Complete project directory

A community catalog for System-1 Agent architectures with Jev. Explore projects and learning resources with entry types, review basis, and license facts.

• jev-ultrafast

  browser-use · Browser & OS Action

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

• typesafe-mcp

  itsmostafa · MCP & Integrations

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

• jev-mcp

  jkudish · MCP & Integrations

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

• SemDecide

  sharziki · CLI & Pipelines

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

• jev-codex-router

  0xNatoshi · Model Routing

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

• Winnow

  GhalebDweikat · Context GC

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

• Jev Review

  devagrawal09 · Code Navigation

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

• Blink

  ellipsis-dev · Code Navigation

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

• neo4jev

  jexp · Code Navigation

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

• jev-desktop

  lahfir · Browser & OS Action

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

• TypeSafe AI Playground

  markjaquith · CLI & Pipelines

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

• Prism

  irfndi · Domain Tools

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

• OneVOneJev

  emrickgarrett · High-Frequency / Games

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

• safer-with-jev

  andrelandgraf · Security & Guardrails

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

• fast-jev-compaction

  tamaratran · Context GC

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

• jev-review

  NiazMorshed2007 · Evaluation & Observability

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

• pg-jev

  realZachi · Data & Search

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

• jevpilot

  standardagents · High-Frequency / Games

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

• jev-browser

  jkudish · Browser & OS Action

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

• pi-jev

  y0usaf · Security & Guardrails

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

• pi-jev-auto-mode

  jomatsu · Security & Guardrails

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

• Jev-Trades

  zadescoxp · Domain Tools

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

• jev

  dannote · SDK & Decision Frameworks

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

• jev-mcp

  blakestone-x · MCP & Integrations

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

• HA-Jev

  AboveColin · Domain Tools

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

• jev-benchmarks

  AbdelStark · Evaluation & Observability

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

• Jevbridge

  gamesonrblx · MCP & Integrations

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

• jev-playground

  mizchi · Evaluation & Observability

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

• zod-jev

  jomatsu · SDK & Decision Frameworks

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

• jev-lm

  y0usaf · Evaluation & Observability

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

• jev-search

  superagents-lab · Data & Search

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

• live-jev

  vinilana · High-Frequency / Games

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

• jev-code

  devagrawal09 · Code Navigation

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

• daf-jev

  docxology · SDK & Decision Frameworks

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

• jev-chat

  adhyaay-karnwal · Evaluation & Observability

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

• jev-cli

  tumf · CLI & Pipelines

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

• AskJev

  ranjan2829 · Browser & OS Action

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

• jev-for-engineers

  Foadsf · Domain Tools

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

• jev-system-one

  haseeb-heaven · Voice & Conversation

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

• JevBird

  leftspace89 · High-Frequency / Games

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

• jev-judgment

  HyunjunJeon · Security & Guardrails

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

• jev-cli

  jtsang4 · CLI & Pipelines

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

• claude-jev

  buchmark · Code Navigation

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

• jev-browser

  tontoko · Browser & OS Action

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

• pi-jev

  TheoOliveira · MCP & Integrations

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

• jev-tree

  reachjalil · Classification

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

• jev-starter

  hamakyo · SDK & Decision Frameworks

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

• aside-jev

  himomohi · Browser & OS Action

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

• jev-skill-gate

  ShivamPansuriya · Context GC

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

• jev-guard

  leepokai · Security & Guardrails

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

• jev-mcp

  rashedInt32 · MCP & Integrations

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

• jevclient

  AboveColin · SDK & Decision Frameworks

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

• jev-workbench

  molis-ai · MCP & Integrations

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

• jev-got

  phureewat29 · Creative Tools

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

• pi-fast-jev-compaction

  joelhooks · Context GC

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

• hermes-jev-approvals

  anpicasso · Security & Guardrails

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

• jev-research

  sherajdev · Model Routing

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

• jev-resilience

  Vicente-MD · SDK Integrations

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

• jev-go

  Stumble · SDK & Decision Frameworks

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

• jev-agent-failure-benchmark

  TokenTrim · Evaluation & Observability

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

• computer-use-jev

  paulsmith · Browser & OS Action

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

• jev-broadcast-lab

  4anti · High-Frequency / Games

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

• jevgo

  fgn · SDK & Decision Frameworks

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

• jev-little-airways

  lbotinelly · High-Frequency / Games

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

• jev-playground

  Little-Planet-Labs · Decision Tools

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

• laravel-typesafe-jev

  Butochnikov · SDK Integrations

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

• jev-go

  guillemus · SDK & Decision Frameworks

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

• ask-jev

  omni- · Evaluation & Observability

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

• jev-code

  rhighs · CLI & Pipelines

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

• jev-doom-agent

  lukaske · High-Frequency / Games

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

• jev-rerank-bench

  anessbelbati · Evaluation & Observability

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

• jev-predict-skill

  DanielKillenberger · Decision Tools

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

• jev-trade

  aowang-ai · Domain Tools

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

• jevsume

  unownone · Domain Tools

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

• jev_ampcode

  thesammykins · MCP & Integrations

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

• jev-tool-permissions

  NicolasMontone · Security & Guardrails

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

• jevthoven

  cocktailpeanut · Creative Tools

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

• doom-jev

  AmoghCreator · High-Frequency / Games

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

• jev-context

  zbush · Context GC

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

• ui-generator-instinct-jev

  joevidev · Creative Tools

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

• mobile-jev

  droidrun · Browser & OS Action

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

• jev-demo

  minghanminghan · Model Routing

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

• jev-music-theory-1

  adammichaelwood · Creative Tools

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

• jev-macos-loop

  jcpsimmons · Browser & OS Action

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

• jev-router-playground

  hugo-alves · Model Routing

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

• jevscript

  amberwhitehead · CLI & Pipelines

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

• jev-trade

  Waxmell114514 · Domain Tools

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

• jev-demos

  Bud-ro · Evaluation & Observability

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

• jevex

  jvsteiner · SDK & Decision Frameworks

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

• jev-experiments

  mittal-parth · High-Frequency / Games

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

• foreman-jev

  Shifty-Eye-Games · Evaluation & Observability

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

• jevlogs

  reachjalil · Context GC

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

• ha-conversation-jev

  luxus · Voice & Conversation

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

• ai

  vercel · SDK & Decision Frameworks

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

• langchain

  langchain-ai · SDK Integrations

  An optional Jev classifier integration for Python LangChain workflows.

