistant conversation integration routing simple lighting commands to services and other requests to Grok.

- Repository: https://github.com/luxus/ha-conversation-jev
- Category: Voice & Conversation
- Jev decision: Jev classifies the utterance and exposed devices; code chooses a lighting service or conversation path.
- Purpose: Provides a bounded lighting fast path rather than support for every smart-home command.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/luxus/ha-conversation-jev/
- Source evidence: https://github.com/luxus/ha-conversation-jev/blob/a405366b66b8c8dc5d73b32333043befdbbe2287/README.md
- Source evidence: https://github.com/luxus/ha-conversation-jev/blob/a405366b66b8c8dc5d73b32333043befdbbe2287/custom_components/jev_assist/jev_client.py
- Source evidence: https://github.com/luxus/ha-conversation-jev/blob/a405366b66b8c8dc5d73b32333043befdbbe2287/custom_components/jev_assist/jev_router.py
- Source evidence: https://github.com/luxus/ha-conversation-jev/blob/a405366b66b8c8dc5d73b32333043befdbbe2287/custom_components/jev_assist/conversation.py

## ai

The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.

- Repository: https://github.com/vercel/ai
- Category: SDK & Decision Frameworks
- Jev decision: Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.
- Purpose: Reuses a common evaluation interface within AI SDK applications.
- Review scope: The verified scope is one optional provider in the repository, not that all of AI SDK is powered by Jev or that all users use it.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vercel/ai/
- Source evidence: https://github.com/vercel/ai/blob/73ec7015edd4f04ca9144ce93a8a037a731e5db8/packages/typesafe-ai/src/typesafe-ai-evaluation-model.ts
- Source evidence: https://github.com/vercel/ai/blob/73ec7015edd4f04ca9144ce93a8a037a731e5db8/README.md
- Source evidence: https://github.com/vercel/ai/blob/73ec7015edd4f04ca9144ce93a8a037a731e5db8/LICENSE

## langchain

An optional Jev classifier integration for Python LangChain workflows.

- Repository: https://github.com/langchain-ai/langchain
- Category: SDK & Integrations
- Jev decision: Submits binary, categorical and ordered-score questions and returns typed answers with probabilities.
- Purpose: Adds a classification step that can participate in existing LangChain pipelines.
- Review scope: This entry covers the TypeSafe partner module, not a claim that LangChain uses Jev by default.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/langchain-ai/langchain/
- Source evidence: https://github.com/langchain-ai/langchain/blob/eba445b7563d1709427bd8072892975a6ea59fdc/README.md
- Source evidence: https://github.com/langchain-ai/langchain/blob/eba445b7563d1709427bd8072892975a6ea59fdc/libs/partners/typesafe/langchain_typesafe/classifier.py

## oh-my-pi

Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows.

- Repository: https://github.com/can1357/oh-my-pi
- Category: Routing & Cost Optimization
- Jev decision: Sends agent state and typed questions to Jev and parses structured answers.
- Purpose: Adds a replaceable judgment provider to existing agent workflows.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/can1357/oh-my-pi/
- Source evidence: https://github.com/can1357/oh-my-pi/blob/78b753124d11f8dd3ae73e2524125890ff7c977e/packages/ai/src/judgment/typesafe.ts#L4
- Source evidence: https://github.com/can1357/oh-my-pi/blob/78b753124d11f8dd3ae73e2524125890ff7c977e/README.md
- Source evidence: https://github.com/can1357/oh-my-pi/blob/78b753124d11f8dd3ae73e2524125890ff7c977e/infra/docs/README.md

## eliza

An optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.

- Repository: https://github.com/elizaOS/eliza
- Category: SDK & Decision Frameworks
- Jev decision: Only an explicit systemOne call sends state and questions, returning validated typed answers.
- Purpose: Provides a reusable server-side module; its presence is not evidence of deployed Jev adoption.
- Review scope: The adapter is not registered with the runtime by default; source presence does not establish real adoption or deployment.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/elizaos/eliza/
- Source evidence: https://github.com/elizaOS/eliza/blob/ebc808e3a67fb941e29153d89fc896524d32fe3c/README.md
- Source evidence: https://github.com/elizaOS/eliza/blob/ebc808e3a67fb941e29153d89fc896524d32fe3c/packages/agent/src/services/typesafe/README.md
- Source evidence: https://github.com/elizaOS/eliza/blob/ebc808e3a67fb941e29153d89fc896524d32fe3c/packages/agent/src/services/typesafe/client.ts

## composio

An optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.

- Repository: https://github.com/ComposioHQ/composio
- Category: SDK & Decision Frameworks
- Jev decision: Turns tool or action conditions into structured questions and passes Jev answers to local invocation logic.
- Purpose: Adds structured judgments to existing tool interfaces.
- Review scope: The verified scope is an optional provider. Open-text arguments, execution policy, and external-service authorization remain the caller’s responsibility.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/composiohq/composio/
- Source evidence: https://github.com/ComposioHQ/composio/blob/4b5920bf7aa55c8a44657b060d4bd25ce7b13a9a/ts/packages/providers/typesafe/src/decide.ts
- Source evidence: https://github.com/ComposioHQ/composio/blob/4b5920bf7aa55c8a44657b060d4bd25ce7b13a9a/README.md

## pydantic-ai

An optional TypeSafe provider and Jev model integration for Pydantic AI.

- Repository: https://github.com/pydantic/pydantic-ai
- Category: SDK & Integrations
- Jev decision: Converts supported structured output fields into typed Jev questions and maps answers back to the output model.
- Purpose: Lets supported classification outputs use the existing Pydantic AI interface.
- Review scope: An optional provider rather than a general chat-model replacement; supported output types depend on this implementation. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/pydantic/pydantic-ai/
- Source evidence: https://github.com/pydantic/pydantic-ai/blob/c4898abb54dc25ae6f6aef208a4c0661b30a455e/README.md
- Source evidence: https://github.com/pydantic/pydantic-ai/blob/c4898abb54dc25ae6f6aef208a4c0661b30a455e/pydantic_ai_slim/pydantic_ai/providers/typesafe.py
- Source evidence: https://github.com/pydantic/pydantic-ai/blob/c4898abb54dc25ae6f6aef208a4c0661b30a455e/pydantic_ai_slim/pydantic_ai/models/typesafe.py

## litellm

LiteLLM can use Jev to classify requests for its complexity-based model router.

- Repository: https://github.com/BerriAI/litellm
- Category: Routing & Cost Optimization
- Jev decision: Maps requests to configured complexity classes that drive backend routing.
- Purpose: Makes the complexity judgment behind routing inspectable.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/berriai/litellm/
- Source evidence: https://github.com/BerriAI/litellm/blob/56116079c8022da0e8f7ff9ccb017ad5aca5aed2/litellm/router_strategy/complexity_router/jev_classifier.py#L70
- Source evidence: https://github.com/BerriAI/litellm/blob/56116079c8022da0e8f7ff9ccb017ad5aca5aed2/README.md
- Source evidence: https://github.com/BerriAI/litellm/blob/56116079c8022da0e8f7ff9ccb017ad5aca5aed2/tests/README.MD
- Source evidence: https://github.com/BerriAI/litellm/blob/56116079c8022da0e8f7ff9ccb017ad5aca5aed2/LICENSE

## langchainjs

An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.

- Repository: https://github.com/langchain-ai/langchainjs
- Category: SDK & Decision Frameworks
- Jev decision: Uses invoke to call TypeSafe and parse choice, noul, score and probability fields.
- Purpose: Adds typed decisions to LangChain workflows without treating Jev as a chat generator.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/langchain-ai/langchainjs/
- Source evidence: https://github.com/langchain-ai/langchainjs/blob/206d8b992bcf90ce7d46f2158f1ad85fc1d826c0/README.md
- Source evidence: https://github.com/langchain-ai/langchainjs/blob/206d8b992bcf90ce7d46f2158f1ad85fc1d826c0/libs/providers/langchain-typesafe/README.md
- Source evidence: https://github.com/langchain-ai/langchainjs/blob/206d8b992bcf90ce7d46f2158f1ad85fc1d826c0/libs/providers/langchain-typesafe/src/classifier.ts
- Source evidence: https://github.com/langchain-ai/langchainjs/blob/206d8b992bcf90ce7d46f2158f1ad85fc1d826c0/libs/providers/langchain-typesafe/src/utils/client.ts

## firstmate

Firstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.

- Repository: https://github.com/kunchenguid/firstmate
- Category: Routing & Cost Optimization
- Jev decision: Sends the task brief and candidate rules to Jev, then resolves execution profiles with confidence and local conditions.
- Purpose: Separates semantic matching from the final dispatch policy.
- Review scope: This is opt-in dispatch assistance, not a claim that the whole Firstmate workflow uses Jev by default. Task briefs are sent to TypeSafe.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kunchenguid/firstmate/
- Source evidence: https://github.com/kunchenguid/firstmate/blob/4812db801628040b609dc25a2a8a91ed5efac662/bin/fm-dispatch-resolve.sh
- Source evidence: https://github.com/kunchenguid/firstmate/blob/4812db801628040b609dc25a2a8a91ed5efac662/README.md

## openchamber

OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.

- Repository: https://github.com/openchamber/openchamber
- Category: Routing & Cost Optimization
- Jev decision: Jev selects a task category; local category mappings determine the model configuration.
- Purpose: Keeps routing categories and their model assignments explicit.
- Review scope: Only the optional routing module was inspected; cost or quality improvements for model combinations were not verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/openchamber/openchamber/
- Source evidence: https://github.com/openchamber/openchamber/blob/614d7f76e581a132a86575c03d3fa9aad5e624b6/README.md
- Source evidence: https://github.com/openchamber/openchamber/blob/614d7f76e581a132a86575c03d3fa9aad5e624b6/packages/web/server/lib/routing/jev.js

## ax

Ax provides a TypeSafe integration for boolean or finite-class signatures and native Jev answers.

- Repository: https://github.com/ax-llm/ax
- Category: SDK & Integrations
- Jev decision: Maps supported signatures to Jev questions or sends native System One requests.
- Purpose: Reuses structured signatures and Jev probabilities within Ax workflows.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ax-llm/ax/
- Source evidence: https://github.com/ax-llm/ax/blob/5c43344f9ef3016db576fa2c3b59d48ef21b4d71/src/ax/ai/typesafe/client.ts#L1
- Source evidence: https://github.com/ax-llm/ax/blob/5c43344f9ef3016db576fa2c3b59d48ef21b4d71/README.md
- Source evidence: https://github.com/ax-llm/ax/blob/5c43344f9ef3016db576fa2c3b59d48ef21b4d71/src/ax/README.md

## agentgateway

A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.

- Repository: https://github.com/agentgateway/agentgateway
- Category: Security & Guardrails
- Jev decision: Jev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.
- Purpose: Demonstrates gateway integration, not guaranteed prevention of all attacks.
- Review scope: Reviewed the fixed-version README and call path.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/agentgateway/agentgateway/
- Source evidence: https://github.com/agentgateway/agentgateway/blob/6b0270efd25b5255932943e48b5ca47583d3ad28/README.md
- Source evidence: https://github.com/agentgateway/agentgateway/blob/6b0270efd25b5255932943e48b5ca47583d3ad28/examples/llm-guardrail-jev/README.md
- Source evidence: https://github.com/agentgateway/agentgateway/blob/6b0270efd25b5255932943e48b5ca47583d3ad28/examples/llm-guardrail-jev/guardrail.ts
- Source evidence: https://github.com/agentgateway/agentgateway/blob/6b0270efd25b5255932943e48b5ca47583d3ad28/examples/llm-guardrail-jev/config.yaml

## omg.dev

An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.

- Repository: https://github.com/BennyKok/omg.dev
- Category: Browser & OS Action
- Jev decision: Chooses controls and checks completion or blockage before the test runner operates the UI.
- Purpose: Adds choices grounded in current UI state to mobile testing.
- Review scope: Only the optional mobile-test integration was verified, not that the entire omg.dev product is controlled by Jev. This site has not executed the tests.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bennykok/omg.dev/
- Source evidence: https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/mobile/scripts/jev.ts
- Source evidence: https://github.com/BennyKok/omg.dev/blob/a00f56684a569ee417be787c148eaa9874946f2b/README.md

## pi-fabric

Pi’s programmable runtime includes an optional Jev loop for observing state, making decisions and running bounded actions.

- Repository: https://github.com/monotykamary/pi-fabric
- Category: SDK & Decision Frameworks
- Jev decision: Programmed questions feed Jev judgments into local action logic under runtime budgets.
- Purpose: Keeps observation, judgment and execution steps in a reusable program.
- Review scope: This covers the optional Jev capability in pi-fabric; other features and benchmark results are not attributed to Jev. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/monotykamary/pi-fabric/
- Source evidence: https://github.com/monotykamary/pi-fabric/blob/2e5fcdd94cc364445b115756edefcaab24f68928/README.md
- Source evidence: https://github.com/monotykamary/pi-fabric/blob/2e5fcdd94cc364445b115756edefcaab24f68928/src/jev/client.ts

## latitude-llm

Latitude includes an optional Jev preclassifier for conversation checks and their selection records.

- Repository: https://github.com/latitude-dev/latitude-llm
- Category: Evaluation & Observability
- Jev decision: Judges which checks apply and can add checks when thresholds and rate limits permit.
- Purpose: Records models, thresholds, latency and selection reasons alongside the baseline.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/latitude-dev/latitude-llm/
- Source evidence: https://github.com/latitude-dev/latitude-llm/blob/6b2484c1d74973877fc7d353b8867c7496568d78/packages/domain/flaggers/src/use-cases/run-jev-preclassifier.ts#L1
- Source evidence: https://github.com/latitude-dev/latitude-llm/blob/6b2484c1d74973877fc7d353b8867c7496568d78/README.md
- Source evidence: https://github.com/latitude-dev/latitude-llm/blob/6b2484c1d74973877fc7d353b8867c7496568d78/fern/README.md
- Source evidence: https://github.com/latitude-dev/latitude-llm/blob/6b2484c1d74973877fc7d353b8867c7496568d78/packages/platform/ai-jev/src/jev-shadow-decision-provider.ts

## instructor-php

A TypeSafe Decision driver within Instructor PHP’s Polyglot module.

- Repository: https://github.com/cognesy/instructor-php
- Category: SDK & Decision Frameworks
- Jev decision: Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.
- Purpose: Lets PHP applications use Jev through a shared Decision interface.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/cognesy/instructor-php/
- Source evidence: https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/README.md
- Source evidence: https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/packages/polyglot/src/Decision/Drivers/TypeSafe/TypesafeDriver.php
- Source evidence: https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/packages/polyglot/src/Decision/Drivers/TypeSafe/TypesafeRequestAdapter.php
- Source evidence: https://github.com/cognesy/instructor-php/blob/bb1160ce2360dcf1434788c46ee97809fe782ea3/packages/polyglot/src/Decision/Drivers/TypeSafe/TypesafeResponseAdapter.php

## atomic

An optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.

- Repository: https://github.com/bastani-inc/atomic
- Category: Routing & Cost Optimization
- Jev decision: Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.
- Purpose: Separates structured decisions from text-generation interfaces.
- Review scope: The verified scope is an optional structured-output provider, not that Atomic uses Jev by default or for every feature. LICENSE includes an additional UI-attribution condition above stated business-size thresholds. It is not standard MIT; read the license text.
- License: Custom license
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bastani-inc/atomic/
- Source evidence: https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/packages/coding-agent/src/core/structured-output/jev.ts
- Source evidence: https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/README.md
- Source evidence: https://github.com/bastani-inc/atomic/blob/33ca4ccb5f39488aeba67c0212a52a31cd14059d/LICENSE

## WrongStack

An optional Jev dispatch classifier for choosing among WrongStack specialist Agents.

- Repository: https://github.com/WrongStack/WrongStack
- Category: Routing & Cost Optimization
- Jev decision: Jev evaluates the task against eligible specialists; local dispatch rules use the result.
- Purpose: Makes specialist selection a configurable step in an existing coding Agent.
- Review scope: An optional dispatch module, not evidence that all WrongStack tasks use Jev or that dispatch is always correct.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wrongstack/wrongstack/
- Source evidence: https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/README.md
- Source evidence: https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/packages/core/src/types/config/typesafe.ts
- Source evidence: https://github.com/WrongStack/WrongStack/blob/4cf97c0aa4f855751949ee8e99c719d06f4c26e0/packages/core/src/coordination/typesafe-dispatch-classifier.ts

## celesto

A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.

- Repository: https://github.com/CelestoAI/celesto
- Category: Codebase & Graph Pathfinding
- Jev decision: Judges whether a finding was introduced by the change, is supported and merits a fix.
- Purpose: Shows execution records and reviewer judgments together.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/celestoai/celesto/
- Source evidence: https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/models.py#L96
- Source evidence: https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/examples/pr-review-jev/README.md
- Source evidence: https://github.com/CelestoAI/celesto/blob/fff7bb567752baee4ce195fcb78b5ee5e4da889f/README.md

## req\_llm

A TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir.

- Repository: https://github.com/agentjido/req_llm
- Category: SDK & Decision Frameworks
- Jev decision: Sends state and questions, normalizes answers and retains the raw provider response.
- Purpose: Keeps decision evaluation separate from chat generation in Elixir applications.
- Review scope: Reviewed the fixed-version README and call path.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/agentjido/req_llm/
- Source evidence: https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/README.md
- Source evidence: https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/lib/req_llm/providers/typesafe.ex
- Source evidence: https://github.com/agentjido/req_llm/blob/9cb0ee7a0fea5f3520fc953911d352c93193615e/lib/req_llm/evaluation.ex

## vellum-assistant

An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.

- Repository: https://github.com/vellum-ai/vellum-assistant
- Category: MCP & Integrations
- Jev decision: Submits state and question bundles to System One and returns structured answers to the Assistant.
- Purpose: Adds choices, probabilities, and scoring to an existing assistant.
- Review scope: Only the Jev provider integration was verified, not that Jev drives the assistant’s memory, automation, or overall behavior.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vellum-ai/vellum-assistant/
- Source evidence: https://github.com/vellum-ai/vellum-assistant/blob/ee5ba342719e72b67698c2e1a4a78837321d0b1d/assistant/src/providers/jev/client.ts
- Source evidence: https://github.com/vellum-ai/vellum-assistant/blob/ee5ba342719e72b67698c2e1a4a78837321d0b1d/README.md

## vexjoy-agent

An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows.

- Repository: https://github.com/notque/vexjoy-agent
- Category: Routing & Cost Optimization
- Jev decision: After deterministic routing guards, Jev judges the remaining candidates and required workflow components.
- Purpose: Keeps repeatable routing rules and model-selected candidates in separate stages.
- Review scope: Forced routing and unavailable-provider paths exist; not every dispatch is a Jev decision. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/notque/vexjoy-agent/
- Source evidence: https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/README.md
- Source evidence: https://github.com/notque/vexjoy-agent/blob/ab51ee7da567e84f72f76d73b6e7b83cec5ef060/scripts/jev-route.py

## aiavatarkit

An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.

- Repository: https://github.com/uezo/aiavatarkit
- Category: Voice & Conversation
- Jev decision: Assesses utterance completeness and whether the user is likely to continue speaking.
- Purpose: Adds a semantic signal to silence-based turn detection.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/uezo/aiavatarkit/
- Source evidence: https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/aiavatar/sts/vad/turn_end_gates/jev.py#L172
- Source evidence: https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/README.md
- Source evidence: https://github.com/uezo/aiavatarkit/blob/38b617b8b9269939734e70ef503d7ea6976acdbd/examples/nod/README.md

## taskuary

An optional Jev judgment module in Taskuary for checking user-defined conditions on task state.

- Repository: https://github.com/ldbumble/taskuary
- Category: Evaluation & Observability
- Jev decision: Turns conditions into yes/no probability questions and returns local-threshold verdicts plus probabilities.
- Purpose: Adds structured checks to task outcomes without making Jev the controller of the whole messaging system.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ldbumble/taskuary/
- Source evidence: https://github.com/ldbumble/taskuary/blob/4ad29d7b292a7899767338cfcc83b2dde8f43330/README.md
- Source evidence: https://github.com/ldbumble/taskuary/blob/4ad29d7b292a7899767338cfcc83b2dde8f43330/README.zh-CN.md
- Source evidence: https://github.com/ldbumble/taskuary/blob/4ad29d7b292a7899767338cfcc83b2dde8f43330/taskuary/jev.py

## orchestkit

OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.

- Repository: https://github.com/yonatangross/orchestkit
- Category: CLI & Pipelines
- Jev decision: Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.
- Purpose: Distinguishes sessions by work type and supports a shadow comparison mode.
- Review scope: Jev and shadow modes require explicit configuration. Shadow logs decisions without applying them; this does not mean Jev drives all of OrchestKit.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/yonatangross/orchestkit/
- Source evidence: https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/src/hooks/src/lib/session-category-provider.ts
- Source evidence: https://github.com/yonatangross/orchestkit/blob/569095f35ce61a4881197dfb8117f4c3312e2bee/README.md

## skillbox

A self-hosted, versioned Agent skills library with optional Jev recommendations.