• oh-my-pi

  can1357 · Model Routing

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

• eliza

  elizaOS · SDK & Decision Frameworks

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

• composio

  ComposioHQ · SDK & Decision Frameworks

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

• pydantic-ai

  pydantic · SDK Integrations

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

• litellm

  BerriAI · Model Routing

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

• langchainjs

  langchain-ai · SDK & Decision Frameworks

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

• firstmate

  kunchenguid · Model Routing

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

• openchamber

  openchamber · Model Routing

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

• ax

  ax-llm · SDK Integrations

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

• agentgateway

  agentgateway · Security & Guardrails

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

• omg.dev

  BennyKok · Browser & OS Action

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

• pi-fabric

  monotykamary · SDK & Decision Frameworks

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

• latitude-llm

  latitude-dev · Evaluation & Observability

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

• instructor-php

  cognesy · SDK & Decision Frameworks

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

• atomic

  bastani-inc · Model Routing

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

• WrongStack

  WrongStack · Model Routing

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

• celesto

  CelestoAI · Code Navigation

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

• req_llm

  agentjido · SDK & Decision Frameworks

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

• vellum-assistant

  vellum-ai · MCP & Integrations

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

• vexjoy-agent

  notque · Model Routing

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

• aiavatarkit

  uezo · Voice & Conversation

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

• taskuary

  ldbumble · Evaluation & Observability

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

• orchestkit

  yonatangross · CLI & Pipelines

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

• skillbox

  kitze · Model Routing

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

• interlinked-cli

  QuentinCody · Security & Guardrails

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

• effect-agent

  danieljvdm · SDK & Decision Frameworks

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

• pi-warden

  DevMortimer · Security & Guardrails

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

• advocaat

  pithings · SDK & Decision Frameworks

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

• synkora-ai

  getsynkora · MCP & Integrations

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

• ai

  hackclub · SDK & Decision Frameworks

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

• unclutter

  kitze · Security & Guardrails

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

• openai-scala-client

  cequence-io · SDK & Decision Frameworks

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

• ego-jev

  phd-peter · Browser & OS Action

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

• bluenoise

  rokcso · Context GC

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

• jev-gomoku

  XieChengYuan · Evaluation & Observability

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

• jev-voice-browser

  moritzkremb · Browser & OS Action

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

• hono-jev-router

  yusukebe · Model Routing

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

• openjev

  razorback16 · SDK & Decision Frameworks

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

• typesafe-jev-workflow

  GiesN · Classification

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

• JevRouter

  BillionsBobby · Model Routing

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

• jevwire

  Brainwires · MCP & Integrations

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

• llama-index-jev

  WiktorB2004 · Data & Search

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

• jevcal

  abhixhek · Evaluation & Observability

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

• jev-benchmark

  wondertwins · Evaluation & Observability

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

• jev-shield

  vmendes90 · Browser & OS Action

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

• jev-frontend-qa

  Nainish-Rai · Evaluation & Observability

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

• omp-jev-compaction

  jerryfane · Context GC

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

• todo-jev

  maker-KK · Model Routing

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

• jevsome-projects

  ozers · Data & Search

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

• jev-cli

  Nasrallah-AL · CLI & Pipelines

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

• hermes-jev-north-star

  poponline63 · Evaluation & Observability

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

• codex-jev-compaction

  Wang-auspicious · Context GC

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

• pi-jev-compaction

  Wang-auspicious · Context GC

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

• jev-review-action

  fatwang2 · Code Navigation

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

• jev-curate

  AkashPriyadarshii · Data & Search

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

• jevify

  altryne · Decision Tools

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

• jev-synergy-screening

  PistachioAIHQ · Evaluation & Observability

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

• jev-mcp

  BYK · MCP & Integrations

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

• jev-classifier

  felpsdev · MCP & Integrations

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

• jev-exploration

  SamuelSacco · Evaluation & Observability

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

• jevscan

  jevbook · Domain Tools

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

• jev-askable-arm

  TarunTomar122 · High-Frequency / Games

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

• jev-flash-review

  TheBous · Evaluation & Observability

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

• jevchat

  kt3k · Decision Tools

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

• jevarena

  raihankhan-rk · High-Frequency / Games

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

• supercov

  supercorp-ai · Evaluation & Observability

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

• jev-pref

  doeixd · Evaluation & Observability

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

• jevql

  kylemclaren · Data & Search

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

• json-render

  vercel-labs · Creative Tools

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

• cua

  trycua · Browser & OS Action

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

• cline-plugin-jev-browser

  abeatrix · Browser & OS Action

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

• ai-hedge-fund

  virattt · Domain Tools

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

• jev-model-router

  davila7 · Model Routing

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

• rig-typesafeai

  0xPlaygrounds · SDK & Decision Frameworks

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

• jev-trader

  jarrodwatts · Domain Tools

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

• typesafe-computer-use

  awlevin · Browser & OS Action

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

• typesafe-mario

  fhshaik · High-Frequency / Games

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

• jev-drone

  RomanSlack · High-Frequency / Games

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

• tsai-sc

  phyous · High-Frequency / Games

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

• oc-plugins

  OpeOginni · Security & Guardrails

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

• jev-block-android-ad

  ufec · Security & Guardrails

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

• Jev-cu

  Sac-Y · Browser & OS Action

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

• jev-pruner

  tamaratran · Context GC

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

• typesafe-adblock

  realZachi · Browser & OS Action

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

• jev-cvss

  Red5d · Security & Guardrails

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

• typesafe-playground

  kavehmz · Evaluation & Observability

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

• ruby_decision_model

  obie · SDK & Decision Frameworks

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

• plasmallm

  joshuaeroman · MCP & Integrations

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

• goodwatch-monorepo

  alp82 · Evaluation & Observability

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

• mk-jev-fly-brain

  lavallee · High-Frequency / Games

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

• SpecPi

  TannerMidd · SDK & Decision Frameworks

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

• rift

  exYze · CLI & Pipelines

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

• Jev-Moderation-Bot

  brainstormity · Security & Guardrails

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

• leadgenrationaivoiceagent

  sumitrevolt · Domain Tools

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

• Agent

  AgentiLoop · Security & Guardrails

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

• captaincore

  CaptainCore · Security & Guardrails

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

• OpenWhisper

  Knuckles92 · Voice & Conversation

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

• jev

  BorisLeMeec · Code Navigation

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

• runline

  Michaelliv · SDK & Decision Frameworks

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

• super-jev

  Kevthetech143 · SDK & Decision Frameworks

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

• tenbin

  simota · MCP & Integrations

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

• qualm

  qddegtya · SDK & Decision Frameworks

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

• your-signal

  MithrilMan · Context GC

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

• jev-scout

  AkashPriyadarshii · Data & Search

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

• jev-play-ping-pong

  Icohen007 · High-Frequency / Games

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

• typesafe-rs

  AbdelStark · SDK & Decision Frameworks

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

• jevmeter

  ChetasLua · Creative Tools

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

• loki

  wundercorp · Model Routing

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

• snifftest

  DanRWilloughby · Creative Tools

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

• refgarden

  AlbionaHoti · Creative Tools

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

• jev-axi

  shiftynick · CLI & Pipelines

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

• typesafe-skill-router

  DECRUX9812 · Model Routing

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

• jev-calibration-audit

  jujumilk3 · Evaluation & Observability

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

• openclaw-typesafe-ai

  Olli0103 · MCP & Integrations

  An independent OpenClaw plugin registering one explicitly invoked typesafe_decide tool.

• typesafe-sdk-java

  Premo-Cloud · SDK & Decision Frameworks

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

• typesafe-go

  2389-research · SDK & Decision Frameworks

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

• typesafe-go

  cole-gillespie · SDK & Decision Frameworks

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

• pi-typesafe

  DevMortimer · MCP & Integrations

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

• typesafe-sdk-swift

  marandaneto · SDK & Decision Frameworks

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

• typesafe-sdk-rust

  codeitlikemiley · SDK & Decision Frameworks

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

• typesafe-sdk-php

  Butochnikov · SDK & Decision Frameworks

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

• typesafe-sdk-js

  typesafe-ai · SDK & Decision Frameworks

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

• jev-browser-use

  wy-coliney · Browser & OS Action

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

• goodall

  bensyverson · SDK & Decision Frameworks

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

• jev-go

  Gaurav-Gosain · SDK & Decision Frameworks

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

• swift-typesafe

  ainame · SDK & Decision Frameworks

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

• typesafe_sdk

  nshkrdotcom · SDK & Decision Frameworks

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

• typesafe-ai

  Twister915 · SDK & Decision Frameworks

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

• typesafe-ai-rs

  gilljon · SDK & Decision Frameworks

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

• typesafe-sdk

  joshmn · SDK & Decision Frameworks

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

• typesafe-sdk-go

  Tangerg · SDK & Decision Frameworks

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

• hermes-jev

  keeltrace · Decision Tools

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

• jev-browser

  Ying-Kai-Liao · Browser & OS Action

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

• jev-ego

  romaluev · Browser & OS Action

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

• pg_typesafe

  giuliosmall · Data & Search

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

• ruby_llm-typesafe

  kieranklaassen · SDK Integrations

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

• jev-seo

  AkashPriyadarshii · Domain Tools

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

• leanest

  baronunread · Code Navigation

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

• typesafe-ai-benchmark

  iammrduncan · Evaluation & Observability

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

• jev-dsl

  inanna-malick · SDK & Decision Frameworks

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

• typesafe-go

  zhirschtritt · SDK & Decision Frameworks

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

• Canny

  qkal · Evaluation & Observability

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

• commit-miner

  devanshbatham · Code Navigation

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

• pi-jev-compact

  ilkerulusoy · Context GC

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

• pi-jev-context

  kevinpita · Context GC

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

• duckdb-jev

  colliber · Data & Search

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

• jev-reviewer

  choxos · Domain Tools

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

• jevsql

  EugeneBoondock · Data & Search

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

• n8n-nodes-typesafe-jev

  n3ndor · MCP & Integrations

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

• tax-doc-classifier

  kyotofin · Domain Tools

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

• jev-experiments

  dabit3 · Security & Guardrails

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

• jevscape

  Skyvern-AI · High-Frequency / Games

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

• killmyidea

  monteduro · Decision Tools

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

• vibecheck

  RafalWilinski · Creative Tools

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

• jev-behavior-study

  RINNECODER · Evaluation & Observability

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

• jev-eval

  4esv · Evaluation & Observability

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

• PiJ

  tonyzdev · Code Navigation

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

• jev-commit

  valentynkit · Decision Tools

  A commit-msg hook that scores the message against the staged diff with one Jev request of five Nouls and warns by default. Default blocking is a local regex belt on high-precision added-line hits; the secret_shaped Noul blocks only with --strict.

• jev-belay

  valentynkit · Decision Tools

  A Claude Code Stop hook that reads the turn transcript locally and calls Jev only when files changed and no check has passed, blocking an unverified “done”.