- Repository: https://github.com/kitze/skillbox
- Category: Routing & Cost Optimization
- Jev decision: Jev scores task relevance among skills the client is allowed to access.
- Purpose: Suggests relevant skills while retaining the library’s client access scope.
- Review scope: Jev provides optional skill recommendations, not log pruning; recommendation accuracy was not measured here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kitze/skillbox/
- Source evidence: https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/README.md
- Source evidence: https://github.com/kitze/skillbox/blob/d83ba4ecd254c8dfa6a759d1feb5141384e26a9e/src/server/recommendations.ts

## interlinked-cli

Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.

- Repository: https://github.com/QuentinCody/interlinked-cli
- Category: Security & Guardrails
- Jev decision: Assesses inputs such as test names, documentation claims and supporting evidence.
- Purpose: Keeps model advice distinct from deterministic rules and records checks.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/quentincody/interlinked-cli/
- Source evidence: https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/src/harness/jev/client.ts#L14
- Source evidence: https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/README.md
- Source evidence: https://github.com/QuentinCody/interlinked-cli/blob/207330d8131c5203ecc74e9fd4c24ba416463718/docs/README.md

## effect-agent

An Effect Agent TypeSafe decision provider for typed question sets and optional model selection.

- Repository: https://github.com/danieljvdm/effect-agent
- Category: SDK & Decision Frameworks
- Jev decision: Jev answers probability, choice and score questions for application transitions or model selection.
- Purpose: Integrates decisions into Effect dependencies and errors; applications configure retries and deadlines.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/danieljvdm/effect-agent/
- Source evidence: https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/README.md
- Source evidence: https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/packages/ai-typesafe/README.md
- Source evidence: https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/packages/ai-typesafe/src/TypeSafeClient.ts
- Source evidence: https://github.com/danieljvdm/effect-agent/blob/88005e497e9b627eeb16d670f278903c57601da9/packages/ai-decision/src/AutoModel.ts

## pi-warden

Adds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.

- Repository: https://github.com/DevMortimer/pi-warden
- Category: Security & Guardrails
- Jev decision: Uses Jev to judge rule violations, irreversible actions, and task drift, feeding results back to the Agent.
- Purpose: Brings rule findings and actions needing confirmation into the active workflow.
- Review scope: Source contains integration and action checks. The author’s limited comparisons are not a security guarantee; this site has not independently verified protection or savings.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/devmortimer/pi-warden/
- Source evidence: https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/src/guard.ts
- Source evidence: https://github.com/DevMortimer/pi-warden/blob/e6c801679464b1a9624225114eb5fb443c27d823/README.md

## advocaat

A small TypeScript client for asking Jev multiple typed questions about the same data.

- Repository: https://github.com/pithings/advocaat
- Category: SDK & Decision Frameworks
- Jev decision: Combines yes/no, Choice and Score questions and maps responses to typed values.
- Purpose: Reuses one interface for probabilities, choices and scores.
- Review scope: Client interfaces and request code were inspected; type wrappers do not guarantee correct judgments. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/pithings/advocaat/
- Source evidence: https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/README.md
- Source evidence: https://github.com/pithings/advocaat/blob/bc46287fc1102b95852a81d679c6e34a2c44f4a2/src/api.ts

## synkora-ai

Synkora includes optional TypeSafe client tools for classification, scoring and yes/no judgments.

- Repository: https://github.com/getsynkora/synkora-ai
- Category: MCP & Integrations
- Jev decision: Sends workflow state and named questions to Jev and returns structured answers to agents.
- Purpose: Makes these judgments available within existing platform workflows.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/getsynkora/synkora-ai/
- Source evidence: https://github.com/getsynkora/synkora-ai/blob/2ef7600c9772a025110e49ee06e66e18bb300843/api/src/core/typesafe_client.py#L2
- Source evidence: https://github.com/getsynkora/synkora-ai/blob/2ef7600c9772a025110e49ee06e66e18bb300843/README.md
- Source evidence: https://github.com/getsynkora/synkora-ai/blob/2ef7600c9772a025110e49ee06e66e18bb300843/api/README.md

## ai

A Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.

- Repository: https://github.com/hackclub/ai
- Category: SDK & Decision Frameworks
- Jev decision: Forwards authorized structured requests to TypeSafe and returns answers with usage accounting.
- Purpose: Adds a decision API to the existing proxy rather than an MCP tool server.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hackclub/ai/
- Source evidence: https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/README.md
- Source evidence: https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/src/routes/proxy/v1/jev.ts
- Source evidence: https://github.com/hackclub/ai/blob/a76ea2cb159f707a60107935a5b2e0dbdc7455f5/src/routes/proxy/v1/index.ts

## unclutter

A browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.

- Repository: https://github.com/kitze/unclutter
- Category: Security & Guardrails
- Jev decision: Evaluates candidate page elements before the extension applies local hiding rules.
- Purpose: Turns page judgments into reusable rules.
- Review scope: Reviewed the README and integration code at a fixed commit. This site has not run the project or independently verified performance, security, or business outcomes.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kitze/unclutter/
- Source evidence: https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/lib/jev.ts
- Source evidence: https://github.com/kitze/unclutter/blob/9ef9beccc1e57b4e3115ae68644b8fc9c19c29f6/README.md

## openai-scala-client

A dedicated TypeSafe module in a Scala client that supports multiple AI providers.

- Repository: https://github.com/cequence-io/openai-scala-client
- Category: SDK & Decision Frameworks
- Jev decision: Sends shared state and typed questions to Jev and parses structured answers.
- Purpose: Lets Scala applications reuse provider transport and error-handling conventions.
- Review scope: This covers the dedicated TypeSafe module; adoption of the overall multi-provider repository is not Jev adoption. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/cequence-io/openai-scala-client/
- Source evidence: https://github.com/cequence-io/openai-scala-client/blob/cfabe8842344da713615d0121a7804840649eb46/README.md
- Source evidence: https://github.com/cequence-io/openai-scala-client/blob/cfabe8842344da713615d0121a7804840649eb46/typesafe-client/src/main/scala/io/cequence/openaiscala/typesafe/service/impl/TypeSafeServiceImpl.scala

## ego-jev

Connects Ego Lite snapshots and browser actions to a bounded Jev decision loop.

- Repository: https://github.com/phd-peter/ego-jev
- Category: Browser & OS Action
- Jev decision: Selects only current snapshot candidates and supported actions; another model can supply typed text.
- Purpose: Executes against current snapshot references and records step state.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/phd-peter/ego-jev/
- Source evidence: https://github.com/phd-peter/ego-jev/blob/0da45e4f3a3bdad56402b5c38226ad3a2e10409c/src/jev-client.ts#L1
- Source evidence: https://github.com/phd-peter/ego-jev/blob/0da45e4f3a3bdad56402b5c38226ad3a2e10409c/README.md

## bluenoise

An X/Twitter filtering extension using local rules by default, with optional Jev checks for unmatched replies.

- Repository: https://github.com/rokcso/bluenoise
- Category: Context GC & Filter
- Jev decision: When experimental AI is enabled, Jev evaluates replies missed by rules and local thresholds decide whether to hide them.
- Purpose: Applies reversible local rules first and adds model judgment only when requested.
- Review scope: Jev is disabled by default. Enabling it sends relevant replies to TypeSafe, so AI mode is not fully local processing. This site has not run it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/rokcso/bluenoise/
- Source evidence: https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/entrypoints/background.ts
- Source evidence: https://github.com/rokcso/bluenoise/blob/ef81ea7a7c3677501d6de8f9235a4d6a866b573a/README.md

## jev-gomoku

A nine-board, 15×15 Gomoku workbench comparing how two Jev players respond to different input representations.

- Repository: https://github.com/XieChengYuan/jev-gomoku
- Category: Evaluation & Observability
- Jev decision: Jev chooses from locally generated move candidates while the experiment varies board and tactical information.
- Purpose: Supports labeled replays and bring-your-own-key live games with per-move records.
- Review scope: Free mode replays saved games without new inference. Match outcomes do not establish general playing strength; not rerun here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/xiechengyuan/jev-gomoku/
- Source evidence: https://github.com/XieChengYuan/jev-gomoku/blob/2aac72cd54ab63fd35e7d29e65def787dda2b333/README.md
- Source evidence: https://github.com/XieChengYuan/jev-gomoku/blob/2aac72cd54ab63fd35e7d29e65def787dda2b333/src/decision.js
- Source evidence: https://github.com/XieChengYuan/jev-gomoku/blob/2aac72cd54ab63fd35e7d29e65def787dda2b333/src/online.js

## jev-voice-browser

Controls a Playwright browser by sending incremental speech transcripts to Jev.

- Repository: https://github.com/moritzkremb/jev-voice-browser
- Category: Browser & OS Action
- Jev decision: Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.
- Purpose: Shows probabilities, actions and request timing during voice interaction.
- Review scope: The reported 250–350 ms measures an individual request, not guaranteed end-to-end response time for every voice command. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/moritzkremb/jev-voice-browser/
- Source evidence: https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/src/jev.js#L123
- Source evidence: https://github.com/moritzkremb/jev-voice-browser/blob/054db0f3dbf537af63a8117632d3f941ccd520e1/README.md

## hono-jev-router

An experimental semantic HTTP router for Hono using natural-language route descriptions.

- Repository: https://github.com/yusukebe/hono-jev-router
- Category: Routing & Cost Optimization
- Jev decision: Jev scores request-to-description matches; code selects the first route above its threshold.
- Purpose: Explores semantic routing; the author explicitly warns against using it for authentication or authorization.
- Review scope: Experimental semantic routing, explicitly unsuitable for authentication or authorization; production traffic behavior was not verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/yusukebe/hono-jev-router/
- Source evidence: https://github.com/yusukebe/hono-jev-router/blob/04f6e103e1397bca659ab85c042011a1f14b679d/README.md
- Source evidence: https://github.com/yusukebe/hono-jev-router/blob/04f6e103e1397bca659ab85c042011a1f14b679d/src/index.ts

## openjev

An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.

- Repository: https://github.com/razorback16/openjev
- Category: SDK & Decision Frameworks
- Jev decision: Accepts Jev-style state and Noul, Choice, and Score questions, producing probabilities with a local model.
- Purpose: Lets existing TypeSafe SDKs connect to a self-hosted compatible service.
- Review scope: This is a protocol-compatible implementation, not the Jev model, an official product, or TypeSafe inference. Speed, calibration, and compatibility have not been independently retested.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/razorback16/openjev/
- Source evidence: https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/openjev/api.py
- Source evidence: https://github.com/razorback16/openjev/blob/91d5005effcf8cc0ecccaa9538ceabbb130fef59/README.md

## typesafe-jev-workflow

An async LangGraph example that classifies mocked emails as invoice-related or general.

- Repository: https://github.com/GiesN/typesafe-jev-workflow
- Category: Classification & Taxonomy
- Jev decision: Jev returns invoice or general; graph nodes choose the corresponding demo handler.
- Purpose: Separates model classification from local workflow routing.
- Review scope: Emails are mock data and handlers only set destinations; they do not send mail or payments. Not run here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/giesn/typesafe-jev-workflow/
- Source evidence: https://github.com/GiesN/typesafe-jev-workflow/blob/251019670ebc3bf95870e924740d5876c1cd56b5/README.md
- Source evidence: https://github.com/GiesN/typesafe-jev-workflow/blob/251019670ebc3bf95870e924740d5876c1cd56b5/src/typesafe_ai_basic/__init__.py
- Source evidence: https://github.com/GiesN/typesafe-jev-workflow/blob/251019670ebc3bf95870e924740d5876c1cd56b5/src/typesafe_ai_langgraph/typesafe_ai_langgraph_workflow.py

## JevRouter

Routes among models, subagents, skills, MCP tools and CLIs using a shared candidate set.

- Repository: https://github.com/BillionsBobby/JevRouter
- Category: Routing & Cost Optimization
- Jev decision: Jev makes a Choice; the router separately checks availability, permissions, risk and confirmation policy.
- Purpose: Records model choices separately from execution policy.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/billionsbobby/jevrouter/
- Source evidence: https://github.com/BillionsBobby/JevRouter/blob/715970774ae8070e958e83ac9b1a780b32a9184c/src/provider.ts#L72
- Source evidence: https://github.com/BillionsBobby/JevRouter/blob/715970774ae8070e958e83ac9b1a780b32a9184c/README.md
- Source evidence: https://github.com/BillionsBobby/JevRouter/blob/715970774ae8070e958e83ac9b1a780b32a9184c/docs/cookbook/README.md

## jevwire

Provides Jev MCP tools, an embeddable library and Claude Code hooks for Agents.

- Repository: https://github.com/Brainwires/jevwire
- Category: MCP & Integrations
- Jev decision: Uses Jev for ranking, verification, action checks and next-step selection, with code applying policy.
- Purpose: Reuses the decision layer through MCP or host code; hook behavior depends on configuration.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/brainwires/jevwire/
- Source evidence: https://github.com/Brainwires/jevwire/blob/21abf12fabced4089779f664424fc520a67eaacb/README.md
- Source evidence: https://github.com/Brainwires/jevwire/blob/21abf12fabced4089779f664424fc520a67eaacb/src/jev/client.ts
- Source evidence: https://github.com/Brainwires/jevwire/blob/21abf12fabced4089779f664424fc520a67eaacb/src/tools/evaluate.ts
- Source evidence: https://github.com/Brainwires/jevwire/blob/21abf12fabced4089779f664424fc520a67eaacb/src/hooks/handlers/pre-tool-use.ts

## llama-index-jev

Provides Jev rerankers and routers for LlamaIndex to score retrieved passages or select query tools.

- Repository: https://github.com/WiktorB2004/llama-index-jev
- Category: Data & Search
- Jev decision: Uses Score for passage relevance and Choice for selecting query engines or tools.
- Purpose: Adds Jev judgments to existing retrieval and query workflows.
- Review scope: A community integration, not an official LlamaIndex or TypeSafe product. Reranking preserves the retrieval order on failure; selectors have separate failure policies. Retrieval quality was not independently retested.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wiktorb2004/llama-index-jev/
- Source evidence: https://github.com/WiktorB2004/llama-index-jev/blob/72c73dc50bca4b7ea6928ef65ea09f1a7ee4a01e/packages/llama-index-postprocessor-jev/llama_index/postprocessor/jev/openrouter.py
- Source evidence: https://github.com/WiktorB2004/llama-index-jev/blob/72c73dc50bca4b7ea6928ef65ea09f1a7ee4a01e/README.md

## jevcal

A toolkit for evaluating Jev probabilities on labeled data, selecting confidence thresholds and checking model drift.

- Repository: https://github.com/abhixhek/jevcal
- Category: Evaluation & Observability
- Jev decision: Runs fixed questions and measures accuracy, calibration, coverage and escalation rates.
- Purpose: Connects threshold selection and model-change checks to reports and CI.
- Review scope: The README demo table uses a simulator, not measured Jev results; production thresholds need workload-specific validation. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abhixhek/jevcal/
- Source evidence: https://github.com/abhixhek/jevcal/blob/ae8f3144d69c9cb0e5e0a2c17f70b9d14714cb9f/README.md
- Source evidence: https://github.com/abhixhek/jevcal/blob/ae8f3144d69c9cb0e5e0a2c17f70b9d14714cb9f/src/jevcal/providers/llm.py
- Source evidence: https://github.com/abhixhek/jevcal/blob/ae8f3144d69c9cb0e5e0a2c17f70b9d14714cb9f/src/jevcal/providers/typesafe.py

## jev-benchmark

Benchmarks Jev on chess moves and identifying which game NPC a player addresses.

- Repository: https://github.com/wondertwins/jev-benchmark
- Category: Evaluation & Observability
- Jev decision: Selects legal chess moves or judges whether an utterance addresses each NPC.
- Purpose: Publishes labeled data, raw requests and responses, and evaluation code.
- Review scope: Chess strength, F1 and latency come from the author’s specific tasks and settings, not general game-playing capability. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wondertwins/jev-benchmark/
- Source evidence: https://github.com/wondertwins/jev-benchmark/blob/1c2509ac7d5508b8a7ce00ae4df6d7652d05de8b/jevcommon/client.py#L82
- Source evidence: https://github.com/wondertwins/jev-benchmark/blob/1c2509ac7d5508b8a7ce00ae4df6d7652d05de8b/README.md

## jev-shield

A Chrome ad-filtering extension that uses Jev to assess promotional intent in feed elements.

- Repository: https://github.com/vmendes90/jev-shield
- Category: Browser & OS Action
- Jev decision: Batches candidate DOM elements for TypeSafe and uses Noul probabilities with thresholds to decide which to collapse.
- Purpose: Adds text-based semantic judgments alongside local ad rules.
- Review scope: This is browser filtering, not a game or simulation. Candidate content is sent to an external API.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vmendes90/jev-shield/
- Source evidence: https://github.com/vmendes90/jev-shield/blob/85cf3445931cbed7320f140db9af5d1fd13c4c64/src/background/typesafe.ts
- Source evidence: https://github.com/vmendes90/jev-shield/blob/85cf3445931cbed7320f140db9af5d1fd13c4c64/README.md

## jev-frontend-qa

Frontend QA that uses Jev to choose browser actions and checks contracts through DOM, HTTP and database evidence.

- Repository: https://github.com/Nainish-Rai/jev-frontend-qa
- Category: Evaluation & Observability
- Jev decision: Jev selects observed controls and operations; test code owns expected values and pass criteria.
- Purpose: Records exploratory behavior separately from contract acceptance.
- Review scope: The author reports acceptance on synthetic reference scenarios, not arbitrary websites; not rerun here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/nainish-rai/jev-frontend-qa/
- Source evidence: https://github.com/Nainish-Rai/jev-frontend-qa/blob/2a57d0a23471ca627a2840eff04102ddc844dd57/README.md
- Source evidence: https://github.com/Nainish-Rai/jev-frontend-qa/blob/2a57d0a23471ca627a2840eff04102ddc844dd57/src/jev_frontend_qa/core/decisions.py
- Source evidence: https://github.com/Nainish-Rai/jev-frontend-qa/blob/2a57d0a23471ca627a2840eff04102ddc844dd57/src/jev_frontend_qa/core/model_client.py

## omp-jev-compaction

An Oh My Pi extension that prunes tool history verbatim and reuses decisions to limit prefix rewrites.

- Repository: https://github.com/jerryfane/omp-jev-compaction
- Category: Context GC & Filter
- Jev decision: Jev judges tool-call and output utility; the extension truncates selected content with recovery notes.
- Purpose: Remembers pruning decisions and reapplies them across requests.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jerryfane/omp-jev-compaction/
- Source evidence: https://github.com/jerryfane/omp-jev-compaction/blob/5cc9daf51d97f0922d39f8396694631d6a87535c/src/asker.ts#L15
- Source evidence: https://github.com/jerryfane/omp-jev-compaction/blob/5cc9daf51d97f0922d39f8396694631d6a87535c/README.md

## todo-jev

A task-routing experiment combining skill conditions and environment checks to suggest rules, skills or a large model.

- Repository: https://github.com/maker-KK/todo-jev
- Category: Routing & Cost Optimization
- Jev decision: Jev classifies requests and matches skills, with heuristic fallback when unavailable.
- Purpose: Classification and recommendations are implemented; execution handlers still return examples and need real integrations.
- Review scope: The classification call is implemented, but task execution handlers return example output; end-to-end task execution is unverified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/maker-kk/todo-jev/
- Source evidence: https://github.com/maker-KK/todo-jev/blob/08c8a1e744c311e9f88721b414e636d7eb7c156c/README.md
- Source evidence: https://github.com/maker-KK/todo-jev/blob/08c8a1e744c311e9f88721b414e636d7eb7c156c/app/classifier.py
- Source evidence: https://github.com/maker-KK/todo-jev/blob/08c8a1e744c311e9f88721b414e636d7eb7c156c/app/router.py

## jevsome-projects

A Jev project directory and discovery pipeline that stores integration evidence and can use Jev for classification.

- Repository: https://github.com/ozers/jevsome-projects
- Category: Data & Search
- Jev decision: When configured with a key, sends project state and candidate categories to Jev; otherwise uses local classification rules.
- Purpose: Keeps a project index alongside concrete source evidence.
- Review scope: Actual TypeSafe request code exists, but the directory’s ratings and evidence for downstream projects remain its authors’ assessments; this site does not endorse each conclusion.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ozers/jevsome-projects/
- Source evidence: https://github.com/ozers/jevsome-projects/blob/ba0bfdceb27f8ba1df10f76d4b5b090438eee952/pipeline/lib/jev.mjs
- Source evidence: https://github.com/ozers/jevsome-projects/blob/ba0bfdceb27f8ba1df10f76d4b5b090438eee952/README.md

## jev-cli

The jevctl command-line tool connects verification, classification and scoring questions to text input and scripts.

- Repository: https://github.com/Nasrallah-AL/jev-cli
- Category: CLI & Pipelines
- Jev decision: Sends input and bounded answer options to Jev, then reports judgments and probabilities using local thresholds.
- Purpose: Provides structured results for pipelines and CI, with request inspection and dry-run support.
- Review scope: Distinct from other authors’ jev-cli repositories. Implementation was inspected; performance and verification accuracy were not measured.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/nasrallah-al/jev-cli/
- Source evidence: https://github.com/Nasrallah-AL/jev-cli/blob/02ca80177aaef0b30a897959207f99df1e0c8446/README.md
- Source evidence: https://github.com/Nasrallah-AL/jev-cli/blob/02ca80177aaef0b30a897959207f99df1e0c8446/plugin/hooks/fast-jev.ts
- Source evidence: https://github.com/Nasrallah-AL/jev-cli/blob/02ca80177aaef0b30a897959207f99df1e0c8446/src/provider.ts

## hermes-jev-north-star

A Hermes goal-checking skill that saves requirements, creates a run prompt and checks completion evidence.