• jev.nvim

  valentynkit · Decision Tools

  A Neovim plugin that asks a plain-language question of every function in the buffer and lists every Jev hit in quickfix, ranked by probability.

• jev-skip

  valentynkit · Decision Tools

  A browser extension that classifies YouTube caption segments with Jev, splitting requests when the segment or token budget is exceeded, paints five categories on the seek bar, and auto-skips those painted slices over the threshold.

• jev-plays-pokemon-red

  valentynkit · Decision Tools

  Pokemon Red on PyBoy where Python owns the route and the arithmetic, and Jev chooses only among legal actions at actual branches.

• elons-job

  bugkiwi · Context GC

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

• turing-jail

  bugkiwi · Decision Tools

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

• typesafe-sdk-python

  typesafe-ai · SDK & Decision Frameworks

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

• JevFilterForX

  grayrepo-byte · Browser & OS Action

  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.

• JevScout

  hqman · Domain Tools

  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.

• typesafeai-dotnet-sdk

  saibimajdi · SDK & Decision Frameworks

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

• zio-typesafe-ai

  jamesward · SDK & Decision Frameworks

  A Scala 3 / ZIO client that asks typed Noul, Choice, and Score questions in one round-trip and returns a NamedTuple of answers.

• typesafe-ai-rails

  GenieRobot · SDK & Decision Frameworks

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

• jev-superpowers

  AkashPriyadarshii · CLI & Pipelines

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

• reranker

  hev · Data & Search

  A Python reranker that packs a query and up to 30 candidates into one Jev state, with one Noul relevance question per document.

• typesafe-ai-playground

  BunsDev · Domain Tools

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

• litjev

  zhengxuyu · High-Frequency / Games

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

• jev-shell-history

  mrnugget · CLI & Pipelines

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

• is-malicious

  luantak · Security & Guardrails

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

• jev-router

  gargpratyush · Model Routing

  A Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.

• opencode-jev-orchestrator

  aaronshaf · Model Routing

  An OpenCode orchestrator that keeps a cheap sticky parent model and, when Jev flags a hard turn, escalates through a child subagent.

• fast-dev-compaction

  leonaaardob · Context GC

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

• yoshi

  compozy · Context GC

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

• tiershift

  iamvatsalpatel · Model Routing

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

• heist-one

  AbdelStark · High-Frequency / Games

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

• typesafe-snake

  sorrycc · High-Frequency / Games

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

• slidepilot

  harshil1712 · Creative Tools

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

• youtube-sponsor-detection

  trungdq88 · Creative Tools

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

• kev

  jaredpalmer · High-Frequency / Games

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

• NanoJev

  TianyuCodings · High-Frequency / Games

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

• simple-jev

  featherless-ai · SDK & Decision Frameworks

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

• Janus

  FirasSX914 · Model Routing

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

• jev-eval-agent

  vinilana · Domain Tools

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

• jev-search-rerank-eval

  zhuyansen · Data & Search

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

• polar_llama

  pnthn-ai · Data & Search

  A Polars library for parallel provider inference that also calls Jev per row as Noul, Choice, and Score questions, or as one typed contract over a document.

• JevBrowserExt

  chy4pro · Browser & OS Action

  A Manifest V3 Chrome port of jev-ultrafast: Jev picks the operation and DOM element in one request per step; a small chat model fills TYPE_TEXT.

• antivirus

  newuser7171 · Security & Guardrails

  A file scanner that sends extracted features to Jev for a verdict, a 0–4 severity score, and Noul indicators, then applies local quarantine or review rules.

• jev-pii-checker

  coo-quack · Security & Guardrails

  A CLI that sends text to TypeSafe Jev for PII category Nouls and a sensitivity Score, then locates spans with regex and segmentation.

• jev-robotics-demo

  FazalAAli · High-Frequency / Games

  A MuJoCo arm demo where local code proposes candidate moves and Jev chooses the target, grasp or release, and completion.

• jev-semgrep

  uehaj · Data & Search

  A semantic grep that scores each line with Jev against a meaning, including AND/OR/NOT and cross-language queries.

• jev-tweet-radar

  DDnim · Browser & OS Action

  A Chrome extension that scores each X timeline post with one Jev Noul batch for engagement value and optional tags.

• pr-sieve

  Thestral12 · CLI & Pipelines

  A GitHub Action that compiles `.jev.yml` rules into Jev questions and fails, comments, or passes from the numbers.

• questions

  nitoba · SDK & Decision Frameworks

  A TypeScript decision library that asks typed questions via Zod or native batches, defaulting to TypeSafe Jev, with optional Vercel or generative adapters.

• kody

  kentcdodds · Data & Search

  Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.

• jev-clash-royale-test

  JanDalhuysen · High-Frequency / Games

  A Clash Royale-style sandbox whose Jev bot decides play-or-hold, card, lane, and depth in one System One call.

• jevis

  jaewgwon · Browser & OS Action

  A Flutter integration_test package that registers allowed UI actions and lets Jev pick the next action and whether the goal is done.

• typesafe-ai-ruby

  hnegishi · SDK & Decision Frameworks

  A stdlib-only Ruby client that sends Choice, Score, or Noul questions to TypeSafe System One.

• jev-decision-gateway

  kuldeepsinh19 · Model Routing

  A gateway that asks Jev continue / tool / verify questions and invokes a generative LLM only when policy says generation is needed.

• foreman

  thruwire · CLI & Pipelines

  An independent supervisor loop that reads worker diffs, logs and tests, asks Jev Nouls about stuck / off-track / verify, then applies a Python policy.

• jev-clerk

  stas4000 · Browser & OS Action

  A macOS desktop clerk that books supplier invoices: Jev picks each click from a closed action list; a deep model only rewrites the playbook.

• jev-gpt

  florian-hoenicke · High-Frequency / Games

  Cascaded Choice questions that make Jev pick the next word from a word tree instead of generating text.

• TypeSafeSDK

  DotNetVibeCoderz · SDK & Decision Frameworks

  An unofficial .NET client that POSTs state and typed questions to TypeSafe /v1/systemone. The parent repo also contains unrelated SDK dumps.

• pi-jev-sentinel

  harshwasan · Security & Guardrails

  Open-source Pi coding-agent extension that uses Jev to check tool calls before they run, scan files for prompt injection, flag risky replies, and keep secrets out of what it sends.

• jev-use

  shitianfang · Context GC

  Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM

• jev-web-analyzer

  replynodes · SDK & Decision Frameworks

  See what Jev thinks about your SaaS website — powered by ReplyNodes web context and Vercel AI Gateway.

• slopcheck-jev

  harshpuri84 · CLI & Pipelines

  A prose linter that catches AI writing tells. Regex settles the 18 a pattern can settle. Jev takes the 15 that need reading, as 15 Nouls in one call, 604 ms median. It ships as a Claude Code `Stop` hook that scores Claude's own output after every turn and warns rather than blocks.

• jev_dart

  Solido · SDK & Decision Frameworks

  Jev Dart SDK to build cli, server and Flutter apps.

• fast-jev-compaction-pi

  joslynSmall · Context GC

  This Pi extension asks Jev whether each completed tool call and its full result should be kept, then locally retains, truncates, or drops verbatim tool evidence in the compaction summary.

• jev-social

  socai-io · Domain Tools

  Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.

• jev-libero

  Dimweaker · High-Frequency / Games

  Two LIBERO tasks, one control engine. Each demo loads its own JSON task definition. Videos follow simulation time, with decision and physics-preview waiting omitted.

• minojev

  zeredy879 · SDK & Decision Frameworks

  Decisions, not tokens: minojev reads calibrated, typed probability distributions straight from hidden states in one forward pass — zero output tokens, fully reproducible on a laptop CPU.

• ask-jev-skill

  shantanugoel · SDK & Decision Frameworks

  A skill for Hermes and other agents to query TypeSafe Jev for bounded option judgments and confidence escalations.

• every

  sufianetaouil · Data & Search

  Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.

• tsai-civ2

  phyous · High-Frequency / Games

  An experimental harness where TypeSafe Jev plays classic Civilization II in a browser, computing live action probability distributions.

• jev-bfs

  komikat · Data & Search

  Wikipedia link race pathfinder guided by Jev: assesses outbound links to navigate between two articles in real time.

• jev-router

  prismhq · Model Routing

  An open-source LLM router built on LiteLLM and Jev: dynamically routes requests based on task complexity and context.

• jev-secret-detection

  teyhouse · Security & Guardrails

  Benchmark and tool evaluating how well TypeSafe Jev identifies real secret credentials in file snippets.

• limpet

  noplan-inc · SDK & Decision Frameworks

  A Stop hook guardrail for coding agents: prevents premature completion by judging plain-language rules via Jev.

• pi-jev-router

  mejiasd3v · Model Routing

  Automatic model router for Pi coding assistant: integrates Jev via Vercel AI Gateway to dispatch tasks efficiently.

• pi-typesafe-jev

  legacybridge-tech · SDK & Decision Frameworks

  A Pi extension exposing TypeSafe judgments as five narrow tools, keeping threshold and action control in host code.

• robo-harness

  grmkris · Domain Tools

  SO-101 robot-arm workbench combining Bun/Effect and Python drivers, using Jev for joint action constraints.

• snake-jev

  siroccomask · High-Frequency / Games

  Real-time Snake game driven by parallel Jev assessments, deciding optimal turns in a single API call per tick.