- Repository: https://github.com/poponline63/hermes-jev-north-star
- Category: Evaluation & Observability
- Jev decision: Local checks handle machine-verifiable requirements; Jev assesses the remaining semantic conditions.
- Purpose: Connects goals with checkable criteria without replacing actual acceptance evidence with model opinions.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/poponline63/hermes-jev-north-star/
- Source evidence: https://github.com/poponline63/hermes-jev-north-star/blob/b5499f2da6b940258e2dc7c935552a217c7df993/README.md
- Source evidence: https://github.com/poponline63/hermes-jev-north-star/blob/b5499f2da6b940258e2dc7c935552a217c7df993/scripts/jev_judge.py
- Source evidence: https://github.com/poponline63/hermes-jev-north-star/blob/b5499f2da6b940258e2dc7c935552a217c7df993/scripts/north_star.py

## codex-jev-compaction

Curates Codex handoff context by using Jev to select old tool records while retaining selected text verbatim.

- Repository: https://github.com/Wang-auspicious/codex-jev-compaction
- Category: Context GC & Filter
- Jev decision: Judges relevance of eligible read-only tool records; local rules protect required content and assemble a handoff packet.
- Purpose: Preserves source references, selection reasons, and original text order in the handoff.
- Review scope: Prepares explicit handoff packets; it does not replace Codex automatic compaction or reclaim Tokens in the current conversation. Selection is lossy, so original input should be retained.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wang-auspicious/codex-jev-compaction/
- Source evidence: https://github.com/Wang-auspicious/codex-jev-compaction/blob/26fa09f83113a777b0d0db25d847f1c2a25d3388/plugins/codex-jev-compaction/lib/core.mjs
- Source evidence: https://github.com/Wang-auspicious/codex-jev-compaction/blob/26fa09f83113a777b0d0db25d847f1c2a25d3388/README.md

## pi-jev-compaction

Extractive context compaction for Pi that keeps selected original tool records instead of generating a summary.

- Repository: https://github.com/Wang-auspicious/pi-jev-compaction
- Category: Context GC & Filter
- Jev decision: Jev judges complete read-only tool pairs; local code removes those rated unnecessary.
- Purpose: Preserves original evidence and Pi’s recent-message boundary.
- Review scope: Depends on Pi’s compaction interface and version; extractive filtering can still omit useful content. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wang-auspicious/pi-jev-compaction/
- Source evidence: https://github.com/Wang-auspicious/pi-jev-compaction/blob/058d91db752f97c7d52062e465eb151bddab060d/README.md
- Source evidence: https://github.com/Wang-auspicious/pi-jev-compaction/blob/058d91db752f97c7d52062e465eb151bddab060d/src/client.ts

## jev-review-action

A configurable GitHub Action that reviews catalog submissions or classifies PRs and updates a templated comment.

- Repository: https://github.com/fatwang2/jev-review-action
- Category: Codebase & Graph Pathfinding
- Jev decision: Answers policy questions over pinned repository evidence or PR patches, then applies classification rules.
- Purpose: Keeps question definitions, thresholds and comment templates inspectable.
- Review scope: The code reviews, classifies and comments; it does not establish automatic PR merging. The previous auto-merge description was removed. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/fatwang2/jev-review-action/
- Source evidence: https://github.com/fatwang2/jev-review-action/blob/0cc579cb2aa5b160b6d8a788a4775953a31c6e1e/src/typesafe.mjs#L36
- Source evidence: https://github.com/fatwang2/jev-review-action/blob/0cc579cb2aa5b160b6d8a788a4775953a31c6e1e/README.md

## jev-curate

A Rust dataset-filtering experiment using Jev scores to keep or reject text records.

- Repository: https://github.com/AkashPriyadarshii/jev-curate
- Category: Data & Search
- Jev decision: Runs local prefilters, calls TypeSafe and applies probability and score thresholds to each record.
- Purpose: Provides local prefilters and score thresholds for experimenting with per-record data pipelines.
- Review scope: Reviewed the Rust API and filtering path; the advertised 1,500+ rows/sec has no verified measurement and the checked Python binding lacks the documented sift method.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/akashpriyadarshii/jev-curate/
- Source evidence: https://github.com/AkashPriyadarshii/jev-curate/blob/a35d420cdf15eb1d109171fc896ddc54e6cb9a45/README.md
- Source evidence: https://github.com/AkashPriyadarshii/jev-curate/blob/a35d420cdf15eb1d109171fc896ddc54e6cb9a45/src/client.rs
- Source evidence: https://github.com/AkashPriyadarshii/jev-curate/blob/a35d420cdf15eb1d109171fc896ddc54e6cb9a45/src/filter.rs
- Source evidence: https://github.com/AkashPriyadarshii/jev-curate/blob/a35d420cdf15eb1d109171fc896ddc54e6cb9a45/src/main.rs
- Source evidence: https://github.com/AkashPriyadarshii/jev-curate/blob/a35d420cdf15eb1d109171fc896ddc54e6cb9a45/src/lib.rs

## jevify

An Agent Skill for finding suitable Jev decision points and designing questions and comparison experiments.

- Repository: https://github.com/altryne/jevify
- Category: Decision Tools
- Jev decision: Designs Noul, Choice, and Score question packs for an application, with a script for API-backed case runs.
- Purpose: Connects integration ideas, question design, and evaluation methods.
- Review scope: Not the Jev model, an SDK, or an official product. Installing the Skill makes no API calls; actual inference requires a separate run and configured key.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/altryne/jevify/
- Source evidence: https://github.com/altryne/jevify/blob/9b50ba134487f9a5a568386583c18e876cae3f56/scripts/run_cases.py
- Source evidence: https://github.com/altryne/jevify/blob/9b50ba134487f9a5a568386583c18e876cae3f56/README.md

## jev-synergy-screening

A Jev title-and-abstract screening experiment compared with Cohen Abstract Triage labels for an ADHD review.

- Repository: https://github.com/PistachioAIHQ/jev-synergy-screening
- Category: Evaluation & Observability
- Jev decision: Asks Choice and Noul questions about eligibility, then combines them into include or exclude decisions.
- Purpose: Records metrics for specific dataset slices and question designs to examine screening errors.
- Review scope: A dataset-specific literature experiment, not clinical evidence or a replacement for human systematic-review screening; not rerun here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/pistachioaihq/jev-synergy-screening/
- Source evidence: https://github.com/PistachioAIHQ/jev-synergy-screening/blob/4142c88513b68520958cee1fa72ed59385f91376/README.md
- Source evidence: https://github.com/PistachioAIHQ/jev-synergy-screening/blob/4142c88513b68520958cee1fa72ed59385f91376/src/jev_client.py

## jev-mcp

An evaluation-focused Jev MCP server for individual questions, batch processing and question or threshold comparisons.

- Repository: https://github.com/BYK/jev-mcp
- Category: MCP & Integrations
- Jev decision: Runs typed questions and uses labeled samples to measure accuracy and calibration.
- Purpose: Makes question design and threshold choices inspectable through sample results.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/byk/jev-mcp/
- Source evidence: https://github.com/BYK/jev-mcp/blob/cee2e6d58112d006ccd3ebad1163a31083262ae9/src/typesafe.ts#L1
- Source evidence: https://github.com/BYK/jev-mcp/blob/cee2e6d58112d006ccd3ebad1163a31083262ae9/README.md

## jev-classifier

A local Jev tool-routing gateway for coding Agents, with an MCP suggestion interface.

- Repository: https://github.com/felpsdev/jev-classifier
- Category: MCP & Integrations
- Jev decision: Jev selects among available tools; adapters may record suggestions or influence actual tool selection.
- Purpose: Keeps decision logs while some clients remain observation-only or choose whether to follow suggestions.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/felpsdev/jev-classifier/
- Source evidence: https://github.com/felpsdev/jev-classifier/blob/e0c6cc7c6d2b1027be86ad8f4e03e191a88ec402/README.md
- Source evidence: https://github.com/felpsdev/jev-classifier/blob/e0c6cc7c6d2b1027be86ad8f4e03e191a88ec402/src/jev.ts
- Source evidence: https://github.com/felpsdev/jev-classifier/blob/e0c6cc7c6d2b1027be86ad8f4e03e191a88ec402/src/router.ts
- Source evidence: https://github.com/felpsdev/jev-classifier/blob/e0c6cc7c6d2b1027be86ad8f4e03e191a88ec402/src/mcp.ts

## jev-exploration

A research repository tracking Jev claims and limitations, with calibration experiments and runnable examples.

- Repository: https://github.com/SamuelSacco/jev-exploration
- Category: Evaluation & Observability
- Jev decision: Calls Jev on defined questions and labeled cases, then analyzes errors, calibration, and difficulty effects.
- Purpose: Links research claims to experiment code, data, and an evidence ledger.
- Review scope: The author’s calibration and benchmark conclusions are limited by datasets, samples, and protocols. This site reviewed integration code but did not reproduce the experiments.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/samuelsacco/jev-exploration/
- Source evidence: https://github.com/SamuelSacco/jev-exploration/blob/af91a6e09bf82c7f43d142de2bf5f1573d89b1b9/jevlab/client.py
- Source evidence: https://github.com/SamuelSacco/jev-exploration/blob/af91a6e09bf82c7f43d142de2bf5f1573d89b1b9/README.md

## jevscan

An EVM Token screening tool with library, CLI and MCP interfaces for market-feature-based risk judgments.

- Repository: https://github.com/jevbook/jevscan
- Category: Domain & Vertical Tools
- Jev decision: Uses a deterministic local engine by default; a TypeSafe key enables real Jev judgments over features.
- Purpose: Shows features, decision provenance and scores together for inspection.
- Review scope: Default output is not Jev inference. This is not a contract-bytecode audit or evidence of investment safety.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jevbook/jevscan/
- Source evidence: https://github.com/jevbook/jevscan/blob/cdaf9b882cc6e221ceeaac2767fac82f584b9d88/README.md
- Source evidence: https://github.com/jevbook/jevscan/blob/cdaf9b882cc6e221ceeaac2767fac82f584b9d88/src/index.js
- Source evidence: https://github.com/jevbook/jevscan/blob/cdaf9b882cc6e221ceeaac2767fac82f584b9d88/src/engine.js

## jev-askable-arm

Uses Jev to chain predefined skills for English-language goals in a ManiSkill robot-arm simulation.

- Repository: https://github.com/TarunTomar122/jev-askable-arm
- Category: High-Frequency & Simulation
- Jev decision: Chooses a skill and target from privileged object and gripper state and about thirty primitives.
- Purpose: Separates skill selection from Python motor control.
- Review scope: The robot uses privileged simulation state, not vision. About one second per pick is an author-reported seed-0 example, not a physical-robot validation. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/taruntomar122/jev-askable-arm/
- Source evidence: https://github.com/TarunTomar122/jev-askable-arm/blob/bef98b31a122a7033dd4bfb52867cd6ccb2d7e67/jev_robotics/common.py#L76
- Source evidence: https://github.com/TarunTomar122/jev-askable-arm/blob/bef98b31a122a7033dd4bfb52867cd6ccb2d7e67/README.md

## jev-flash-review

An MCP review engine that evaluates Agent-supplied diffs against explicit rules.

- Repository: https://github.com/TheBous/jev-flash-review
- Category: Evaluation & Observability
- Jev decision: Jev checks the diff, selects evidence from actual hunks and adjudicates candidate findings.
- Purpose: The caller supplies diffs and task boundaries; the engine does not scan the repository itself.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/thebous/jev-flash-review/
- Source evidence: https://github.com/TheBous/jev-flash-review/blob/658a7bd52e30292daa21ca3941179429634371eb/README.md
- Source evidence: https://github.com/TheBous/jev-flash-review/blob/658a7bd52e30292daa21ca3941179429634371eb/src/judge.ts
- Source evidence: https://github.com/TheBous/jev-flash-review/blob/658a7bd52e30292daa21ca3941179429634371eb/src/mcp/reviewServer.ts

## jevchat

A chat-style Jev demo whose answers are selected from predefined or custom options rather than generated prose.

- Repository: https://github.com/kt3k/jevchat
- Category: Decision Tools
- Jev decision: Maps answer styles to Choice options and selects chat titles from fragments of the question.
- Purpose: Shows answer options and probabilities in a chat UI with customizable answer sets.
- Review scope: The chat appearance does not imply free-text generation. This is a demo; selected answers are not guaranteed factual, and this site has not run it.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kt3k/jevchat/
- Source evidence: https://github.com/kt3k/jevchat/blob/18ecea877ebcdaa66b0d2eba9a4db87f0b9715ab/main.ts
- Source evidence: https://github.com/kt3k/jevchat/blob/18ecea877ebcdaa66b0d2eba9a4db87f0b9715ab/README.md

## jevarena

Two Jev Agents play Snake in side-by-side browser panes with visible per-step choices.

- Repository: https://github.com/raihankhan-rk/jevarena
- Category: High-Frequency & Simulation
- Jev decision: Selects a direction-button target from allowed controls using structured board state.
- Purpose: Displays candidate controls, action probabilities and game progress together.
- Review scope: Jev receives structured state rather than screenshots; demo or offline paths do not establish live-model win rates. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/raihankhan-rk/jevarena/
- Source evidence: https://github.com/raihankhan-rk/jevarena/blob/c22adde05edfc3ee16911d38b12b337c5f9727a1/README.md
- Source evidence: https://github.com/raihankhan-rk/jevarena/blob/c22adde05edfc3ee16911d38b12b337c5f9727a1/lib/server/jev.ts

## supercov

A quality and coverage CLI for coding agents: Jev assesses source properties while local coverage highlights testing targets.

- Repository: https://github.com/supercorp-ai/supercov
- Category: Evaluation & Observability
- Jev decision: Asks Jev about file-quality properties; code composes scores and ordering.
- Purpose: Breaks scores into named properties and caches results by content.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/supercorp-ai/supercov/
- Source evidence: https://github.com/supercorp-ai/supercov/blob/55f5ce93a239829c224b89e6749991310be91ea4/crates/supercov-cli/src/quality.rs#L30
- Source evidence: https://github.com/supercorp-ai/supercov/blob/55f5ce93a239829c224b89e6749991310be91ea4/README.md
- Source evidence: https://github.com/supercorp-ai/supercov/blob/55f5ce93a239829c224b89e6749991310be91ea4/contracts/v1/README.md

## jev-pref

Turns AGENTS.md preferences into rules checked by Jev against hunks, staged files or PRs.

- Repository: https://github.com/doeixd/jev-pref
- Category: Evaluation & Observability
- Jev decision: Jev classifies change evidence against configured rules; code maps answers to review outcomes.
- Purpose: Feeds semantic-rule findings to coding Agents without replacing type checks, tests or security audits.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/doeixd/jev-pref/
- Source evidence: https://github.com/doeixd/jev-pref/blob/9d77ea6069123a0b3eedf465ec39781842722b0a/README.md
- Source evidence: https://github.com/doeixd/jev-pref/blob/9d77ea6069123a0b3eedf465ec39781842722b0a/packages/jev-pref/src/jev.js
- Source evidence: https://github.com/doeixd/jev-pref/blob/9d77ea6069123a0b3eedf465ec39781842722b0a/packages/jev-pref/src/commands/review.js

## jevql

Adds Jev semantic filtering, grouping, and ranking around ordinary PostgreSQL without installing a database extension.

- Repository: https://github.com/kylemclaren/jevql
- Category: Data & Search
- Jev decision: The CLI or service layer evaluates jev\_\* calls over row text before completing the query.
- Purpose: Shares semantic SQL interfaces across a CLI, HTTP, MCP, and SDKs.
- Review scope: Jev calls run in the client or service layer, not inside the Postgres engine. Row content is sent to an external API.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kylemclaren/jevql/
- Source evidence: https://github.com/kylemclaren/jevql/blob/b5e546bafd18a2c887142bbbdfbce7ed9e06960e/internal/typesafe/client.go
- Source evidence: https://github.com/kylemclaren/jevql/blob/b5e546bafd18a2c887142bbbdfbce7ed9e06960e/README.md

## json-render

A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.

- Repository: https://github.com/vercel-labs/json-render
- Category: Creative Tools
- Jev decision: Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.
- Purpose: Provides an inspectable composition path alongside token-by-token JSON generation.
- Review scope: This covers the website’s Jev experiment, not the whole framework. Claims such as 3.21 s versus 880 ms were not independently verified.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vercel-labs/json-render/
- Source evidence: https://github.com/vercel-labs/json-render/blob/3ad381881194e7011ad3ccd6d668033495a06c29/README.md
- Source evidence: https://github.com/vercel-labs/json-render/blob/3ad381881194e7011ad3ccd6d668033495a06c29/apps/web/lib/jev/compose.ts

## cua

Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.

- Repository: https://github.com/trycua/cua
- Category: Browser & OS Action
- Jev decision: Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.
- Purpose: Provides Python and TypeScript loops with separate offline and live checks.
- Review scope: The Jev integration is a public-preview example, not the entire Cua framework or CUA-S1. Offline fixture checks do not establish live model performance. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/trycua/cua/
- Source evidence: https://github.com/trycua/cua/blob/83f142c4290a0f7d9ed545ae8532858c6e4f8145/libs/cua-driver/examples/jev-use/python/jev_adapter.py#L11
- Source evidence: https://github.com/trycua/cua/blob/83f142c4290a0f7d9ed545ae8532858c6e4f8145/libs/cua-driver/examples/jev-use/README.md
- Source evidence: https://github.com/trycua/cua/blob/83f142c4290a0f7d9ed545ae8532858c6e4f8145/README.md

## cline-plugin-jev-browser

A Cline plugin using an isolated Playwright browser and Jev decisions through Vercel AI Gateway.

- Repository: https://github.com/abeatrix/cline-plugin-jev-browser
- Category: Browser & OS Action
- Jev decision: Jev selects operations from a DOM target table; a separate text model supplies typed text when needed.
- Purpose: Captures before-and-after screenshots and yields on sensitive actions; completion still needs readback verification.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abeatrix/cline-plugin-jev-browser/
- Source evidence: https://github.com/abeatrix/cline-plugin-jev-browser/blob/c886dcb35cb7d64d682a56211f9b04a5345c6433/README.md
- Source evidence: https://github.com/abeatrix/cline-plugin-jev-browser/blob/c886dcb35cb7d64d682a56211f9b04a5345c6433/src/jev-model.ts
- Source evidence: https://github.com/abeatrix/cline-plugin-jev-browser/blob/c886dcb35cb7d64d682a56211f9b04a5345c6433/src/jev-run.ts
- Source evidence: https://github.com/abeatrix/cline-plugin-jev-browser/blob/c886dcb35cb7d64d682a56211f9b04a5345c6433/index.ts

## ai-hedge-fund

An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.

- Repository: https://github.com/virattt/ai-hedge-fund
- Category: Domain & Vertical Tools
- Jev decision: Converts strategy questions to System One requests and normalizes native answers to the project’s result format.
- Purpose: Allows Jev or other model backends to be used in the same research workflow.
- Review scope: The author describes an educational research prototype that currently does not execute trades. It is not an official Jev adapter, a zero-hallucination system, or evidence of profitability. This site has not backtested it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/virattt/ai-hedge-fund/
- Source evidence: https://github.com/virattt/ai-hedge-fund/blob/154a8b2f46dca0f40764d814e4e747b0ad71f4c4/hedge_fund/llm/client.py
- Source evidence: https://github.com/virattt/ai-hedge-fund/blob/154a8b2f46dca0f40764d814e4e747b0ad71f4c4/README.md

## jev-model-router

A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.

- Repository: https://github.com/davila7/claude-code-templates
- Category: Routing & Cost Optimization
- Jev decision: Evaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.
- Purpose: Makes routing rules and per-request choices explicit and configurable.
- Review scope: A davila7 community project, not an official Anthropic repository or mod. Aggregate savings and safety effects were not verified here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/davila7/claude-code-templates/
- Source evidence: https://github.com/davila7/claude-code-templates/blob/61bfcd1586bf1076f6d3cfa0436317c912811e6c/README.md
- Source evidence: https://github.com/davila7/claude-code-templates/blob/61bfcd1586bf1076f6d3cfa0436317c912811e6c/scripts/jev-spike.mjs
- Source evidence: https://github.com/davila7/claude-code-templates/blob/61bfcd1586bf1076f6d3cfa0436317c912811e6c/cli-tool/components/mods/productivity/jev-model-router/hooks/jev-model-router.ts
- Source evidence: https://github.com/davila7/claude-code-templates/blob/61bfcd1586bf1076f6d3cfa0436317c912811e6c/cli-tool/components/mods/productivity/jev-model-router/README.md

## rig-typesafeai

An experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.

- Repository: https://github.com/0xPlaygrounds/rig
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Reuses field layouts between questions and answers and validates answers against questions.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/0xplaygrounds/rig/
- Source evidence: https://github.com/0xPlaygrounds/rig/blob/2d16c1b25f6749b3a2cd841beddf767106495069/crates/rig-typesafeai/src/wire.rs#L40
- Source evidence: https://github.com/0xPlaygrounds/rig/blob/2d16c1b25f6749b3a2cd841beddf767106495069/crates/rig-typesafeai/README.md
- Source evidence: https://github.com/0xPlaygrounds/rig/blob/2d16c1b25f6749b3a2cd841beddf767106495069/examples/typesafeai_chat/README.md

## jev-trader

A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.