• sqlite3-jev

  mattn · Domain Tools

  SQLite C extension enabling TypeSafe Jev judgments as native SQL functions for semantic scoring and choices.

• azdaja

  kubet · Context GC

  Bare, open-source RLM layer for existing coding agents

• jev-router

  rajdhakad9826 · Model Routing

  Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.

• ask-jev

  logicrw · CLI & Pipelines

  Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines

• slop-grader

  lukstei · CLI & Pipelines

  Rule-based CLI and agent skill that evaluates text and markdown files against custom rulesets for AI slop, grammar, and technical doc quality using Jev scores and line-by-line violation flags, then guides an AI agent to auto-fix violations.

• paper-radar-jev

  LYchoon · CLI & Pipelines

  An automated research paper radar that fetches the latest papers from arXiv, evaluates their relevance to a configurable research profile using TypeSafe AI, and ranks them by relevance score. Designed for personalized, daily literature discovery across different research domains.

• jev-issue-radar

  Patrick-SCH03 · Domain Tools

  Jev Issue Radar is a read-only dashboard for GitHub duplicate-issue triage. It retrieves likely candidates, asks Jev whether each pair is duplicate, related, distinct, or insufficiently documented, and shows selected passages from both original reports for a maintainer to review.

• soupbase

  spoonnotfound · High-Frequency / Games

  Soupbase is a bilingual Chinese-English Turtle Soup game where Jev judges player questions and reconstructions, and the app checks structured Choice results and confidence to decide clearance.

• jselect

  keltokhy · Data & Search

  Selects source-linked evidence within a token budget using Jev Noul relevance judgments and local diversity-aware selection.

• jgrep

  keltokhy · CLI & Pipelines

  Filters text, structured records, functions, and diff hunks against plain-English descriptions using Jev Noul judgments.

• openrouter-jev-mcp

  ctmx · MCP & Integrations

  A Python decision gateway and Model Context Protocol (MCP) server exposing TypeSafe's Jev model through OpenRouter's decisions endpoint to Claude Code, Codex, and Cursor agents.

• jev-align

  sutro-sh · CLI & Pipelines

  1. Evaluates the configured dataset and measures uncertainty. 2. Selects ambiguous rows plus a random audit sample for you to label. 3. Uses your accumulated labels and optional rationales to run GEPA. 4. Shows the score, certainty change, and proposed definition diff. 5. Lets you accept, reject, rewind, or resume later.

• jev-use

  savka777 · Browser & OS Action

  Voice and typed computer use for macOS. You say what you want. Jev picks the next on-screen action. macOS performs it. No screenshots: the app reads the screen through the Accessibility tree.

• grok-bot-jev

  Bodila51 · Model Routing

  Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples

• jev-dsh-decision

  Devin-AXIS · SDK & Decision Frameworks

  Provides Jev structured decision support for Agent Harness to recommend tools, Skills and Agents and return judgments with probabilities, with a native DeepSeek Harness plugin and an iPolloWork entry serving OpenCode, DeepSeek Harness and Codex Harness.

• jev-recall

  samdotmak · Context GC

  Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev

• jevbench

  fstandhartinger · SDK & Decision Frameworks

  JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open.

• jev-capability-atlas

  Zaious · SDK & Decision Frameworks

  This repository collects real Jev API-call receipts, test suites, and bilingual guides to map which narrow-decision tasks suit Jev and how Agents should evaluate and report fit.

• jevgrep

  nassim-arifette · Code Navigation

  Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.

• jev-reflex-autonomy-lab

  khordoo · High-Frequency / Games

  Multi-drone autonomy lab demonstrating TypeSafe Jev reflex decisions with optional System 2 strategy guidance.

• jevvy

  PanAchy · Security & Guardrails

  Jev-powered plugins for coding agents

• RoboJEV

  lykycy123 · High-Frequency / Games

  RoboJEV is a small, inspectable robotics laboratory. JEV receives **structured simulator state, not images**, selects an immediate intent, then selects X/Y/Z directions and a gripper command. A Cartesian controller executes the action using real MuJoCo contacts. Each task has independent physical success checks; model answers cannot declare success.

• jevalyn

  Ray-Hughes · SDK & Decision Frameworks

  The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.

• jev-security-scan

  win4r · Security & Guardrails

  Reviews Agent Skills and MCP configurations and source code with local static checks and TypeSafe Jev before installation or execution, reporting file and line evidence, risk categories, model probabilities, and coverage gaps.

• jev_jsonschema

  Kiln-AI · SDK & Decision Frameworks

  `probabilities` is keyed by your schema's values, not Jev's internal labels, so a score of `1`–`5` reads as `"1"`–`"5"` and not `"0"`–`"4"`. Noul questions carry no confidence of their own, so `confidence` is `None` for booleans and numbers.

• jev-auto-approve

  metalbear-co · Security & Guardrails

  Jev is a decision model: it answers a typed question with a calibrated probability rather than prose. This action asks it one yes/no question per thing worth being sure about — answered in parallel in a single call — and approves only when every one of them clears your threshold:

• JevFind

  Peu77 · Data & Search

  Fast semantic code search powered by Jev. Find the relevant files, line ranges, and snippets

• jev-oas-sentinel

  ShuhanSun · CLI & Pipelines

  JEV never writes a review or changes a specification. It returns typed decisions and probabilities; deterministic Python code decides whether to pass, request review, or block.