- Repository: https://github.com/jarrodwatts/jev-trader
- Category: Domain & Vertical Tools
- Jev decision: In Jev mode, order-book judgments feed code that simulates fills or submits configured post-only limit orders.
- Purpose: Defaults to a mock model and dry-runs without a private key; simulated results do not establish profitability.
- Review scope: Defaults to a mock model and simulates fills without a wallet key. Live trading, latency and profitability were not verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jarrodwatts/jev-trader/
- Source evidence: https://github.com/jarrodwatts/jev-trader/blob/b587759e459ea049590102e54a0b07800864cdc3/README.md
- Source evidence: https://github.com/jarrodwatts/jev-trader/blob/b587759e459ea049590102e54a0b07800864cdc3/src/model.ts
- Source evidence: https://github.com/jarrodwatts/jev-trader/blob/b587759e459ea049590102e54a0b07800864cdc3/src/trader.ts
- Source evidence: https://github.com/jarrodwatts/jev-trader/blob/b587759e459ea049590102e54a0b07800864cdc3/src/config.ts

## typesafe-computer-use

Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.

- Repository: https://github.com/awlevin/typesafe-computer-use
- Category: Browser & OS Action
- Jev decision: Selects the next step from deterministically extracted controls and actions before desktop execution.
- Purpose: Separates screen reading, action selection, and text generation.
- Review scope: README cost and speed comparisons use the author’s limited screenshot and goal setup, with some reasoning supplied by deterministic code. They are not general savings multipliers and were not independently retested.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/awlevin/typesafe-computer-use/
- Source evidence: https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/typesafe_computer_use/decide.py
- Source evidence: https://github.com/awlevin/typesafe-computer-use/blob/cc7b5066ae1a07b5e3182e8f87a9b5b6dfdcffc1/README.md

## typesafe-mario

An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.

- Repository: https://github.com/fhshaik/typesafe-mario
- Category: High-Frequency & Simulation
- Jev decision: Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.
- Purpose: Records model state and actions without screenshot input.
- Review scope: An experimental controller without game ROMs. Sustained rates, full completion and long-horizon reliability were not tested here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/fhshaik/typesafe-mario/
- Source evidence: https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/README.md
- Source evidence: https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/src/typesafe_mario/cli.py
- Source evidence: https://github.com/fhshaik/typesafe-mario/blob/ca22449ed187118d19326d1f54b01b6636578aa4/src/typesafe_mario/policy.py

## jev-drone

A MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.

- Repository: https://github.com/RomanSlack/jev-drone
- Category: High-Frequency & Simulation
- Jev decision: Uses range sectors, obstacle heights and target state to choose maneuvers and assess risk or target loss.
- Purpose: Separates tactical judgments from local guidance, reflexes and flight control.
- Review scope: The 2.5/50/500 Hz figures describe the author’s simulation architecture. They are not a flight-safety guarantee or validation on a real aircraft. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/RomanSlack/jev-drone/
- Source evidence: https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/tactics.py#L184
- Source evidence: https://github.com/RomanSlack/jev-drone/blob/cbeb53ce4f17a06ea490ae43effcdad231143610/README.md

## tsai-sc

A Jev harness for StarCraft shareware’s Strongarm mission, pausing the game during state reads and inference.

- Repository: https://github.com/phyous/tsai-sc
- Category: High-Frequency & Simulation
- Jev decision: Selects commands from structured game state and executes them with mouse and keyboard input.
- Purpose: The author provides a victory recording and verification report; this is a bounded mission experiment, not a real-time competitive benchmark.
- Review scope: The 421 decisions and victory are from an author-reported run with the game paused during inference; this site reviewed source and reports but did not reproduce it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/phyous/tsai-sc/
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/README.md
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/tsai_sc/typesafe.py
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/tsai_sc/controller.py
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/tsai_sc/verify.py
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/docs/verified-run.json
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/docs/run-environment.json
- Source evidence: https://github.com/phyous/tsai-sc/blob/6046ecc60156c4a3c04d384b41821a4ff08501b7/docs/visual-review.json

## oc-plugins

The oc-auto-perms plugin in an OpenCode plugin collection uses Jev to check tool intent against natural-language rules.

- Repository: https://github.com/OpeOginni/oc-plugins
- Category: Security & Guardrails
- Jev decision: Sends proposed actions and permission rules to Jev, then uses local logic to allow, deny, or ask the user.
- Purpose: Connects permission policies to judgments about individual tool actions.
- Review scope: The verified scope is oc-auto-perms, not every plugin in the monorepo. Model-based permission checks are not a complete security boundary; this site has not performed adversarial tests.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/OpeOginni/oc-plugins/
- Source evidence: https://github.com/OpeOginni/oc-plugins/blob/237f814908a56eb188c33af298c61531e72dbfe0/packages/oc-auto-perms/src/index.ts
- Source evidence: https://github.com/OpeOginni/oc-plugins/blob/237f814908a56eb188c33af298c61531e72dbfe0/README.md

## jev-block-android-ad

An Android notification and SMS filter that applies local OTP rules before asking Jev whether a message is advertising noise.

- Repository: https://github.com/ufec/jev-block-android-ad
- Category: Security & Guardrails
- Jev decision: Classifies text that passes local gates; local mapping decides whether to allow or suppress it.
- Purpose: Makes OTP handling and fail-open behavior explicit in code.
- Review scope: Local OTP matching is not an infallibility guarantee. Code-level gates do not replace device testing for false blocks.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ufec/jev-block-android-ad/
- Source evidence: https://github.com/ufec/jev-block-android-ad/blob/8da22d212a3392468686d21a020eb8ae06afe320/README.md
- Source evidence: https://github.com/ufec/jev-block-android-ad/blob/8da22d212a3392468686d21a020eb8ae06afe320/core/decision/src/commonMain/kotlin/me/ethanxu/jevnoisegate/core/decision/TypeSafeBackend.kt

## Jev-cu

A Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.

- Repository: https://github.com/Sac-Y/Jev-cu
- Category: Browser & OS Action
- Jev decision: Chooses targets and actions and assesses completion and risk; local policy controls execution or confirmation.
- Purpose: Uses text candidates and starts with a dry run by default.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/sac-y/jev-cu/
- Source evidence: https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/scripts/jev-decide.mjs#L6
- Source evidence: https://github.com/Sac-Y/Jev-cu/blob/38fb31de7dfe6209bbe6e04057c00c6e885ba577/README.md

## jev-pruner

A Claude Code output-pruning plugin filtering selected Bash output before it reaches the main model.

- Repository: https://github.com/tamaratran/jev-pruner
- Category: Context GC & Filter
- Jev decision: After length and content checks, Jev judges which chunks to retain while original output is archived.
- Purpose: Short output, errors and recognized structured or source content pass through unchanged.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tamaratran/jev-pruner/
- Source evidence: https://github.com/tamaratran/jev-pruner/blob/c5bf7df482b9f8df3dcb838034f06da0d8d0d07a/README.md
- Source evidence: https://github.com/tamaratran/jev-pruner/blob/c5bf7df482b9f8df3dcb838034f06da0d8d0d07a/src/jev.ts
- Source evidence: https://github.com/tamaratran/jev-pruner/blob/c5bf7df482b9f8df3dcb838034f06da0d8d0d07a/src/index.ts
- Source evidence: https://github.com/tamaratran/jev-pruner/blob/c5bf7df482b9f8df3dcb838034f06da0d8d0d07a/src/output.ts

## typesafe-adblock

An experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.

- Repository: https://github.com/realZachi/typesafe-adblock
- Category: Browser & OS Action
- Jev decision: Batches element text, labels, and link information into Noul questions and applies a threshold.
- Purpose: Shows how semantic judgments can be connected to concrete page elements.
- Review scope: The author calls it a fun experiment: it can miss ads or remove non-ads and does not handle tracking, malware, or video ads. Requires the user’s API key.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/realzachi/typesafe-adblock/
- Source evidence: https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/src/typesafe.js
- Source evidence: https://github.com/realZachi/typesafe-adblock/blob/7e067d243d87b7fe4d511653c0ddcd77b9beee18/README.md

## jev-cvss

Scripts that use Jev to select CVSS metrics from vulnerability descriptions, then compute v3.0, v3.1 or v4.0 scores in Python.

- Repository: https://github.com/Red5d/jev-cvss
- Category: Security & Guardrails
- Jev decision: Maps attack conditions and impacts to discrete metrics; local CVSS formulas calculate the numeric score.
- Purpose: Exposes the selected metrics and vector alongside the final score.
- Review scope: Score formulas are deterministic but model-selected metrics may be wrong; not penetration testing or validation of actual exploit impact. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/red5d/jev-cvss/
- Source evidence: https://github.com/Red5d/jev-cvss/blob/b0fdc446e4b9ef070abd570db347a277e496d70c/README.md
- Source evidence: https://github.com/Red5d/jev-cvss/blob/b0fdc446e4b9ef070abd570db347a277e496d70c/cvss3_jev.py

## typesafe-playground

Interactive Jev experiments for support-routing previews and 3D driving simulations.

- Repository: https://github.com/kavehmz/typesafe-playground
- Category: Evaluation & Observability
- Jev decision: Judges support messages or chooses lanes and target speed from structured simulated sensors.
- Purpose: Shows inputs, probabilities and resulting behavior together.
- Review scope: The support demo sends no real tickets or refunds. Jev reads structured simulated sensors, not images; this is not real-vehicle autonomous-driving validation. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kavehmz/typesafe-playground/
- Source evidence: https://github.com/kavehmz/typesafe-playground/blob/ec6102ef693de3c1775af5c844d48713b6d3f4a2/demo01/server.mjs#L67
- Source evidence: https://github.com/kavehmz/typesafe-playground/blob/ec6102ef693de3c1775af5c844d48713b6d3f4a2/README.md
- Source evidence: https://github.com/kavehmz/typesafe-playground/blob/ec6102ef693de3c1775af5c844d48713b6d3f4a2/demo01/README.md

## ruby\_decision\_model

A Ruby decision-model client for Jev through TypeSafe’s native API or OpenRouter.

- Repository: https://github.com/obie/ruby_decision_model
- Category: SDK & Decision Frameworks
- Jev decision: A shared Client sends state and typed questions and parses choices, probabilities, scores and usage.
- Purpose: Uses only the Ruby standard library and supports provider selection behind one interface.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/obie/ruby_decision_model/
- Source evidence: https://github.com/obie/ruby_decision_model/blob/f79a890ce4eaa8f83d8220727319ee7b11416e01/README.md
- Source evidence: https://github.com/obie/ruby_decision_model/blob/f79a890ce4eaa8f83d8220727319ee7b11416e01/lib/ruby_decision_model/providers/typesafe.rb
- Source evidence: https://github.com/obie/ruby_decision_model/blob/f79a890ce4eaa8f83d8220727319ee7b11416e01/lib/ruby_decision_model/client.rb
- Source evidence: https://github.com/obie/ruby_decision_model/blob/f79a890ce4eaa8f83d8220727319ee7b11416e01/lib/ruby_decision_model/response.rb

## plasmallm

A Jev Decisions adapter in a KDE Plasma assistant widget for displaying structured judgments.

- Repository: https://github.com/joshuaeroman/plasmallm
- Category: MCP & Integrations
- Jev decision: Converts the current message into decision questions and receives answers from TypeSafe or a compatible Decisions endpoint.
- Purpose: Makes decision models available in an existing desktop assistant UI.
- Review scope: The adapter evaluates each message independently without conversation memory. It does not establish that Jev controls all desktop actions or command routing.
- License: GPL-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/joshuaeroman/plasmallm/
- Source evidence: https://github.com/joshuaeroman/plasmallm/blob/b7d4975b31722624343d932a2b4a2d2b8a9952ff/package/contents/ui/adapters/decisions.js
- Source evidence: https://github.com/joshuaeroman/plasmallm/blob/b7d4975b31722624343d932a2b4a2d2b8a9952ff/README.md

## goodwatch-monorepo

A film-and-TV attribute-scoring experiment inside GoodWatch comparing Jev question designs and batch sizes.

- Repository: https://github.com/alp82/goodwatch-monorepo
- Category: Evaluation & Observability
- Jev decision: Asks whether predefined traits are present or how strongly they appear, recording scores, latency and Token usage.
- Purpose: Compares rating scales, input variants and batching over a frozen sample.
- Review scope: The source identifies a standalone scoring experiment, not proof of production recommendation use or superiority to vector recommendations; not rerun here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/alp82/goodwatch-monorepo/
- Source evidence: https://github.com/alp82/goodwatch-monorepo/blob/58aa7b3683f82ee4ea58f7da1007ee76400a7115/README.md
- Source evidence: https://github.com/alp82/goodwatch-monorepo/blob/58aa7b3683f82ee4ea58f7da1007ee76400a7115/goodwatch-flows/windmill/f/dna/prototype_comparison/jev_run.py

## mk-jev-fly-brain

Compares a fly-connectome spiking simulation, Jev and rule policies in the mk.js fighting game.

- Repository: https://github.com/lavallee/mk-jev-fly-brain
- Category: High-Frequency & Simulation
- Jev decision: Jev reads game state and chooses among the same seven moves offered to other controllers.
- Purpose: Uses control variants, match records and experiment notes to compare contributions.
- Review scope: This is a game-based spiking-network simulation, not a living fly or evidence of general biological intelligence or real-time capability. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/lavallee/mk-jev-fly-brain/
- Source evidence: https://github.com/lavallee/mk-jev-fly-brain/blob/8217937e6e725b0ce3160c6e1ab0183db8b8aa30/jev.py#L19
- Source evidence: https://github.com/lavallee/mk-jev-fly-brain/blob/8217937e6e725b0ce3160c6e1ab0183db8b8aa30/README.md

## SpecPi

A Pi configuration and extension bundle with an optional Jev advisor for capabilities and workflow checks.

- Repository: https://github.com/TannerMidd/SpecPi
- Category: SDK & Decision Frameworks
- Jev decision: Jev evaluates candidate capabilities, outputs and task state; per-feature switches control applying or recording advice.
- Purpose: Advisor failures return to the original path rather than guaranteeing better parameters or lower costs.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tannermidd/specpi/
- Source evidence: https://github.com/TannerMidd/SpecPi/blob/55c4c55e9d8d5c2a5ae803d7f4e5ebd5427a45c3/README.md
- Source evidence: https://github.com/TannerMidd/SpecPi/blob/55c4c55e9d8d5c2a5ae803d7f4e5ebd5427a45c3/extensions/jev-advisor/client.mjs
- Source evidence: https://github.com/TannerMidd/SpecPi/blob/55c4c55e9d8d5c2a5ae803d7f4e5ebd5427a45c3/extensions/jev-advisor/index.ts
- Source evidence: https://github.com/TannerMidd/SpecPi/blob/55c4c55e9d8d5c2a5ae803d7f4e5ebd5427a45c3/extensions/jev-advisor/broker.mjs

## rift

An optional TypeSafe decision client in the Rust coding terminal Rift for bounded Jev judgments.

- Repository: https://github.com/exYze/rift
- Category: CLI & Pipelines
- Jev decision: Sends state and typed questions to System One and parses answers for terminal workflows.
- Purpose: Adds a separate decision interface alongside generative coding models.
- Review scope: Rift’s overall performance benchmarks cannot be attributed to this Jev integration. This site reviewed client code but did not execute terminal workflows.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/exyze/rift/
- Source evidence: https://github.com/exYze/rift/blob/b446c3fb8ecf0b0e445b16436fd937262956d010/crates/rift-typesafe/src/lib.rs
- Source evidence: https://github.com/exYze/rift/blob/b446c3fb8ecf0b0e445b16436fd937262956d010/README.md

## Jev-Moderation-Bot

A Discord moderation bot using Jev to check spam and scam links, with local warning and timeout rules.

- Repository: https://github.com/brainstormity/Jev-Moderation-Bot
- Category: Security & Guardrails
- Jev decision: Assesses messages or recent member history; the bot applies deletion, warnings or timeouts.
- Purpose: Connects judgments, moderation logs and manual correction controls.
- Review scope: Model moderation can produce false positives, and message history is cached for evaluation. Throughput, safety effects and deployment were not verified.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/brainstormity/jev-moderation-bot/
- Source evidence: https://github.com/brainstormity/Jev-Moderation-Bot/blob/1629ac80bea758883ee7541ffc654c83acfae4b6/README.md
- Source evidence: https://github.com/brainstormity/Jev-Moderation-Bot/blob/1629ac80bea758883ee7541ffc654c83acfae4b6/typesafe/__init__.py

## leadgenrationaivoiceagent

An experimental TypeSafe module in a marketing and voice platform chooses specialization labels for agent roles.

- Repository: https://github.com/sumitrevolt/leadgenrationaivoiceagent
- Category: Domain & Vertical Tools
- Jev decision: Sends role data and bounded specialization candidates to Choice, then maps labels to capabilities.
- Purpose: Provides an example of role classification in a business application.
- Review scope: The verified integration classifies role specializations. Per-turn voice-intent routing and 300 ms performance were not established. API-failure defaults are not model confidence. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/sumitrevolt/leadgenrationaivoiceagent/
- Source evidence: https://github.com/sumitrevolt/leadgenrationaivoiceagent/blob/0ed2da0ea032eb077a196798d1ed5e6aa8602a2b/app/platform/agent_talent_pool.py#L59
- Source evidence: https://github.com/sumitrevolt/leadgenrationaivoiceagent/blob/0ed2da0ea032eb077a196798d1ed5e6aa8602a2b/README.md
- Source evidence: https://github.com/sumitrevolt/leadgenrationaivoiceagent/blob/0ed2da0ea032eb077a196798d1ed5e6aa8602a2b/ops/README.md
- Source evidence: https://github.com/sumitrevolt/leadgenrationaivoiceagent/blob/0ed2da0ea032eb077a196798d1ed5e6aa8602a2b/app/platform/typesafe_integration.py

## Agent

An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.

- Repository: https://github.com/AgentiLoop/Agent
- Category: Security & Guardrails
- Jev decision: Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.
- Purpose: API failures generally allow the command with a warning, so it is not complete system protection.
- Review scope: Jev is an optional additional risk judgment and failures generally fail open; no system-security validation was performed.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/agentiloop/agent/
- Source evidence: https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/README.md
- Source evidence: https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/Agent/Services/JevAdvisor.swift
- Source evidence: https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/TypeSafeKit/Sources/TypeSafeMiddleware/JevProvider.swift
- Source evidence: https://github.com/AgentiLoop/Agent/blob/078f87ceca1d1190cc73706ac8ec16442e766a27/TypeSafeKit/Sources/TypeSafeKit/TypeSafeClient.swift

## captaincore

Jev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.

- Repository: https://github.com/CaptainCore/captaincore
- Category: Security & Guardrails
- Jev decision: Sends scan rules, matched snippets, and file context to Jev to assess likely true positives and suggested handling.
- Purpose: Organizes rule-based scan findings into a queue for human review.
- Review scope: The ask and triage commands were verified; the old plugin-compatibility prediction claim was unsupported. A scan probability is not a definitive malware verdict or security guarantee.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/captaincore/captaincore/
- Source evidence: https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/cmd/typesafe.go
- Source evidence: https://github.com/CaptainCore/captaincore/blob/f54e0669350707b2f4f4c67a0130fdd6574bd0b5/readme.md

## OpenWhisper

A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.

- Repository: https://github.com/Knuckles92/OpenWhisper
- Category: Voice & Conversation
- Jev decision: Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.
- Purpose: Keeps model probabilities separate from local thresholds, switches and failure fallbacks.
- Review scope: Jev is an optional text-judgment module, not proof that all meeting processing stays local. Effects and latency were not tested here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/knuckles92/openwhisper/
- Source evidence: https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/README.md
- Source evidence: https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/services/typesafe.py
- Source evidence: https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/docs/typesafe-fast-judgments.md
- Source evidence: https://github.com/Knuckles92/OpenWhisper/blob/9e83653df183096104769e302a3c907cb277c551/meeting/agent/typesafe_signals.py

## jev

A Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.

- Repository: https://github.com/BorisLeMeec/jev
- Category: Codebase & Graph Pathfinding
- Jev decision: Screens and verifies code relevance before whole files enter the agent context.
- Purpose: Returns file locations and judgments for focused inspection.
- Review scope: This is code retrieval, not model-tier routing. Some reported comparisons rely on labeled private repositories that are not published. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/borislemeec/jev/
- Source evidence: https://github.com/BorisLeMeec/jev/blob/e81c1d006b8b23a616486610f311039088521d0c/internal/typesafe/client.go#L23
- Source evidence: https://github.com/BorisLeMeec/jev/blob/e81c1d006b8b23a616486610f311039088521d0c/README.md
- Source evidence: https://github.com/BorisLeMeec/jev/blob/e81c1d006b8b23a616486610f311039088521d0c/bench/README.md

## runline

A TypeSafe plugin exposing Jev decisions as callable actions in Runline Agent JavaScript.

- Repository: https://github.com/Michaelliv/runline
- Category: SDK & Decision Frameworks
- Jev decision: evaluate, choice, score and noul actions submit questions and retain answers and usage.
- Purpose: Composes decisions with Runline plugins; it does not automatically inspect every shell command for safety.
- Review scope: Reviewed the fixed-version README and call path.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/michaelliv/runline/
- Source evidence: https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/README.md
- Source evidence: https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/packages/runline-plugins/typesafe/src/shared.ts
- Source evidence: https://github.com/Michaelliv/runline/blob/6bdddfa82cd95b6b9a07e57fd93a271ae83a0d1b/packages/runline-plugins/typesafe/src/index.ts

## super-jev

A TypeScript decision-to-action harness connecting evidence, Jev judgments, permitted actions, and outcome records.