• jev-ood-calibration

  scienthoon · SDK & Decision Frameworks

  Independent calibration test of TypeSafe's Jev on a task it cannot have seen: 900 rule-generated support tickets (choice / score / boolean) plus 3 public benchmarks via Vercel AI Gateway. Raw responses, ECE with noise floor, temperature refit, per-type sign of miscalibration. Reproducible for ~$0.06.

• fast-compaction-dsh

  kolawong · Context GC

  Verdict-based context compaction for DeepSeek Harness — replaces lossy LLM summaries with fast keep/truncate/drop decisions from jev-latest; everything kept stays verbatim. Port of tamaratran/fast-jev-compaction.

• jgrep

  kyu1204 · CLI & Pipelines

  grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.

• jlink

  keltokhy · Data & Search

  The string baselines are best-match Jaro-Winkler and best-match TF-IDF cosine; the table shows the better of the two. Exact matching after normalization scores 0.26, 0.41, 0.00, 0.00 and 0.22.

• jsort

  keltokhy · CLI & Pipelines

  Ranks text along a plain-English criterion using pairwise Jev Noul comparisons and a locally fitted Bradley-Terry scale.

• hermes-jev-skills

  kerpopule · Model Routing

  Jev-powered decision toolkit for Hermes, Claude Code, and Codex providing model routing, memory compaction, and dynamic skill selection.

• jev-skill-suggester

  win4r · CLI & Pipelines

  A Python CLI and Codex Skill that recommends a suitable installed skill for the current task using TypeSafe Jev Choice and Noul checks without executing candidate skills.

• jev-linkmap

  stas4000 · Domain Tools

  Site: www.bles-software.com, 566 pages, 8,460 link decisions (15 candidate targets per page). Run on 19 Sep 2026. Every number below is from the run files in `out/` and `runs/`.

• jev-yt-time-saver

  jaibhasin · Browser & OS Action

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• pi-jev-guard

  Reindeer-AI · Security & Guardrails

  Check Pi code edits against repository Markdown rules with TypeSafe Jev

• jev-search

  larguesa · Data & Search

  Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.

• jevfill

  imohitmayank · Browser & OS Action

  Open `test/sample-form.html` in the browser, configure the extension, and click **Autofill page**.

• jev-model-tokengate

  Thanh-Mathieu95 · Security & Guardrails

  An OpenAI-compatible proxy that sits between your LLM and your users. It evaluates each sliding window of tokens **while the response is still streaming** and cuts the stream **before** a violating token can reach the screen.

• jev

  virolea · SDK & Decision Frameworks

  Ruby client for the typesafe AI Jev model

• open-jev-approvals

  alexj11324 · Security & Guardrails

  Binary approval gate for Codex and Claude Code — every intercepted tool call is reviewed by TypeSafe JEV and composed through a versioned local policy, with scoped authorization.

• Jev

  cobusgreyling · SDK & Decision Frameworks

  Unofficial TypeSafe Jev showcase — System One decisions, not chat.

• dsh-jev

  zhangxaochen · Security & Guardrails

  Jev (System One decision model) plugin suite for DeepSeek Harness (dsh)

• jevmetrics

  ishantanu · CLI & Pipelines

  Use it to assess unfamiliar instrumentation, review candidates for reduced retention, and selectively filter metrics before they reach a primary backend. Inference runs asynchronously, and cached assessments let subsequent batches use the same decision without another API call.

• jev-java

  gudcks0305 · SDK & Decision Frameworks

  Unofficial Java SDK for TypeSafe Jev and Vercel AI Gateway, with Spring Boot and WebClient support

• jevtest

  joshhu · Domain Tools

  It provides a web and CLI demo that sends user text to Jev through OpenRouter for Choice, Score, and Noul probability judgments and compares the results side-by-side with a general LLM.

• actiongate-jev

  omkarghugarkar007 · Security & Guardrails

  Open-source Jev tool-calling authorization gateway for AI agents: deterministic policy, exact-action single-use permits, MCP and HTTP enforcement.

• jeveryword

  jkrup · Data & Search

  Jev answers multiple-choice questions and does not generate text, so on its own it cannot return a name, an email address or a quote. jeveryword numbers the words of your text, offers those numbers as the answer options, and converts the numbers Jev picks back into the original substring with its character offsets.

• work-with-jev

  Adkid-Zephyr · Domain Tools

  Work with Jev is a local-first message classifier that uses Jev to sort work messages into urgent, to-do, worth-reading, and skippable groups with cross-chat to-do management and Feishu and WeCom adapters.

• Jev-Auto-Router

  miniLV · Model Routing

  Jev Auto Router (Jev Router): experimental per-call GPT model routing for Codex via TypeSafe Jev and a local Responses proxy, with independent task verification.

• jev-311-heatmap

  CompleteTech-LLC-AI-Research · Data & Search

  The live run excluded 205 reports with missing or invalid coordinates, completed **634 API calls without retries**, and reported **539,979 input tokens**. Repeated descriptions share one evaluation.

• jev-model-router

  lucianfialho · Model Routing

  Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list

• jev-phishing-bench

  anisselbd · Security & Guardrails

  The signal result above was challenged on three points: no non-AI baseline, selection and evaluation on the same emails, and no equivalent decomposition for the LLM. Three controls were added (`bench/heuristics.py`, `bench/protocol.py`, `run_llm_signals.py`); nothing above was changed. Full tables in `results/report.md`, chart in `results/controls.png`.