- Repository: https://github.com/Kevthetech143/super-jev
- Category: SDK & Decision Frameworks
- Jev decision: Submits typed questions, validates answers, and lets domain rules choose registered tools with permission and argument checks.
- Purpose: Keeps local traces of judgments, tool calls, and outcomes.
- Review scope: An experimental harness. Default demos use labeled fixtures; the author’s small live smoke tests do not establish general production readiness. This site has not run it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kevthetech143/super-jev/
- Source evidence: https://github.com/Kevthetech143/super-jev/blob/69bb082587459aa2e78245fbb713aac54d53a204/src/jev.ts
- Source evidence: https://github.com/Kevthetech143/super-jev/blob/69bb082587459aa2e78245fbb713aac54d53a204/README.md

## tenbin

Documentation, an MCP server and a Skill for designing Jev judgments with question linting, batch evaluation and calibration.

- Repository: https://github.com/simota/tenbin
- Category: MCP & Integrations
- Jev decision: Runs Choice, Score and Noul over samples and uses measured results to design local thresholds.
- Purpose: Connects question design, sample evaluation and runtime rules.
- Review scope: Calibration requires labeled samples for the workload and does not make judgments infallible; tests were not rerun here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/simota/tenbin/
- Source evidence: https://github.com/simota/tenbin/blob/80e797986b2334e988bb8c940329a31fe138fbdc/README.md
- Source evidence: https://github.com/simota/tenbin/blob/80e797986b2334e988bb8c940329a31fe138fbdc/tenbin/src/client.ts

## qualm

A TypeScript wrapper for Jev decisions with an explicit unsure branch.

- Repository: https://github.com/qddegtya/qualm
- Category: SDK & Decision Frameworks
- Jev decision: Preserves probabilities and option types and routes uncertainty to a caller-supplied fallback.
- Purpose: Uses types to require uncertainty handling without guaranteeing model correctness.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/qddegtya/qualm/
- Source evidence: https://github.com/qddegtya/qualm/blob/e1aacf6844f312ba95eb6a1bd26fad15575a7173/README.md
- Source evidence: https://github.com/qddegtya/qualm/blob/e1aacf6844f312ba95eb6a1bd26fad15575a7173/README.zh-CN.md
- Source evidence: https://github.com/qddegtya/qualm/blob/e1aacf6844f312ba95eb6a1bd26fad15575a7173/src/provider.ts
- Source evidence: https://github.com/qddegtya/qualm/blob/e1aacf6844f312ba95eb6a1bd26fad15575a7173/src/client.ts

## your-signal

A BYOK Chrome extension using Jev to score X posts against personal preferences and adjust their display.

- Repository: https://github.com/MithrilMan/your-signal
- Category: Context GC & Filter
- Jev decision: Scores relevance, substance, usefulness, and promotion; local weights and thresholds control highlighting, collapsing, or hiding.
- Purpose: Makes personal feed rules adjustable and display changes reversible.
- Review scope: Display decisions run locally, but post text submitted for scoring is sent to TypeSafe. Filtering accuracy and privacy implementation have not been independently verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/mithrilman/your-signal/
- Source evidence: https://github.com/MithrilMan/your-signal/blob/2970c069231b96f094f6fcfe4c11bfcf2da0ecb2/extension/background.js
- Source evidence: https://github.com/MithrilMan/your-signal/blob/2970c069231b96f094f6fcfe4c11bfcf2da0ecb2/README.md

## jev-scout

A repository and Rust crate search tool that asks Jev to score and select retrieved candidates for a request.

- Repository: https://github.com/AkashPriyadarshii/jev-scout
- Category: Data & Search
- Jev decision: Compares candidate information with the request, scores fit and maintenance signals, and chooses a candidate.
- Purpose: Keeps recommendations tied to retrieved candidates and source links.
- Review scope: Retrieved candidates do not guarantee search coverage, correct scoring or project quality; “zero hallucination” is not a verified conclusion here. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/akashpriyadarshii/jev-scout/
- Source evidence: https://github.com/AkashPriyadarshii/jev-scout/blob/acae39260212267288353451c6977aeab7d6af1d/README.md
- Source evidence: https://github.com/AkashPriyadarshii/jev-scout/blob/acae39260212267288353451c6977aeab7d6af1d/src/jev.rs

## jev-play-ping-pong

Uses Jev to choose serve direction, return angle and pace in a browser table-tennis game.

- Repository: https://github.com/Icohen007/jev-play-ping-pong
- Category: High-Frequency & Simulation
- Jev decision: Reads structured telemetry and selects contact and pace through Choice before code executes inputs.
- Purpose: Keeps action, latency and match records for reviewing a run.
- Review scope: The 11–0 result is one author-recorded Club-difficulty match. Its 325 ms median API latency and win do not establish a general win rate or latency guarantee. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/icohen007/jev-play-ping-pong/
- Source evidence: https://github.com/Icohen007/jev-play-ping-pong/blob/af8eb3a1f2a14fcebca5accf23a7875b09b30d5e/src/typesafe.mjs#L1
- Source evidence: https://github.com/Icohen007/jev-play-ping-pong/blob/af8eb3a1f2a14fcebca5accf23a7875b09b30d5e/README.md

## typesafe-rs

A community Rust Jev client with async requests, an optional blocking interface and local mock testing.

- Repository: https://github.com/AbdelStark/typesafe-rs
- Category: SDK & Decision Frameworks
- Jev decision: Sends state and named questions to TypeSafe and parses choice, score and noul answers.
- Purpose: Provides client configuration, retries and error types for async or blocking Rust applications.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abdelstark/typesafe-rs/
- Source evidence: https://github.com/AbdelStark/typesafe-rs/blob/8e8b7a2ae1af5bf7d3e5d831e634fdf328b2fbcc/README.md
- Source evidence: https://github.com/AbdelStark/typesafe-rs/blob/8e8b7a2ae1af5bf7d3e5d831e634fdf328b2fbcc/crates/typesafe-rs/src/client.rs
- Source evidence: https://github.com/AbdelStark/typesafe-rs/blob/8e8b7a2ae1af5bf7d3e5d831e634fdf328b2fbcc/crates/typesafe-rs/src/transport.rs
- Source evidence: https://github.com/AbdelStark/typesafe-rs/blob/8e8b7a2ae1af5bf7d3e5d831e634fdf328b2fbcc/crates/typesafe-rs/src/types/response.rs

## jevmeter

Creates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.

- Repository: https://github.com/ChetasLua/jevmeter
- Category: Creative Tools
- Jev decision: Scores transcript sentences with preset questions and scales for meters placed on the video timeline.
- Purpose: Aligns sentence scores with the corresponding video segments for review.
- Review scope: Transcript scoring is a model judgment, not external fact-checking or mind-reading. Author-reported accuracy and cost were not independently retested; video processing does not imply hard real-time streaming.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/chetaslua/jevmeter/
- Source evidence: https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/jevmeter/score.py
- Source evidence: https://github.com/ChetasLua/jevmeter/blob/cbf8e117b5b8835e3294c3a8ee652c7dfa737a9a/README.md

## loki

Loki optionally adds Jev typed-judgment tools and routes a new session to a model within the selected gateway.

- Repository: https://github.com/wundercorp/loki
- Category: Routing & Cost Optimization
- Jev decision: Assesses the first task’s capability needs; local policy chooses a same-gateway model and keeps the route sticky.
- Purpose: Makes model routing explicit while retaining the selected route for the session.
- Review scope: The README describes companion tools and session routing, not a guaranteed completion referee. Cost effects were not measured here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wundercorp/loki/
- Source evidence: https://github.com/wundercorp/loki/blob/5f1aea7c786f5ea8c5f9b9f2db2b791ec326c535/README.md
- Source evidence: https://github.com/wundercorp/loki/blob/5f1aea7c786f5ea8c5f9b9f2db2b791ec326c535/agent/typesafe_client.py
- Source evidence: https://github.com/wundercorp/loki/blob/5f1aea7c786f5ea8c5f9b9f2db2b791ec326c535/agent/jev_auto_router.py

## snifftest

A Markdown and plain-text prose linter using local rules and optional Jev judgments.

- Repository: https://github.com/DanRWilloughby/snifftest
- Category: Creative Tools
- Jev decision: Assesses paragraphs against style rules such as redundant closings, clichés and excessive hedging.
- Purpose: Reports files, lines and rules while leaving revision to the author.
- Review scope: Style-rule hits do not establish that AI wrote a passage. This is not a reliable authorship or AI-origin detector. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/danrwilloughby/snifftest/
- Source evidence: https://github.com/DanRWilloughby/snifftest/blob/240653e2b082c114c38fed50a42e7eb311e21219/src/jev.ts#L50
- Source evidence: https://github.com/DanRWilloughby/snifftest/blob/240653e2b082c114c38fed50a42e7eb311e21219/README.md
- Source evidence: https://github.com/DanRWilloughby/snifftest/blob/240653e2b082c114c38fed50a42e7eb311e21219/assets/nose/README.md

## refgarden

A visual-reference gallery drawing from The Met, NASA and Cosmos, with Jev in local Explore mode.

- Repository: https://github.com/AlbionaHoti/refgarden
- Category: Creative Tools
- Jev decision: Jev selects search phrases and highlights references using titles and descriptions, not image pixels.
- Purpose: Keeps source links; the public search demo does not call Jev and is not evidence of visual clustering.
- Review scope: Local Explore uses text metadata for Jev judgments; the public demo does not call Jev, and image understanding or clustering was not verified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/albionahoti/refgarden/
- Source evidence: https://github.com/AlbionaHoti/refgarden/blob/6affd25a31dd0ed39fc9f71508732fb7ee0b8acc/README.md
- Source evidence: https://github.com/AlbionaHoti/refgarden/blob/6affd25a31dd0ed39fc9f71508732fb7ee0b8acc/src/jev-client.ts
- Source evidence: https://github.com/AlbionaHoti/refgarden/blob/6affd25a31dd0ed39fc9f71508732fb7ee0b8acc/src/decision.ts
- Source evidence: https://github.com/AlbionaHoti/refgarden/blob/6affd25a31dd0ed39fc9f71508732fb7ee0b8acc/server.ts

## jev-axi

A CLI for Jev pick, rate, check, rank, triage, and guard tasks, with optional hooks before Agent tool calls.

- Repository: https://github.com/shiftynick/jev-axi
- Category: CLI & Pipelines
- Jev decision: Converts input state and options into structured questions, returning results or risk scores for local policy.
- Purpose: Reuses the same decision commands in scripts and Agent workflows.
- Review scope: Hooks and risk scores are additional checks, not a guarantee against all dangerous commands or injection. Cost, latency, and protection have not been independently retested.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/shiftynick/jev-axi/
- Source evidence: https://github.com/shiftynick/jev-axi/blob/db4b6fe56f962463d3924019bd038462a2190b2d/src/client.ts
- Source evidence: https://github.com/shiftynick/jev-axi/blob/db4b6fe56f962463d3924019bd038462a2190b2d/README.md

## typesafe-skill-router

An opt-in Hermes Agent plugin that asks Jev to suggest one relevant skill before a model call.

- Repository: https://github.com/DECRUX9812/typesafe-skill-router
- Category: Routing & Cost Optimization
- Jev decision: Compares the request with the skill roster; inserts a suggestion only when suitable and abstains on failure.
- Purpose: Adds a targeted skill hint that the Agent can still ignore.
- Review scope: Recommendations do not force loading or guarantee optimality; cost, Token savings and time to first output were not measured here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/decrux9812/typesafe-skill-router/
- Source evidence: https://github.com/DECRUX9812/typesafe-skill-router/blob/e6cdac26f9ed588b4a94b8a2f7f9f026e1b9faf3/README.md
- Source evidence: https://github.com/DECRUX9812/typesafe-skill-router/blob/e6cdac26f9ed588b4a94b8a2f7f9f026e1b9faf3/typesafe_router/client.py

## jev-calibration-audit

Audits Jev calibration, option-wording effects and Korean judgments through public APIs and datasets.

- Repository: https://github.com/jujumilk3/jev-calibration-audit
- Category: Evaluation & Observability
- Jev decision: Collects Noul and Choice outputs and compares them with labels for error, accuracy and stability.
- Purpose: Keeps per-call records and experiment notes to qualify conclusions.
- Review scope: Calibration varies with tasks, labels and answer options. These experiments do not guarantee reliable confidence in every domain. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jujumilk3/jev-calibration-audit/
- Source evidence: https://github.com/jujumilk3/jev-calibration-audit/blob/daab9e2c2d5d5683bf07f3482deb653c26856219/src/jev_audit/client.py#L12
- Source evidence: https://github.com/jujumilk3/jev-calibration-audit/blob/daab9e2c2d5d5683bf07f3482deb653c26856219/README.md

## openclaw-typesafe-ai

An independent OpenClaw plugin registering one explicitly invoked typesafe\_decide tool.

- Repository: https://github.com/Olli0103/openclaw-typesafe-ai
- Category: MCP & Integrations
- Jev decision: Sends caller-provided state and questions to TypeSafe and returns typed Jev decisions.
- Purpose: Adds no chat provider, automatic hooks or background service; it is not a scraping or CAPTCHA plugin.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/olli0103/openclaw-typesafe-ai/
- Source evidence: https://github.com/Olli0103/openclaw-typesafe-ai/blob/985718448bf38a3a58d18389d376621b9bc54615/README.md
- Source evidence: https://github.com/Olli0103/openclaw-typesafe-ai/blob/985718448bf38a3a58d18389d376621b9bc54615/src/client.ts
- Source evidence: https://github.com/Olli0103/openclaw-typesafe-ai/blob/985718448bf38a3a58d18389d376621b9bc54615/src/index.ts

## typesafe-sdk-java

A community Java TypeSafe client with a Spring Boot Starter for configuring Jev calls.

- Repository: https://github.com/Premo-Cloud/typesafe-sdk-java
- Category: SDK & Decision Frameworks
- Jev decision: Sends Java state and Noul, Choice, and Score questions to System One and parses typed results.
- Purpose: Reuses request, configuration, and error-handling code in Java and Spring Boot projects.
- Review scope: An unofficial community client requiring Java 17+. Integration code was verified, but compatibility and production use were not tested by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/premo-cloud/typesafe-sdk-java/
- Source evidence: https://github.com/Premo-Cloud/typesafe-sdk-java/blob/833893bc46aa3de2e07352a729ff618ea07b6350/typesafe-sdk/src/main/java/io/github/premocloud/typesafe/TypeSafeClient.java
- Source evidence: https://github.com/Premo-Cloud/typesafe-sdk-java/blob/833893bc46aa3de2e07352a729ff618ea07b6350/README.md

## typesafe-go

A TypeSafe System One client that uses only the Go standard library to send Jev questions and read structured answers.

- Repository: https://github.com/2389-research/typesafe-go
- Category: SDK & Decision Frameworks
- Jev decision: Builds requests from state and Noul, Choice or Score questions, then validates and parses responses.
- Purpose: Reuses transport, typed mappings and error handling in Go applications.
- Review scope: No third-party Go dependencies does not mean zero supply-chain risk or a service-security guarantee.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/2389-research/typesafe-go/
- Source evidence: https://github.com/2389-research/typesafe-go/blob/1f9ac50bab4921862327dadc45871bc24b381b3e/README.md
- Source evidence: https://github.com/2389-research/typesafe-go/blob/1f9ac50bab4921862327dadc45871bc24b381b3e/typesafe.go

## typesafe-go

An unofficial Go SDK with typed answers, retries and context cancellation.

- Repository: https://github.com/cole-gillespie/typesafe-go
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/cole-gillespie/typesafe-go/
- Source evidence: https://github.com/cole-gillespie/typesafe-go/blob/188247d639e8aacecd7a0d1aceaf8a4c66f8fa57/client.go#L21
- Source evidence: https://github.com/cole-gillespie/typesafe-go/blob/188247d639e8aacecd7a0d1aceaf8a4c66f8fa57/README.md

## pi-typesafe

A Pi Jev extension providing a decision tool, terminal playground commands and an API for other extensions.

- Repository: https://github.com/DevMortimer/pi-typesafe
- Category: MCP & Integrations
- Jev decision: A shared client batches typed questions, validates responses and records usage and availability.
- Purpose: Centralizes key and client handling so other extensions can reuse the decision interface.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/devmortimer/pi-typesafe/
- Source evidence: https://github.com/DevMortimer/pi-typesafe/blob/b822b8a0e4d729bd0db055a72581f21da686dd42/README.md
- Source evidence: https://github.com/DevMortimer/pi-typesafe/blob/b822b8a0e4d729bd0db055a72581f21da686dd42/src/client.ts
- Source evidence: https://github.com/DevMortimer/pi-typesafe/blob/b822b8a0e4d729bd0db055a72581f21da686dd42/src/extension.ts

## typesafe-sdk-swift

An experimental Swift SDK for TypeSafe using Swift Package Manager, Swift concurrency, and URLSession.

- Repository: https://github.com/marandaneto/typesafe-sdk-swift
- Category: SDK & Decision Frameworks
- Jev decision: Sends state and typed questions to System One and receives structured answers through async/await.
- Purpose: Lets Swift applications reuse Jev request and response handling.
- Review scope: Marked experimental by the author. Cross-platform compilation does not mean runtime testing on every minimum OS version; this site has not tested it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/marandaneto/typesafe-sdk-swift/
- Source evidence: https://github.com/marandaneto/typesafe-sdk-swift/blob/5a8565791b56d6ba874de9f7ea206b8a1a53c794/Sources/TypeSafe/TypeSafeClient.swift
- Source evidence: https://github.com/marandaneto/typesafe-sdk-swift/blob/5a8565791b56d6ba874de9f7ea206b8a1a53c794/README.md

## typesafe-sdk-rust

A Rust client for TypeSafe with asynchronous and optional blocking calls plus typed question and answer wrappers.

- Repository: https://github.com/codeitlikemiley/typesafe-sdk-rust
- Category: SDK & Decision Frameworks
- Jev decision: Builds Jev requests and handles authentication, transport and structured response parsing.
- Purpose: Reuses API models and transport logic in Rust applications.
- Review scope: Type wrappers do not eliminate every invalid request or runtime error; this crate and the live API were not tested here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/codeitlikemiley/typesafe-sdk-rust/
- Source evidence: https://github.com/codeitlikemiley/typesafe-sdk-rust/blob/e7050df6baa611bc9088f1a361b4b90e8571929d/README.md
- Source evidence: https://github.com/codeitlikemiley/typesafe-sdk-rust/blob/e7050df6baa611bc9088f1a361b4b90e8571929d/src/client.rs

## typesafe-sdk-php

A community TypeSafe SDK for PHP 8.2+, with synchronous calls and Guzzle-based async requests.

- Repository: https://github.com/Butochnikov/typesafe-sdk-php
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/butochnikov/typesafe-sdk-php/
- Source evidence: https://github.com/Butochnikov/typesafe-sdk-php/blob/d44db82dbf4ff601b123731b517fba1ca9092278/src/TypeSafeClient.php#L32
- Source evidence: https://github.com/Butochnikov/typesafe-sdk-php/blob/d44db82dbf4ff601b123731b517fba1ca9092278/README.md
- Source evidence: https://github.com/Butochnikov/typesafe-sdk-php/blob/d44db82dbf4ff601b123731b517fba1ca9092278/README.ru.md
- Source evidence: https://github.com/Butochnikov/typesafe-sdk-php/blob/d44db82dbf4ff601b123731b517fba1ca9092278/src/Constants.php

## typesafe-sdk-js

The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.

- Repository: https://github.com/typesafe-ai/typesafe-sdk-js
- Category: SDK & Decision Frameworks
- Jev decision: systemOne submits state and named questions and infers answer types from the questions.
- Purpose: Includes ESM, CommonJS and TypeScript declarations for application integration.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/typesafe-ai/typesafe-sdk-js/
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/README.md
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/src/client.ts
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-js/blob/66880ccded6cb642dc1809620c2b108c33730214/src/types.ts

## jev-browser-use

A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.

- Repository: https://github.com/wy-coliney/jev-browser-use
- Category: Browser & OS Action
- Jev decision: Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.
- Purpose: Separates repetitive page choices into decision steps while reusing the browser connection.
- Review scope: Requires a separately configured Codex browser connection. The author’s reported 5–10× speedup concerns their own workflows, not a general guarantee; this site has not retested it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/wy-coliney/jev-browser-use/
- Source evidence: https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/skills/jev-browser-use/bridge.mjs
- Source evidence: https://github.com/wy-coliney/jev-browser-use/blob/f14b60e0ae1ee90cd73eb6650e30a666a84c021a/README.md

## goodall

An optional TypeSafe package in a Go Agent library, using Jev as a tool or routing judge alongside chat models.

- Repository: https://github.com/bensyverson/goodall
- Category: SDK & Decision Frameworks
- Jev decision: Submits typed questions through a separate client for tools, turn routing and a mail-triage example.
- Purpose: Keeps typed judgments separate from the generative Agent loop.
- Review scope: Jev is not goodall’s primary chat provider; the mail example proposes routes and drafts without sending mail. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bensyverson/goodall/
- Source evidence: https://github.com/bensyverson/goodall/blob/a612f04a712cf6c68926b780bd98e5087c687224/README.md
- Source evidence: https://github.com/bensyverson/goodall/blob/a612f04a712cf6c68926b780bd98e5087c687224/typesafe/client.go

## jev-go

A Go TypeSafe System One client with typed questions, answers and batching helpers.

- Repository: https://github.com/Gaurav-Gosain/jev-go
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/gaurav-gosain/jev-go/
- Source evidence: https://github.com/Gaurav-Gosain/jev-go/blob/c9867e4afad0ddfaf4b9deb31038218495712fd0/client.go#L20
- Source evidence: https://github.com/Gaurav-Gosain/jev-go/blob/c9867e4afad0ddfaf4b9deb31038218495712fd0/README.md

## swift-typesafe

A community Swift TypeSafe client with typed questions, dynamic questions and response parsing.

- Repository: https://github.com/ainame/swift-typesafe
- Category: SDK & Decision Frameworks
- Jev decision: Sends Jev questions through systemOne and exposes answers as Swift types or dynamic maps.
- Purpose: Supports integration on its documented platforms; Swift and OS requirements are version-specific.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ainame/swift-typesafe/
- Source evidence: https://github.com/ainame/swift-typesafe/blob/c990db869c10030b98af02e1219f5bca1e2c7cc2/README.md
- Source evidence: https://github.com/ainame/swift-typesafe/blob/c990db869c10030b98af02e1219f5bca1e2c7cc2/Sources/TypeSafe/TypeSafeClient.swift

## typesafe\_sdk

An Elixir TypeSafe SDK that brings Jev’s typed questions and probabilistic answers into Elixir applications.

- Repository: https://github.com/nshkrdotcom/typesafe_sdk
- Category: SDK & Decision Frameworks
- Jev decision: Builds state and Noul, Choice, and Score requests and parses System One responses.
- Purpose: Reuses Elixir data structures and client wrappers for decision APIs.
- Review scope: The current README describes a TypeSafe/Jev SDK. Older metadata about generic LLM streaming should not be treated as verified functionality. This site has not run it.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/nshkrdotcom/typesafe_sdk/
- Source evidence: https://github.com/nshkrdotcom/typesafe_sdk/blob/deaedd63882045ea0d8e9273002280a20809e170/lib/typesafe_sdk/generated/system_one.ex
- Source evidence: https://github.com/nshkrdotcom/typesafe_sdk/blob/deaedd63882045ea0d8e9273002280a20809e170/README.md

## typesafe-ai

A Rust TypeSafe client with asynchronous reqwest or blocking ureq backends and observable retries.

- Repository: https://github.com/Twister915/typesafe-ai
- Category: SDK & Decision Frameworks
- Jev decision: Sends multiple Jev questions over shared state and parses typed answers, probabilities and usage.
- Purpose: Offers synchronous or asynchronous integration with inspectable errors.
- Review scope: The README and call example were inspected; all feature combinations, backends and retry behaviors were not independently tested.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/twister915/typesafe-ai/
- Source evidence: https://github.com/Twister915/typesafe-ai/blob/d4455efb1d061ae6aac47b40c42ef390182201b1/README.md
- Source evidence: https://github.com/Twister915/typesafe-ai/blob/d4455efb1d061ae6aac47b40c42ef390182201b1/examples/tsg/main.rs
- Source evidence: https://github.com/Twister915/typesafe-ai/blob/d4455efb1d061ae6aac47b40c42ef390182201b1/src/reqwest_client.rs

## typesafe-ai-rs

An independently maintained Rust SDK with async and blocking clients, retries and response metadata.

- Repository: https://github.com/gilljon/typesafe-ai-rs
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/gilljon/typesafe-ai-rs/
- Source evidence: https://github.com/gilljon/typesafe-ai-rs/blob/06f52208c22f63326226446926859174c538e296/src/client.rs#L78
- Source evidence: https://github.com/gilljon/typesafe-ai-rs/blob/06f52208c22f63326226446926859174c538e296/README.md
- Source evidence: https://github.com/gilljon/typesafe-ai-rs/blob/06f52208c22f63326226446926859174c538e296/src/lib.rs

## typesafe-sdk

A community Ruby client for TypeSafe System One, defaulting to jev-latest.

- Repository: https://github.com/joshmn/typesafe-sdk
- Category: SDK & Decision Frameworks
- Jev decision: Builds Choice, Score and Noul questions and exposes parsed answers by type.
- Purpose: Lets Ruby programs read choices, scores and probabilities directly.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/joshmn/typesafe-sdk/
- Source evidence: https://github.com/joshmn/typesafe-sdk/blob/abde35d2ebae5d7dda900d1aa122ea5b653f1d9e/README.md
- Source evidence: https://github.com/joshmn/typesafe-sdk/blob/abde35d2ebae5d7dda900d1aa122ea5b653f1d9e/lib/typesafe/sdk/client.rb
- Source evidence: https://github.com/joshmn/typesafe-sdk/blob/abde35d2ebae5d7dda900d1aa122ea5b653f1d9e/lib/typesafe/sdk/net_http_transport.rb
- Source evidence: https://github.com/joshmn/typesafe-sdk/blob/abde35d2ebae5d7dda900d1aa122ea5b653f1d9e/lib/typesafe/sdk/answer_parser.rb

## typesafe-sdk-go

A Go TypeSafe SDK for defining typed questions and reading Jev choices, scores, and probabilities.

- Repository: https://github.com/Tangerg/typesafe-sdk-go
- Category: SDK & Decision Frameworks
- Jev decision: Validates requests, calls System One, and decodes typed answers.
- Purpose: Packages authentication, requests, and error handling in a reusable Go client.
- Review scope: Typed responses do not guarantee calibrated probabilities or correct judgments. The previous claim of being designed specifically for distributed systems was unsupported.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tangerg/typesafe-sdk-go/
- Source evidence: https://github.com/Tangerg/typesafe-sdk-go/blob/e2f9f8353974fce1d2d2e4dd4283d5e306e8c2a8/client.go
- Source evidence: https://github.com/Tangerg/typesafe-sdk-go/blob/e2f9f8353974fce1d2d2e4dd4283d5e306e8c2a8/README.md

## hermes-jev

An asynchronous Jev companion for Hermes Agent covering relevance, completion, recovery and optional admission decisions.

- Repository: https://github.com/keeltrace/hermes-jev
- Category: Decision Tools
- Jev decision: Jev evaluates bounded questions in the background while Hermes retains reasoning and execution responsibilities.
- Purpose: Records decision provenance and supports configuration that avoids blocking ordinary execution.
- Review scope: A community integration without TypeSafe or Nous endorsement; improved long-task success rates are not established here. Not run here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/keeltrace/hermes-jev/
- Source evidence: https://github.com/keeltrace/hermes-jev/blob/4feea5ef45aeb301622f18175ed4cf2e068b99bd/README.md
- Source evidence: https://github.com/keeltrace/hermes-jev/blob/4feea5ef45aeb301622f18175ed4cf2e068b99bd/hermes_jev/client.py

## jev-browser

A browser library, CLI and MCP server where the caller supplies goals and text while Jev selects actions.

- Repository: https://github.com/Ying-Kai-Liao/jev-browser
- Category: Browser & OS Action
- Jev decision: Chooses elements, actions and values, and assesses completion, errors and irreversible steps.
- Purpose: Separates browser-action loops from caller planning and returns status and traces.
- Review scope: The 40/42 result and about 300 ms per call are author-reported site-specific tests. Token comparisons are estimates, not universal success-rate or cost guarantees. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ying-kai-liao/jev-browser/
- Source evidence: https://github.com/Ying-Kai-Liao/jev-browser/blob/578cff6e701a131733d03256078bb559a45ad188/src/jev.mjs#L8
- Source evidence: https://github.com/Ying-Kai-Liao/jev-browser/blob/578cff6e701a131733d03256078bb559a45ad188/README.md

## jev-ego

A browser Agent for ego lite that numbers actionable elements for Jev to choose the next step.

- Repository: https://github.com/romaluev/jev-ego
- Category: Browser & OS Action
- Jev decision: Jev selects an operation and target in one request; a separate helper handles free-form text when needed.
- Purpose: Offers observation, suggestions and execution, while uploads and dialogs still require other browser tools.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/romaluev/jev-ego/
- Source evidence: https://github.com/romaluev/jev-ego/blob/12eaafe795db56da821d9268ee7b9ae9ea24b23b/README.md
- Source evidence: https://github.com/romaluev/jev-ego/blob/12eaafe795db56da821d9268ee7b9ae9ea24b23b/src/model.ts
- Source evidence: https://github.com/romaluev/jev-ego/blob/12eaafe795db56da821d9268ee7b9ae9ea24b23b/src/agent.ts
- Source evidence: https://github.com/romaluev/jev-ego/blob/12eaafe795db56da821d9268ee7b9ae9ea24b23b/LICENSE

## pg\_typesafe

A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.

- Repository: https://github.com/giuliosmall/pg_typesafe
- Category: Data & Search
- Jev decision: Converts SQL input into System One requests and returns answers through database functions.
- Purpose: Adds typed semantic judgments to existing database queries.
- Review scope: Marked pre-alpha by the author. Requires extension installation and permissions; data is sent to an external API. This site has not tested it in a database.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/giuliosmall/pg_typesafe/
- Source evidence: https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/typesafe.c
- Source evidence: https://github.com/giuliosmall/pg_typesafe/blob/4b5bfc1df11b18c3f07bb10804eeb47e4508ec6a/README.md

## ruby\_llm-typesafe

A TypeSafe provider for RubyLLM 2 that exposes Jev’s three judgment types through structured output.

- Repository: https://github.com/kieranklaassen/ruby_llm-typesafe
- Category: SDK & Integrations
- Jev decision: Builds Noul, Choice and Score questions with Schema and returns answers to the RubyLLM application.
- Purpose: Reuses the structured-output interface in existing RubyLLM programs.
- Review scope: Limited to the provider’s supported structured-output path, not a general chat replacement.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kieranklaassen/ruby_llm-typesafe/
- Source evidence: https://github.com/kieranklaassen/ruby_llm-typesafe/blob/33e680115a43d584b1c0dcff385816f459a4bc71/README.md
- Source evidence: https://github.com/kieranklaassen/ruby_llm-typesafe/blob/33e680115a43d584b1c0dcff385816f459a4bc71/lib/ruby_llm/providers/typesafe.rb

## jev-seo

An experimental Rust SEO/GEO CLI and MCP tool combining page checks, DuckDuckGo queries and optional Jev scoring.

- Repository: https://github.com/AkashPriyadarshii/jev-seo
- Category: Domain & Vertical Tools
- Jev decision: Classifies search intent, direct answers and content gaps, with a custom citation-likelihood rubric.
- Purpose: Collects local checks, search results and model judgments into reports.
- Review scope: Jev requires an API key, so this is not unconditionally free. The GEO score is a model rubric, not measured search-engine indexing, citation or ranking. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/akashpriyadarshii/jev-seo/
- Source evidence: https://github.com/AkashPriyadarshii/jev-seo/blob/bbd59fe994d557e12f31d3548a012e0f02db64d9/src/engine.rs#L28
- Source evidence: https://github.com/AkashPriyadarshii/jev-seo/blob/bbd59fe994d557e12f31d3548a012e0f02db64d9/README.md

## leanest

Adds Jev-based selection before an existing test runner using diffs and test source.

- Repository: https://github.com/baronunread/leanest
- Category: Codebase & Graph Pathfinding
- Jev decision: Jev judges relevance; local policy runs tests on uncertainty, API failure or changes to the test file itself.
- Purpose: Supports shadow-mode comparison, but selected subsets cannot guarantee complete regression coverage.
- Review scope: Source shows conservative run behavior on uncertainty; missed-test rates and complete subset coverage were not measured.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/baronunread/leanest/
- Source evidence: https://github.com/baronunread/leanest/blob/dfb8c6b83e5b362d8258ee64835e15b5766e08d2/README.md
- Source evidence: https://github.com/baronunread/leanest/blob/dfb8c6b83e5b362d8258ee64835e15b5766e08d2/src/jev-client.ts
- Source evidence: https://github.com/baronunread/leanest/blob/dfb8c6b83e5b362d8258ee64835e15b5766e08d2/src/sieve.ts

## typesafe-ai-benchmark

Compares Jev with other structured-output models on shared application tasks, recording errors, latency, Tokens, and estimated cost.

- Repository: https://github.com/iammrduncan/typesafe-ai-benchmark
- Category: Evaluation & Observability
- Jev decision: Maps the same tasks to Jev Choice/Noul questions and normalizes answers to a shared result format.
- Purpose: Preserves comparison methods and results for inspecting model differences.
- Review scope: The current README describes limited synthetic workloads and separately captured results. The demo video is not measurement data, and results are not a ranking for all tasks. This site has not reproduced them.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/iammrduncan/typesafe-ai-benchmark/
- Source evidence: https://github.com/iammrduncan/typesafe-ai-benchmark/blob/cf348cd291bb538ad9fa902334649ef5dd937e92/packages/demos/lib/jev.ts
- Source evidence: https://github.com/iammrduncan/typesafe-ai-benchmark/blob/cf348cd291bb538ad9fa902334649ef5dd937e92/README.md

## jev-dsl

An early Haskell DSL that describes labeled Jev questions, renders requests and decodes matching answers.

- Repository: https://github.com/inanna-malick/jev-dsl
- Category: SDK & Decision Frameworks
- Jev decision: Uses inferred types and labeled handlers to connect Choice answers to predefined program branches.
- Purpose: Keeps questions, result types and branch handling in one inspectable definition.
- Review scope: The README marks it early alpha with a changing interface. Type guarantees do not establish factual correctness, and the library itself has no network transport.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/inanna-malick/jev-dsl/
- Source evidence: https://github.com/inanna-malick/jev-dsl/blob/f16f1363b4d389d6e34f9d695fbd254ca0735f2e/README.md
- Source evidence: https://github.com/inanna-malick/jev-dsl/blob/f16f1363b4d389d6e34f9d695fbd254ca0735f2e/scripts/example.sh

## typesafe-go

An unofficial Go client without third-party dependencies for System One calls and model discovery.

- Repository: https://github.com/zhirschtritt/typesafe-go
- Category: SDK & Decision Frameworks
- Jev decision: Sends application state and questions to Jev and parses Choice, Score or Noul answers.
- Purpose: Packages requests and response parsing for typed decisions in applications.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/zhirschtritt/typesafe-go/
- Source evidence: https://github.com/zhirschtritt/typesafe-go/blob/a4062e525d1ad23aa739d3454247bcec52486a57/client.go#L18
- Source evidence: https://github.com/zhirschtritt/typesafe-go/blob/a4062e525d1ad23aa739d3454247bcec52486a57/README.md

## Canny

Keeps an execution ledger for Claude Code and Codex CLI to check for passing validation after edits.

- Repository: https://github.com/qkal/Canny
- Category: Evaluation & Observability
- Jev decision: Jev can identify completion claims and semantic-rule issues; stop gates depend on ledger facts and local rules.
- Purpose: Separates execution evidence from model opinion rather than letting Jev alone certify completion.
- Review scope: Jev supplies advisory judgments while recorded facts and local rules govern blocking; complete coverage of false completion claims is unverified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/qkal/canny/
- Source evidence: https://github.com/qkal/Canny/blob/74bc3487370ae6d61cef69c5642cce504a8579cb/README.md
- Source evidence: https://github.com/qkal/Canny/blob/74bc3487370ae6d61cef69c5642cce504a8579cb/src/jev.ts
- Source evidence: https://github.com/qkal/Canny/blob/74bc3487370ae6d61cef69c5642cce504a8579cb/src/hook.ts

## commit-miner

Classifies Git commit messages and diffs with Jev for bug fixes, security fixes, CWEs, and change types.

- Repository: https://github.com/devanshbatham/commit-miner
- Category: Codebase & Graph Pathfinding
- Jev decision: Asks fixed-category questions about commits and saves results for filtering and HTML/CSV reports.
- Purpose: Organizes large commit histories into records for further review.
- Review scope: Classifications and CWE labels are model judgments, not confirmed vulnerabilities. This site has not verified accuracy; commit content is sent to an external API.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/devanshbatham/commit-miner/
- Source evidence: https://github.com/devanshbatham/commit-miner/blob/977617ebce07c56b965253a68577b1d92b93fdf1/src/jev.rs
- Source evidence: https://github.com/devanshbatham/commit-miner/blob/977617ebce07c56b965253a68577b1d92b93fdf1/README.md

## pi-jev-compact

A Pi context-pruning extension targeting tool history by default, with optional assistant-prose pruning.

- Repository: https://github.com/ilkerulusoy/pi-jev-compact
- Category: Context GC & Filter
- Jev decision: Jev judges which candidates remain useful; surviving text is returned verbatim.
- Purpose: Provides configurable pruning scope and decision records.
- Review scope: The author has not evaluated keep/drop quality against reference judgments. Synthetic context reductions do not guarantee useful-context preservation. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/ilkerulusoy/pi-jev-compact/
- Source evidence: https://github.com/ilkerulusoy/pi-jev-compact/blob/7d54b2e9a437fcf445c7f50aa49d673dbd863176/src/core/jev.ts#L3
- Source evidence: https://github.com/ilkerulusoy/pi-jev-compact/blob/7d54b2e9a437fcf445c7f50aa49d673dbd863176/README.md

## pi-jev-context

A reversible Pi context filter using Jev to judge whether older messages remain useful.

- Repository: https://github.com/kevinpita/pi-jev-context
- Category: Context GC & Filter
- Jev decision: Scores historical fragments and hides low-scoring content from future requests while preserving session history.
- Purpose: Disabling restores full context; enabling sends selected history to TypeSafe.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kevinpita/pi-jev-context/
- Source evidence: https://github.com/kevinpita/pi-jev-context/blob/640ffa74c376fe8e487e4fec3e75de741f5b53e1/README.md
- Source evidence: https://github.com/kevinpita/pi-jev-context/blob/640ffa74c376fe8e487e4fec3e75de741f5b53e1/src/jev.ts
- Source evidence: https://github.com/kevinpita/pi-jev-context/blob/640ffa74c376fe8e487e4fec3e75de741f5b53e1/src/index.ts

## duckdb-jev

A DuckDB extension that calls Jev from SQL and returns answers as ENUM, numeric, or STRUCT types.

- Repository: https://github.com/colliber/duckdb-jev
- Category: Data & Search
- Jev decision: Asks Choice, Score, and Noul questions about row text and maps answers to SQL types defined by the questions.
- Purpose: Uses structured judgments while querying tables or Parquet data.
- Review scope: Requires an external Jev API configuration. SQL type constraints do not establish answer correctness or eliminate privacy risks.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/colliber/duckdb-jev/
- Source evidence: https://github.com/colliber/duckdb-jev/blob/fad67eb4a1def91fcf1efbc96bdf5e6e11208644/src/jev_client.cpp
- Source evidence: https://github.com/colliber/duckdb-jev/blob/fad67eb4a1def91fcf1efbc96bdf5e6e11208644/README.md

## jev-reviewer

A systematic-review tool that selects verbatim evidence from papers and supplements for human checking and export.

- Repository: https://github.com/choxos/jev-reviewer
- Category: Domain & Vertical Tools
- Jev decision: Jev selects candidate line IDs; code copies the original text with file and location references.
- Purpose: Connects quotes, source locations and human verification status.
- Review scope: Files are stored in the browser, but text used for judgment is sent to Jev. Verbatim quotes do not guarantee relevance or medical correctness.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/choxos/jev-reviewer/
- Source evidence: https://github.com/choxos/jev-reviewer/blob/b00d05fc888973b0147383dd7315318280d01635/README.md
- Source evidence: https://github.com/choxos/jev-reviewer/blob/b00d05fc888973b0147383dd7315318280d01635/server.js

## jevsql

Adds Jev semantic judgments to SQLite for filtering, ranking, matching and tracking decision evidence.

- Repository: https://github.com/EugeneBoondock/jevsql
- Category: Data & Search
- Jev decision: Sends row data and typed questions to Jev and maps answers into queryable SQL results.
- Purpose: Provides batching, caching, budgets and decision history.
- Review scope: README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/eugeneboondock/jevsql/
- Source evidence: https://github.com/EugeneBoondock/jevsql/blob/e0b42f3b4312189f0b9c3996818675c714f126e7/src/client.mjs#L5
- Source evidence: https://github.com/EugeneBoondock/jevsql/blob/e0b42f3b4312189f0b9c3996818675c714f126e7/README.md

## n8n-nodes-typesafe-jev

An n8n community node for submitting typed questions to TypeSafe Jev.

- Repository: https://github.com/n3ndor/n8n-nodes-typesafe-jev
- Category: MCP & Integrations
- Jev decision: Builds state and questions from input items, calls Jev and appends or separately outputs answers.
- Purpose: Supports form or JSON question configuration and use as an Agent tool.
- Review scope: Reviewed the fixed-version README and call path.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/n3ndor/n8n-nodes-typesafe-jev/
- Source evidence: https://github.com/n3ndor/n8n-nodes-typesafe-jev/blob/22ae978a36149982fe14b8556eb0bab0250c2450/README.md
- Source evidence: https://github.com/n3ndor/n8n-nodes-typesafe-jev/blob/22ae978a36149982fe14b8556eb0bab0250c2450/nodes/TypeSafeJev/transport.ts
- Source evidence: https://github.com/n3ndor/n8n-nodes-typesafe-jev/blob/22ae978a36149982fe14b8556eb0bab0250c2450/nodes/TypeSafeJev/TypeSafeJev.node.ts

## tax-doc-classifier

A tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.

- Repository: https://github.com/kyotofin/tax-doc-classifier
- Category: Domain & Vertical Tools
- Jev decision: Extracts PDF page text and sends it to Jev for form type, page type, and confidence.
- Purpose: Connects a fixed form catalog to per-page classifications for downstream document workflows.
- Review scope: The 100% figure and per-page cost are author-reported results on their own corpus, not an accuracy guarantee for all tax documents. This site has not retested them or verified tax judgment capabilities.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/kyotofin/tax-doc-classifier/
- Source evidence: https://github.com/kyotofin/tax-doc-classifier/blob/6afcf701395466d7c936ec8178daf017b9d96b0c/src/backend.ts
- Source evidence: https://github.com/kyotofin/tax-doc-classifier/blob/6afcf701395466d7c936ec8178daf017b9d96b0c/README.md

## jev-experiments

A collection of Jev developer-tool experiments, including Commit Sentry for semantic checks on staged diff hunks.

- Repository: https://github.com/dabit3/jev-experiments
- Category: Security & Guardrails
- Jev decision: Judges risks such as exposed credentials or destructive changes; local rules warn or block a commit.
- Purpose: Presents risk labels with the corresponding diff before commit.
- Review scope: The repository says the demos were built by Devin; performance tables describe author-specific runs. Not a replacement for deterministic secret scanning or full code review, and not retested here.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/dabit3/jev-experiments/
- Source evidence: https://github.com/dabit3/jev-experiments/blob/ed07e87c24822b9258dfd95c63e3d5f436d95b1a/README.md
- Source evidence: https://github.com/dabit3/jev-experiments/blob/ed07e87c24822b9258dfd95c63e3d5f436d95b1a/commit-sentry/src/jev.ts
- Source evidence: https://github.com/dabit3/jev-experiments/blob/ed07e87c24822b9258dfd95c63e3d5f436d95b1a/commit-sentry/README.md

## jevscape

A RuneBench extension using Jev and a bounded rs-sdk action catalog for RuneScape tasks.

- Repository: https://github.com/Skyvern-AI/jevscape
- Category: High-Frequency & Simulation
- Jev decision: Chooses goal actions, tick interventions and the next polling interval from game state.
- Purpose: Provides action-distribution views, run logs and burst or tick control modes.
- Review scope: This repository has its own Jev adapter rather than being an unchanged upstream copy. Demos and cost figures do not establish comprehensive benchmark superiority. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/skyvern-ai/jevscape/
- Source evidence: https://github.com/Skyvern-AI/jevscape/blob/8fe4d37349fc6a8d03ac1c918302eef254bb56c3/agents/jev/jev-client.ts#L3
- Source evidence: https://github.com/Skyvern-AI/jevscape/blob/8fe4d37349fc6a8d03ac1c918302eef254bb56c3/README.md
- Source evidence: https://github.com/Skyvern-AI/jevscape/blob/8fe4d37349fc6a8d03ac1c918302eef254bb56c3/agents/jev/README.md

## killmyidea

A startup-idea evaluation demo assigning KILL, FIX or SHIP labels from Jev scores.

- Repository: https://github.com/monteduro/killmyidea
- Category: Decision Tools
- Jev decision: Jev answers scoring, category and clarity questions; local weights and gates calculate the final label.
- Purpose: Shows a structured assessment process, not market validation, a success forecast or investment advice.
- Review scope: Labels derive from model scores and local weights, not independent market or business validation.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/monteduro/killmyidea/
- Source evidence: https://github.com/monteduro/killmyidea/blob/bc853421f2eb6f17da435621896dd6cd881a051c/README.md
- Source evidence: https://github.com/monteduro/killmyidea/blob/bc853421f2eb6f17da435621896dd6cd881a051c/src/lib/typesafe.ts
- Source evidence: https://github.com/monteduro/killmyidea/blob/bc853421f2eb6f17da435621896dd6cd881a051c/src/lib/scoring.ts
- Source evidence: https://github.com/monteduro/killmyidea/blob/bc853421f2eb6f17da435621896dd6cd881a051c/api/evaluate.ts

## vibecheck

Shows a Jev scorecard before posting on X, assessing draft clarity, tone, and possible offensiveness.

- Repository: https://github.com/RafalWilinski/vibecheck
- Category: Creative Tools
- Jev decision: Sends the draft and reply or quote context to Jev for multiple scores and a posting suggestion.
- Purpose: Collects several perspectives on a draft before it is sent.
- Review scope: Virality and regret risk are subjective model estimates, not guarantees of audience response or posting safety. Image descriptions require an optional external vision model; this site has not verified effectiveness.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/rafalwilinski/vibecheck/
- Source evidence: https://github.com/RafalWilinski/vibecheck/blob/badf9dad5deecababd8afe43a574a5ea6d376711/background.js
- Source evidence: https://github.com/RafalWilinski/vibecheck/blob/badf9dad5deecababd8afe43a574a5ea6d376711/README.md

## jev-behavior-study

An independent Jev 1.13.0 behavior study recording successes and failures across question framing, input conditions and games.

- Repository: https://github.com/RINNECODER/jev-behavior-study
- Category: Evaluation & Observability
- Jev decision: Sends controlled variants of fixed tasks and records choices, probabilities and raw request-response evidence.
- Purpose: Lets readers inspect individual cases rather than infer broad capability from simple-task success.
- Review scope: Author-run synthetic, task-specific experiments; repeated calls are not independent problems, and this is not an official benchmark or a peer-reviewed conclusion. Not rerun here.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/rinnecoder/jev-behavior-study/
- Source evidence: https://github.com/RINNECODER/jev-behavior-study/blob/e4a1d7ec691a91f33d3b5879a780e6f27328f173/README.md
- Source evidence: https://github.com/RINNECODER/jev-behavior-study/blob/e4a1d7ec691a91f33d3b5879a780e6f27328f173/behavior_study.py

## jev-eval

Compares Jev and OpenRouter models on labeled tasks for accuracy, calibration, latency and cost.

- Repository: https://github.com/4esv/jev-eval
- Category: Evaluation & Observability
- Jev decision: Collects judgments on matched tasks and computes confidence intervals and repeat-input stability.
- Purpose: Publishes data processing, runner and statistics code with model-specific results.
- Review scope: The published comparison uses 300 items per task with specified models and dates. Advantages vary by task and do not demonstrate universal superiority or absence of bias. README and integration source reviewed at a fixed commit; not independently run or benchmarked by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/4esv/jev-eval/
- Source evidence: https://github.com/4esv/jev-eval/blob/dcfd6db29dfee2a107ff6e018176c6577002f887/evaljev/runners.py#L15
- Source evidence: https://github.com/4esv/jev-eval/blob/dcfd6db29dfee2a107ff6e018176c6577002f887/README.md

## PiJ

A Pi-based terminal coding Agent whose main model handles reasoning, edits and tools while Jev provides advice.

- Repository: https://github.com/tonyzdev/PiJ
- Category: Codebase & Graph Pathfinding
- Jev decision: Jev suggests skills, reranks actual source candidates and triages failures without automatic retries or permission approval.
- Purpose: Preserves paths, line numbers, source and errors; the author’s bounded experiments do not establish universal gains.
- Review scope: The author provides bounded task experiments; this site reviewed implementation and evidence limits without independently retesting resolve rate, cost or latency.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tonyzdev/pij/
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/README.md
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/README.zh-CN.md
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/src/jev.ts
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/src/gateway.ts
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/src/decisions.ts
- Source evidence: https://github.com/tonyzdev/PiJ/blob/9588d6078af3f3be2b52906e0968ccf8e1542d74/src/extension.ts

## jev-commit

Pre-commit hook for the commit-msg stage: one Jev call judges the message against the staged diff, then warns and gets out of the way, except on a credential on an added line, which it blocks.

- Repository: https://github.com/valentynkit/jev-commit
- Category: Decision Tools
- Jev decision: Jev returns a structured decision for the local program; consult the source for the exact decision policy.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/valentynkit/jev-commit/
- Source evidence: https://github.com/valentynkit/jev-commit/blob/311e163b8abb9c333132155bc2e0bbfac4f36283/README.md
- Source evidence: https://github.com/valentynkit/jev-commit/blob/311e163b8abb9c333132155bc2e0bbfac4f36283/jev_commit/jev.py

## jev-belay

Claude Code Stop hook that blocks an unverified done. It reads the turn transcript locally and only spends a Jev call when files changed and no check has passed since; every error path lets the turn end.

- Repository: https://github.com/valentynkit/jev-belay
- Category: Decision Tools
- Jev decision: Jev returns a structured decision for the local program; consult the source for the exact decision policy.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/valentynkit/jev-belay/
- Source evidence: https://github.com/valentynkit/jev-belay/blob/98f39e04492068e39b48962183acf43b4337da32/README.md
- Source evidence: https://github.com/valentynkit/jev-belay/blob/98f39e04492068e39b48962183acf43b4337da32/tools/fake-jev.mjs
- Source evidence: https://github.com/valentynkit/jev-belay/blob/98f39e04492068e39b48962183acf43b4337da32/belay.mjs

## jev.nvim

Neovim plugin: type a plain-language question, every function in the buffer gets judged, answers land in quickfix ranked by probability.

- Repository: https://github.com/valentynkit/jev.nvim
- Category: Decision Tools
- Jev decision: Treesitter splits the buffer into functions; one request scores each function against the question; implementation in lua/. The README compares against a regex grep on a twelve-file fixture corpus, no accuracy claim beyond that.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/valentynkit/jev.nvim/
- Source evidence: https://github.com/valentynkit/jev.nvim/blob/a1577b0ec874208377e5f38496577d2b8797ab11/README.md
- Source evidence: https://github.com/valentynkit/jev.nvim/blob/a1577b0ec874208377e5f38496577d2b8797ab11/plugin/jev.lua
- Source evidence: https://github.com/valentynkit/jev.nvim/blob/a1577b0ec874208377e5f38496577d2b8797ab11/lua/jev/client.lua

## jev-skip

Browser extension that skips YouTube sponsor reads on videos nobody has labeled, from the caption track alone, and paints a probability per segment on the seek bar.

- Repository: https://github.com/valentynkit/jev-skip
- Category: Decision Tools
- Jev decision: Jev returns a structured decision for the local program; consult the source for the exact decision policy.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/valentynkit/jev-skip/
- Source evidence: https://github.com/valentynkit/jev-skip/blob/6837e3e0f1a48cbfc48c85415d99bcfe3eaf0628/README.md
- Source evidence: https://github.com/valentynkit/jev-skip/blob/6837e3e0f1a48cbfc48c85415d99bcfe3eaf0628/lib/jev.ts

## jev-plays-pokemon-red

Pokemon Red on PyBoy where code owns the route and the arithmetic and Jev picks only where the game branches.

- Repository: https://github.com/valentynkit/jev-plays-pokemon-red
- Category: Decision Tools
- Jev decision: Choice questions at battle actions, blocked-tile sidesteps and dialogue menus; a Noul faints\_this\_turn on every battle turn is labelled from RAM on the next turn and scored by Brier in uv run measure. Speed and cost numbers are deliberately blank in the README until a full playthrough is measured; implementation in src/.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/valentynkit/jev-plays-pokemon-red/
- Source evidence: https://github.com/valentynkit/jev-plays-pokemon-red/blob/cbe5387aeb6c7b3ef6b1f67d4a95e284aee3b0af/README.md
- Source evidence: https://github.com/valentynkit/jev-plays-pokemon-red/blob/cbe5387aeb6c7b3ef6b1f67d4a95e284aee3b0af/src/jpp/policy.py

## elons-job

Local-first Chrome extension that uses Jev to filter sexual and solicitation content in X replies with reversible hidden placeholders.

- Repository: https://github.com/bugkiwi/elons-job
- Category: Context GC & Filter
- Jev decision: Scores X reply text with Jev Noul questions for sexual content, solicitation, and spam, then combines probabilities with local thresholds and structural signals.
- Purpose: Combines local rules, caching, concurrency and cost controls, and fail-open handling; it requires no X API and keeps hidden comments recoverable.
- Review scope: The README and source show TypeSafe System One integration and deterministic mock tests; not independently run or performance-tested by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bugkiwi/elons-job/
- Source evidence: https://github.com/bugkiwi/elons-job/blob/be01f869871fcda5841fb77df3df6e46abbda493/README.md
- Source evidence: https://github.com/bugkiwi/elons-job/blob/be01f869871fcda5841fb77df3df6e46abbda493/src/background.js#L46-L101
- Source evidence: https://github.com/bugkiwi/elons-job/blob/be01f869871fcda5841fb77df3df6e46abbda493/src/shared/core.js#L220-L327

## turing-jail

Interactive three-level AI interrogation game powered by TypeSafe Jev; write responses and pass plea, logic, and paradox verdicts to earn release.

- Repository: https://github.com/bugkiwi/turing-jail
- Category: Decision Tools
- Jev decision: For each level, Jev evaluates release probability plus plea, logic, and paradox signals, then selects a persuasion tactic and scores persuasiveness.
- Purpose: Turns structured Jev judgments into playable feedback, pass thresholds, and leaderboard results that show how arguments affect release probability.
- Review scope: Source-reviewed integration record; runtime behavior and performance were not independently retested by this site.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bugkiwi/turing-jail/
- Source evidence: https://github.com/bugkiwi/turing-jail/blob/629ff1b5617800d851811ce4379845f5ac59f729/README.md
- Source evidence: https://github.com/bugkiwi/turing-jail/blob/629ff1b5617800d851811ce4379845f5ac59f729/server.ts#L91-L123

## typesafe-sdk-python

Official TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.

- Repository: https://github.com/typesafe-ai/typesafe-sdk-python
- Category: SDK & Decision Frameworks
- Jev decision: system\_one sends context and choice, score or yes/no questions to the API, then parses answers by question name.
- Purpose: Reuses request handling, typed answers and connection management in Python, with support for with and async with.
- Review scope: Reviewed the fixed-version README, client source and MIT license.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/typesafe-ai/typesafe-sdk-python/
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/sync/client.py#L206-L221
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/client/aio/client.py#L216-L243
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/_core/question_types.py#L77-L113
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/src/typesafe_sdk/constants.py#L18-L19
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/README.md#L13-L29
- Source evidence: https://github.com/typesafe-ai/typesafe-sdk-python/blob/2ce5c65f13646cab6e6f782328194c9d85f3300a/LICENSE#L1-L21

## JevFilterForX

A browser extension that scores and filters X posts in real time with Jev, folding low-signal content while keeping it expandable. Without an API key, it defaults to local mock scoring.

- Repository: https://github.com/grayrepo-byte/jev_filter_for_x
- Category: Browser & OS Action
- Jev decision: Jev classifies posts with Choice, rates signal, actionability and originality with Score, and assigns Noul labels; local thresholds and noise rules decide whether to fold each post.
- Purpose: Adds scores, labels and adjustable filtering thresholds to the X feed, with reversible folding of posts and their attached media.
- Review scope: Fixed-commit source review only; no runtime, accuracy, latency or cost validation. Mock and live results share a 30-day cache that is not invalidated when a key is added. Interest/value preferences do not affect filtering; missing API scores become zero. Online mode sends post text, author and ID to TypeSafe; the key is stored locally. Public source has no identified license.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/grayrepo-byte/jev_filter_for_x/
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/core/jev.ts#L35-L255
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/core/classifier.ts#L28-L66
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/core/policy.ts#L11-L47
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/entrypoints/background/index.ts#L21-L43
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/storage/cache.ts#L7-L64
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/storage/settings.ts#L4-L44
- Source evidence: https://github.com/grayrepo-byte/jev_filter_for_x/blob/62cb4a602026b5449a9caa94c193c534e0a19c01/src/ui/options/SignalFeedOptions.tsx#L117-L165

## JevScout

A demo job-search Skill for coding Agents that browses company careers pages in Chrome, uses Jev to screen AI and software-engineering roles, and saves the results.

- Repository: https://github.com/hqman/JevScout
- Category: Domain & Vertical Tools
- Jev decision: Jev uses Choice to classify pages and Noul to assess careers links, role relevance, filter controls and candidate fit; local thresholds select navigation, job details and saved results.
- Purpose: Connects careers navigation, role screening and detail matching in one CLI workflow, with local JSON and Markdown reports.
- Review scope: Demo MVP reviewed at a fixed commit; no browser or live API run. Scanning has count and text limits. Mock scores and latency are simulated, while mock mode can still operate real Chrome. The workflow is not guaranteed read-only. Site coverage, matching accuracy and performance were not validated; no open-source license was confirmed.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hqman/jevscout/
- Source evidence: https://github.com/hqman/JevScout/blob/b51390be0c3ca28b5407ab6d8c8044912a03bb31/README.md#L1-L30
- Source evidence: https://github.com/hqman/JevScout/blob/b51390be0c3ca28b5407ab6d8c8044912a03bb31/jev_job_hunter/jev.py#L220-L305
- Source evidence: https://github.com/hqman/JevScout/blob/b51390be0c3ca28b5407ab6d8c8044912a03bb31/jev_job_hunter/questions.py#L3-L88
- Source evidence: https://github.com/hqman/JevScout/blob/b51390be0c3ca28b5407ab6d8c8044912a03bb31/jev_job_hunter/runner.py#L70-L112
- Source evidence: https://github.com/hqman/JevScout/blob/b51390be0c3ca28b5407ab6d8c8044912a03bb31/jev_job_hunter/policy.py#L88-L177

## typesafeai-dotnet-sdk

Community .NET SDK for TypeSafe AI and Jev, providing asynchronous typed evaluation for Choice, Score, and Noul primitives.

- Repository: https://github.com/saibimajdi/typesafeai-dotnet-sdk
- Category: SDK & Decision Frameworks
- Jev decision: Wraps System One API endpoints in TypeSafeClient to issue parallel question evaluations and parse responses into immutable C# records.
- Purpose: Brings native Jev decision primitives to the .NET ecosystem with dependency injection integration and configurable retry policies.
- Review scope: Source code verified against pinned commit. Complete client implementation and models; no live production service benchmark.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/saibimajdi/typesafeai-dotnet-sdk/
- Source evidence: https://github.com/saibimajdi/typesafeai-dotnet-sdk/blob/6be669e0d0b116b76e85136c4f6eaa44fadcecab/src/TypeSafe.Sdk/TypeSafeClient.cs#L1-L283
- Source evidence: https://github.com/saibimajdi/typesafeai-dotnet-sdk/blob/6be669e0d0b116b76e85136c4f6eaa44fadcecab/README.md

## zio-typesafe-ai

A Scala 3 and ZIO library for TypeSafe AI and Jev, integrating discrete decision endpoints into a purely functional effect system.

- Repository: https://github.com/jamesward/zio-typesafe-ai
- Category: SDK & Decision Frameworks
- Jev decision: Models Jev System One queries as ZIO effects, submitting state and typed questions concurrently with robust schema decoding.
- Purpose: Enables functional Scala applications to leverage Jev fast decision-making with fiber-based concurrency and structured error management.
- Review scope: Source code verified against pinned commit. Complete effect wrapper and test specifications; no live load benchmark.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jamesward/zio-typesafe-ai/
- Source evidence: https://github.com/jamesward/zio-typesafe-ai/blob/38082e8712b49ce239ae628557619347909165dc/src/main/scala/com/jamesward/zio_typesafe_ai/TypeSafeAI.scala#L1-L571
- Source evidence: https://github.com/jamesward/zio-typesafe-ai/blob/38082e8712b49ce239ae628557619347909165dc/README.md

## typesafe-ai-rails

Ruby on Rails integration gem for TypeSafe AI and Jev, providing model-level classification and decision policy patterns.

- Repository: https://github.com/GenieRobot/typesafe-ai-rails
- Category: SDK & Decision Frameworks
- Jev decision: Dispatches state and criteria from ActiveRecord models or services to Jev System One endpoints, logging structured outcomes.
- Purpose: Simplifies adding Jev discrete judgments to Rails web apps with standard Railtie configuration and policy wrappers.
- Review scope: Source code verified against pinned commit. Includes Railtie setup and policy classes; production database performance unverified.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/genierobot/typesafe-ai-rails/
- Source evidence: https://github.com/GenieRobot/typesafe-ai-rails/blob/fbac64470904fef7c4e68da172813daf0840f31f/lib/typesafe/rails/client.rb#L1-L148
- Source evidence: https://github.com/GenieRobot/typesafe-ai-rails/blob/fbac64470904fef7c4e68da172813daf0840f31f/README.md

## jev-superpowers

Software development framework for coding agents enhanced with Jev for dependency vetting, completion gates, and debugging decisions.

- Repository: https://github.com/AkashPriyadarshii/jev-superpowers
- Category: CLI & Pipelines
- Jev decision: Invokes Jev at workflow checkpoints to evaluate change validity, test sufficiency, and package safety before advancing agent state.
- Purpose: Constrains coding agent trajectories using fast discrete judgments, preventing hallucinated dependencies and premature task completion.
- Review scope: Source code verified against pinned commit. Framework definitions and examples inspected; accuracy depends on upstream model calibration.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/akashpriyadarshii/jev-superpowers/
- Source evidence: https://github.com/AkashPriyadarshii/jev-superpowers/blob/6ddc702c231fd33fdf04b1ab1c0cce96fd8d2a19/skills/systematic-debugging/condition-based-waiting-example.ts#L1-L159
- Source evidence: https://github.com/AkashPriyadarshii/jev-superpowers/blob/6ddc702c231fd33fdf04b1ab1c0cce96fd8d2a19/README.md

## JevSeek

Local coding workspace and agent decoupling tool routing via Jev from detailed argument generation via DeepSeek.

- Repository: https://github.com/morcoan/JevSeek
- Category: Domain & Vertical Tools
- Jev decision: Employs Jev to classify and select the next tool action based on execution state, delegating parameter generation to DeepSeek.
- Purpose: Combines low-latency discrete routing with capable generative modeling, reducing overall prompt overhead and turn latency.
- Review scope: Source code verified against pinned commit. Covers desktop bridge and routing logic; end-to-end latency depends on provider configuration.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/morcoan/jevseek/
- Source evidence: https://github.com/morcoan/JevSeek/blob/030d59114a03720783e839481a7814e7aecaad85/desktop.py#L1-L141
- Source evidence: https://github.com/morcoan/JevSeek/blob/030d59114a03720783e839481a7814e7aecaad85/README.md

## reranker

Python library utilizing Jev System One as a calibrated reranker, scoring up to 30 candidate documents per single API call.

- Repository: https://github.com/hev/reranker
- Category: Data & Search
- Jev decision: Packs a search query and documents into state, issuing parallel Noul questions to obtain calibrated relevance probabilities.
- Purpose: Evaluates entire batches concurrently without generative overhead, providing scores suitable for absolute thresholding and ranking.
- Review scope: Source code verified against pinned commit. Includes pipeline examples and concurrency handling; retrieval gains vary across datasets.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/hev/reranker/
- Source evidence: https://github.com/hev/reranker/blob/1eb47266270b32b2a3667f9fb89646378ca9c9d6/hev_rerank/rerank.py#L1-L105
- Source evidence: https://github.com/hev/reranker/blob/1eb47266270b32b2a3667f9fb89646378ca9c9d6/examples/bm25_then_jev.py
- Source evidence: https://github.com/hev/reranker/blob/1eb47266270b32b2a3667f9fb89646378ca9c9d6/hev_rerank/__init__.py
- Source evidence: https://github.com/hev/reranker/blob/1eb47266270b32b2a3667f9fb89646378ca9c9d6/README.md

## typesafe-ai-playground

Community playground for TypeSafe AI and Jev featuring 110 real-world scenarios, dilemmas, and interactive experiments.

- Repository: https://github.com/TypeSafeAI/typesafe-playground
- Category: Domain & Vertical Tools
- Jev decision: Submits custom states and questions to Jev via Next.js API routes, displaying discrete probabilities, latency, and confidence scores.
- Purpose: Offers an intuitive web interface for exploring prompt criteria, testing edge cases, and evaluating discrete decision outputs.
- Review scope: Source code verified against pinned commit. Complete Next.js application codebase; live demo latency depends on deployment hosting.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/bunsdev/typesafe-ai-playground/
- Source evidence: https://github.com/BunsDev/typesafe-ai-playground/blob/f67c3571fca1c468b4585f17282a58a1f57b1a17/app/api/run/route.ts#L1-L65
- Source evidence: https://github.com/TypeSafeAI/typesafe-playground/blob/f67c3571fca1c468b4585f17282a58a1f57b1a17/README.md

## litjev

Open reproduction of Jev decision layer on open-weights models, serving the System One schema by inspecting option logits directly.

- Repository: https://github.com/zhengxuyu/litjev
- Category: High-Frequency & Simulation
- Jev decision: Implements the /v1/systemone endpoint (Choice, Score, Noul) by calculating candidate token log-probabilities without text generation.
- Purpose: Enables private and local hosting of Jev-compatible decision services on GPUs without relying on proprietary cloud APIs.
- Review scope: Source code verified against pinned commit. Complete local API server; calibrated probability distribution may differ from hosted Jev.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/zhengxuyu/litjev/
- Source evidence: https://github.com/zhengxuyu/litjev/blob/f21216c9fe5afe7fa52ff7064a402ee57fdbddd3/src/litjev/api.py#L1-L83
- Source evidence: https://github.com/zhengxuyu/litjev/blob/f21216c9fe5afe7fa52ff7064a402ee57fdbddd3/README.md

## jev-shell-history

Fish-style Zsh history suggestion tool ranked by Jev, ordering candidate commands from local history based on context.

- Repository: https://github.com/mrnugget/jev-shell-history
- Category: CLI & Pipelines
- Jev decision: Packages current command input and historical candidates into a Jev request, ranking the most plausible command for inline suggestion.
- Purpose: Combines the safety of local shell history with Jev semantic relevance, filtering out stale or risky command candidates.
- Review scope: Source code verified against pinned commit. Terminal hook and suggestion logic inspected; interactive typing requires fast network connectivity.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/mrnugget/jev-shell-history/
- Source evidence: https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/src/suggest.ts#L1-L196
- Source evidence: https://github.com/mrnugget/jev-shell-history/blob/4b2b75d26c0ccf5726263904514a22a8e11659ea/README.md

## is-malicious

CLI security scanner using Jev to inspect source files, build scripts, and CI configs for suspicious patterns before execution.

- Repository: https://github.com/luantak/is-malicious
- Category: Security & Guardrails
- Jev decision: Feeds file contents and security criteria into Jev to assess risks such as data exfiltration, obfuscated loaders, and credential leakage.
- Purpose: Provides rapid pre-execution safety screening across multiple file formats without needing a heavy static analysis toolchain.
- Review scope: Source code verified against pinned commit. Pattern rules and CLI outputs verified; serves as an advisory layer alongside deterministic linters.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/luantak/is-malicious/
- Source evidence: https://github.com/luantak/is-malicious/blob/b6052465eb47cf85f347596385954aa06532718a/src/jev.ts#L1-L181
- Source evidence: https://github.com/luantak/is-malicious/blob/b6052465eb47cf85f347596385954aa06532718a/README.md

## jev-router

High-throughput semantic router for Claude Code and CLI tools, directing requests to the most cost-effective model via Jev.

- Repository: https://github.com/gargpratyush/jev-router
- Category: Routing & Cost Optimization
- Jev decision: Classifies task complexity with Jev discrete choice queries, dispatching trivial edits to lightweight models and reserving large models for complex logic.
- Purpose: Reduces aggregate API costs for developer tools while preserving quality on challenging architectural questions.
- Review scope: Source code verified against pinned commit. Includes wrapper binaries and policy configs; cost savings vary with workload distribution.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/gargpratyush/jev-router/
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/src/policy.mjs#L1-L63
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/bin/jev-claude.mjs
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/bin/jev-codex.mjs
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/bin/jev-explain.mjs
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/bin/jev-statusline.mjs
- Source evidence: https://github.com/gargpratyush/jev-router/blob/38da6b84ea01241bfc41fbddc0928d0f40a703f0/README.md

## opencode-jev-orchestrator

OpenCode orchestrator that keeps a sticky affordable parent model and delegates difficult turns to subagents using Jev difficulty decisions.

- Repository: https://github.com/aaronshaf/opencode-jev-orchestrator
- Category: Routing & Cost Optimization
- Jev decision: Evaluates turn complexity before execution, triggering specialized subagents powered by premium models only when escalation criteria are met.
- Purpose: Maximizes context cache hits on low-cost models while preserving high-tier reasoning capabilities for challenging code changes.
- Review scope: Source code verified against pinned commit. Core routing and subagent dispatching verified; synthesis quality depends on task boundaries.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/aaronshaf/opencode-jev-orchestrator/
- Source evidence: https://github.com/aaronshaf/opencode-jev-orchestrator/blob/ffe76fed66b3d544f218cacff1947fc191688c3a/src/jev.ts#L1-L193
- Source evidence: https://github.com/aaronshaf/opencode-jev-orchestrator/blob/ffe76fed66b3d544f218cacff1947fc191688c3a/README.md

## fast-dev-compaction

Codex plugin for context compaction, using Jev within session lifecycle hooks to preserve essential history while pruning noise.

- Repository: https://github.com/leonaaardob/fast-dev-compaction
- Category: Context GC & Filter
- Jev decision: Assesses past conversation turns with Jev when context limits approach, selecting critical tool outputs and user requirements for retention.
- Purpose: Avoids blanket truncation or lossy re-summarization by selectively preserving exact code locations and decision traces.
- Review scope: Source code verified against pinned commit. Adapted for Codex lifecycle hooks; compaction ratios depend on conversation style.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/leonaaardob/fast-dev-compaction/
- Source evidence: https://github.com/leonaaardob/fast-dev-compaction/blob/7147a4bab4ff9caf64ae44a2db1ab1f907a20291/dist/compact.js#L1-L234
- Source evidence: https://github.com/leonaaardob/fast-dev-compaction/blob/7147a4bab4ff9caf64ae44a2db1ab1f907a20291/README.md

## yoshi

Context-pruning proxy for Claude Code and Codex, employing Jev to prune redundant history while keeping tool protocols intact.

- Repository: https://github.com/compozy/yoshi
- Category: Context GC & Filter
- Jev decision: Intercepts request payloads and uses Jev to score historical messages, discarding outdated tool noise before forwarding to upstream LLMs.
- Purpose: Decreases input token counts and time-to-first-token while preserving protocol compliance with client tool calling standards.
- Review scope: Source code verified against pinned commit. Proof-of-concept with calibration benchmarks; upstream library integration ongoing.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/compozy/yoshi/
- Source evidence: https://github.com/compozy/yoshi/blob/55c719718e5039f2276fbad804211682ae012f1e/benchmarks/jev-calibrate.ts#L1-L188
- Source evidence: https://github.com/compozy/yoshi/blob/55c719718e5039f2276fbad804211682ae012f1e/README.md

## tiershift

Policy-driven model routing framework routing every LLM call to the cheapest capable tier in ~180 ms via TypeSafe Jev.

- Repository: https://github.com/iamvatsalpatel/tiershift
- Category: Routing & Cost Optimization
- Jev decision: Uses declarative YAML policies evaluated by Jev discrete classification without requiring pre-collected training data.
- Purpose: Provides unified TypeScript and Python interfaces to minimize inference spend with minimal routing overhead.
- Review scope: Source code verified against pinned commit. Includes gate benchmarks and dual-language tests; latency depends on regional network proximity.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/iamvatsalpatel/tiershift/
- Source evidence: https://github.com/iamvatsalpatel/tiershift/blob/16a0826b9f62eba6699240c4b53a7237a8c41617/bench/experiments/gate-experiment.ts#L1-L83
- Source evidence: https://github.com/iamvatsalpatel/tiershift/blob/16a0826b9f62eba6699240c4b53a7237a8c41617/README.md

## heist-one

Observable browser stealth game where Jev makes typed guard judgments while deterministic code owns the physics world.

- Repository: https://github.com/AbdelStark/heist-one
- Category: High-Frequency & Simulation
- Jev decision: Queries Jev during gameplay ticks or events to determine guard alert states, feeding discrete decisions back into the game loop.
- Purpose: Demonstrates using Jev for game AI behavior trees, achieving dynamic situational awareness within deterministic constraints.
- Review scope: Source code verified against pinned commit. Complete monorepo game implementation; high-frequency remote calls require low network latency.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/abdelstark/heist-one/
- Source evidence: https://github.com/AbdelStark/heist-one/blob/632c9a55a1e5eb2cbf0b9f87db575f0b5eb36e8c/packages/game/src/decision.ts#L1-L451
- Source evidence: https://github.com/AbdelStark/heist-one/blob/632c9a55a1e5eb2cbf0b9f87db575f0b5eb36e8c/README.md

## typesafe-snake

Snake autoplayer driven by TypeSafe Jev, executing one discrete System One decision per tick with code-enforced legal moves.

- Repository: https://github.com/sorrycc/typesafe-snake
- Category: High-Frequency & Simulation
- Jev decision: Supplies board state, fruit location, and legal direction choices to Jev, selecting the optimal move direction each tick.
- Purpose: Demonstrates fast discrete choice in constrained environments while deterministic logic prevents illegal collisions.
- Review scope: Source code verified against pinned commit. Complete React/TypeScript implementation; tick frequency is bounded by network latency.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/sorrycc/typesafe-snake/
- Source evidence: https://github.com/sorrycc/typesafe-snake/blob/8bf3f7c261ad35ece3345a02d21ba638ddfaf87f/src/jev/client.ts#L1-L29
- Source evidence: https://github.com/sorrycc/typesafe-snake/blob/8bf3f7c261ad35ece3345a02d21ba638ddfaf87f/README.md

## slidepilot

Voice-driven semantic auto-advance controller for Slidev presentations powered by Cloudflare Agents and TypeSafe Jev.

- Repository: https://github.com/harshil1712/slidepilot
- Category: Creative Tools
- Jev decision: Analyzes live speech transcripts with Jev to judge whether the current slide's topics are covered, triggering slide transitions.
- Purpose: Enables hands-free slide navigation by combining semantic completion checks with manual safety overrides.
- Review scope: Source code verified against pinned commit. Includes Worker endpoints and test cases; transition timing depends on speech transcription fidelity.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/harshil1712/slidepilot/
- Source evidence: https://github.com/harshil1712/slidepilot/blob/8ba4e89b56e4f9a08be2f1f69346240cab95a7b6/apps/worker/src/decision.ts#L1-L219
- Source evidence: https://github.com/harshil1712/slidepilot/blob/8ba4e89b56e4f9a08be2f1f69346240cab95a7b6/README.md

## youtube-sponsor-detection

YouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.

- Repository: https://github.com/trungdq88/youtube-sponsor-detection
- Category: Creative Tools
- Jev decision: Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.
- Purpose: Identifies promotional reads on newly released videos immediately without waiting for crowdsourced segment submissions.
- Review scope: Source code verified against pinned commit. Full extension source inspected; videos lacking transcripts require real-time client audio transcription.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/trungdq88/youtube-sponsor-detection/
- Source evidence: https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/extension/lib/jev.js#L1-L541
- Source evidence: https://github.com/trungdq88/youtube-sponsor-detection/blob/de01f0568d043035889a296a61ce21e0accc8b16/README.md

## kev

Tiny Jev-like decision head built atop Qwen2.5-0.5B that can be trained and run locally on Apple Silicon MacBooks.

- Repository: https://github.com/jaredpalmer/kev
- Category: High-Frequency & Simulation
- Jev decision: Attaches a parallel decision head to an open 0.5B model to answer discrete questions directly from token activations.
- Purpose: Runs entirely offline on edge hardware with minimal memory footprint, offering an accessible base for custom judgment modeling.
- Review scope: Source code verified against pinned commit. Complete training and evaluation pipeline; limited parameter capacity restricts multi-hop reasoning.
- License: Apache-2.0
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/jaredpalmer/kev/
- Source evidence: https://github.com/jaredpalmer/kev/blob/cc954f2f66d86943688fdbfa07b6db18f82ed065/kev/jev.py#L1-L122
- Source evidence: https://github.com/jaredpalmer/kev/blob/cc954f2f66d86943688fdbfa07b6db18f82ed065/README.md

## NanoJev

Nano replica of Jev featuring parallel decisions, dynamic candidate sets, and an end-to-end training and evaluation pipeline.

- Repository: https://github.com/TianyuCodings/NanoJev
- Category: High-Frequency & Simulation
- Jev decision: Evaluates multiple questions and dynamic candidate spaces concurrently in a single forward pass, logging navigation choices.
- Purpose: Provides open-source training infrastructure and game environment benchmarks for investigating non-generative discrete decisions.
- Review scope: Source code verified against pinned commit. Complete training and benchmark suite; generalization depends on dataset diversity.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/tianyucodings/nanojev/
- Source evidence: https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/scripts/evaluate_live_jev_navigation.py#L1-L70
- Source evidence: https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.zh-CN.md
- Source evidence: https://github.com/TianyuCodings/NanoJev/blob/71a513bb0163b5634467842b523ee0c0ed6fb1c7/README.md

## simple-jev

Adapter turning open LLM endpoints into Jev-compatible classification services without training a separate classifier head.

- Repository: https://github.com/featherless-ai/simple-jev
- Category: SDK & Decision Frameworks
- Jev decision: Extracts log-probabilities of candidate tokens from model vocabulary logits, formatting them into standard Jev responses.
- Purpose: Enables rapid prototyping of Jev-like decision workflows against standard inference servers such as vLLM or Hugging Face.
- Review scope: Source code verified against pinned commit. API adapter and demo scripts inspected; output probability calibration depends on base model.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/featherless-ai/simple-jev/
- Source evidence: https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/simple-jev-api.js#L1-L85
- Source evidence: https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/demos/jevpilot/src/jev-request.js
- Source evidence: https://github.com/featherless-ai/simple-jev/blob/0dd5396ffce671ab7c4bfc031506d8e558cf8d23/README.md

## Janus

Framework for measuring when to employ Jev versus generative LLMs on proprietary datasets, routing queries based on measured benchmarks.

- Repository: https://github.com/FirasSX914/Janus
- Category: Routing & Cost Optimization
- Jev decision: Benchmarks Jev response accuracy and latency via a TypeSafe provider integration, deriving empirical routing policies.
- Purpose: Replaces intuition with empirical data when adopting discrete decision models, optimizing overall cost while preserving task success.
- Review scope: Source code verified against pinned commit. Provider code and evaluation policies verified; actual savings depend on dataset profiles.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/firassx914/janus/
- Source evidence: https://github.com/FirasSX914/Janus/blob/9cb66c488cf884e5997356a0de45f75aa3148774/src/janus/providers/typesafe.py#L1-L60
- Source evidence: https://github.com/FirasSX914/Janus/blob/9cb66c488cf884e5997356a0de45f75aa3148774/README.md

## jev-eval-agent

Agent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.

- Repository: https://github.com/vinilana/jev-eval-agent
- Category: Domain & Vertical Tools
- Jev decision: Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.
- Purpose: Mitigates context bloat and hallucinated tool calls in complex agents by isolating candidate selection into fast discrete steps.
- Review scope: Source code verified against pinned commit. Agent routing and simulated suite inspected; tools are primarily mocked environments.
- License: Not declared
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/vinilana/jev-eval-agent/
- Source evidence: https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/agent/lib/jev-router.ts#L1-L154
- Source evidence: https://github.com/vinilana/jev-eval-agent/blob/037de1120c84b4b63cdf748e2acf258ff66d7731/README.md

## jev-search-rerank-eval

Retrieval evaluation system measuring Jev reranking against lexical, embedding, and fusion baselines across 9,831 query-document pairs.

- Repository: https://github.com/zhuyansen/jev-search-rerank-eval
- Category: Data & Search
- Jev decision: Invokes Jev judges to grade multi-level relevance on bilingual queries, evaluating ranking metrics and judge-circularity effects.
- Purpose: Provides rigorous empirical evidence comparing discrete judgment rerankers against vector search in multilingual discovery contexts.
- Review scope: Source code verified against pinned commit. Complete evaluation suite and CLI inspected; benchmarked on Agent Skills Hub data.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/zhuyansen/jev-search-rerank-eval/
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/rankers/jev.py#L1-L46
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/label/jev_judge.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/__init__.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/__main__.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/catalog.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/cli.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/src/jse/evaluate.py
- Source evidence: https://github.com/zhuyansen/jev-search-rerank-eval/blob/c896f14e944182e17a002dd7546f06ba3788d586/README.md

## polar\_llama

A high-performance Python library integrating Polars to orchestrate parallel inference across multiple providers, featuring Jev as an alternate decision and scoring engine.

- Repository: https://github.com/pnthn-ai/polar_llama
- Category: Data & Search
- Jev decision: Serves as an alternate high-throughput decision and scoring engine within parallel Polars pipeline workflows.
- Purpose: Combines Polars dataframe throughput with Jev structured decisions for high-concurrency batch processing.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/pnthn-ai/polar_llama/
- Source evidence: https://github.com/pnthn-ai/polar_llama/blob/d10d48db20af9d5a33e696c39f660187677257f7/README.md
- Source evidence: https://github.com/pnthn-ai/polar_llama/blob/d10d48db20af9d5a33e696c39f660187677257f7/src/model_client/typesafe.rs

## JevBrowserExt

Core use case: Chrome extension (Manifest V3) port of browser-use/jev-ultrafast. Jev picks the browser operation and the DOM element in one request per step; a small text model writes TYPE\_TEXT values; it runs in the user's own tabs via OpenRouter, TypeSafe or Cloudflare Workers AI. MIT.

- Repository: https://github.com/chy4pro/JevBrowserExt
- Category: CLI & Pipelines
- Jev decision: Jev returns a structured decision for the local program; consult the source for the exact decision policy.
- Purpose: Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
- Review scope: Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
- License: MIT
- Details: https://logicrw.github.io/awesome-jev-projects/en/projects/chy4pro/jevbrowserext/
- Source evidence: https://github.com/chy4pro/JevBrowserExt/blob/0e4c5294ab3de8db09e6ddbc523ce8004406e199/README.md
- Source evidence: https://github.com/chy4pro/JevBrowserExt/blob/0e4c5294ab3de8db09e6ddbc523ce8004406e199/README_CN.md
- Source evidence: https://github.com/chy4pro/JevBrowserExt/blob/0e4c5294ab3de8db09e6ddbc523ce8004406e199/src/shared/providers/typesafe.ts