• jevrag

  ajanm007 · SDK & Decision Frameworks

  Replaces hardcoded RAG thresholds with explicit calibrated decision points. Five primitives (retrieval stopping, chunk splitting, context selection, answer abstention, cache trust) behind one swappable state → Decision → confidence → action interface, each evaluated on real datasets with a calibration harness that reports honestly.

• jevish

  hemanth · SDK & Decision Frameworks

  Every mode auto-curries when called with only the patterns:

• traffic-guard

  hemanth · Security & Guardrails

  High-throughput traffic and attack defense gate for incoming HTTP traffic with zero required dependencies, wire-order header validation, and TypeSafe System One acceleration for bot mitigation, exploit detection, and risk scoring.

• jev-chess

  hemanth · High-Frequency / Games

  Chess moves, evaluations, persona opponents, and game classification using TypeSafe AI System One models. Resolves natural language move intents into legal moves, evaluates positional sharpness and king risk in parallel, and powers historical persona opponents (Tal, Capablanca, Petrosian).

• tc39-atlas

  hemanth · Domain Tools

  Interactive semantic explorer and taxonomy for TC39 proposals. Applies TypeSafe AI System One (Jev) to classify ECMAScript proposals across adoption pathways, cognitive overhead, web-compatibility risk, and foundational intent archetypes.

• pkg-gate

  hemanth · Security & Guardrails

  Pre-install security gate for npm lifecycle scripts using TypeSafe System One. Evaluates preinstall, install, and postinstall hooks across intent, threat severity, secret access, and remote execution to intercept supply-chain attacks before execution.

• hfjev

  hemanth · Data & Search

  Classify Hugging Face datasets across typed semantic dimensions with TypeSafe Jev System One. Auto-adapts evaluation rubrics to dataset domains (reviews, news, LLM tuning, support) and classifies rows in a single parallel System One call with calibrated probabilities.

• tool-prune

  hemanth · Model Routing

  Calibrated tool selection and schema pruning for AI agents. Dual-engine: zero-dependency offline TurboQuant or TypeSafe System One (Jev). Prunes candidate MCP tools and schemas down to the relevant set before calling LLMs to eliminate hallucinations and save tokens.

• JevLoop

  zjunlp · Model Routing

  The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed.

• profanity-checker

  4rays · Security & Guardrails

  Deploy this Worker once, then call it from your other Workers.

• jev-paint

  achimala · Creative Tools

  Requires Python 3.9+ and a modern browser with module workers and OffscreenCanvas (current Chrome, Edge, Firefox, or Safari). No packages, build step, or Node installation needed.

• jev-chat-for-twitch

  ethanplusai · Context GC

  Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension

• laya-vs-jev-arena

  PromptEngineer48 · High-Frequency / Games

  Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision.

• jev_vampire_survivors

  oldmoldycake · High-Frequency / Games

  TypeSafe's Jev model plays Vampire Survivors on Steam: BepInEx plugin + Python brain + live decision dashboard. Native Linux only.

• jev_deep_rl

  taodav · High-Frequency / Games

  This project evaluates a fixed model. It records rewards and decisions without training or updating model weights. A seeded random policy provides a local baseline.

• jev-in-blender-experiment

  kolibril13 · Creative Tools

  Blender exposes ~2,500 operators; a TypeSafe `Choice` question holds at most 255 options, so the search is hierarchical (two requests per search):

• jev-builder

  collapseindex · SDK & Decision Frameworks

  A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally.

• jev-in-codex

  teempai · Data & Search

  Jev-powered tool and skill selection, context search, and output triage for Codex via MCP

• hermes-jev-plugin

  ajensenwaud · SDK & Decision Frameworks

  TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate

• ComfyUI-Jev

  hndrr · Creative Tools

  Custom nodes for using Jev's text interpretation and judgments in ComfyUI. Use natural-language instructions to select candidates, evaluate conditions, score text, or extract numbers, then pass the results to other nodes. Jev judgments use the TypeSafe API by default.

• jev-codex-pilot

  Charlyhno-eng · Model Routing

  A Codex overlay incorporating JEV to make the best decisions regarding model selection and depth of reasoning. All while automating the process via an automated Kanban system.

• jevshield

  lgy1027 · Security & Guardrails

  Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.

• jev-ra

  brnyxx · Browser & OS Action

  Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.

• jev-mcp

  rajasekharponakala · MCP & Integrations

  MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents

• jev-mobile

  Friedjof · Browser & OS Action

  `jev-mobile` accepts a high-level task, persists it in SQLite, and lets one durable worker execute **observe → normalize → decide → mutate → verify** against a USB-connected Android device. Jev receives concise semantics and technically valid actions; it never generates coordinates, MCP calls, or arbitrary code.

• jev-decisions

  bojansandhaus · Security & Guardrails

  Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, and a local decision journal.

• jev-browser-local

  rorshopping · Browser & OS Action

  Run jev-browser on a fully local JEV-style decision engine (no cloud API). Warm-browser fork, VRAM guard, measured benchmarks, run traces.

• jev-reranker

  shinpr · Data & Search

  Rerank, filter, and compress JSON search results with TypeSafe AI's Jev.

• ego-jev

  ZHUBoer · Browser & OS Action

  Complete browser tasks with Ego Lite and actively call Jev for semantic target selection, filtering, ranking, classification and text evidence judgments.

• jev-codex-model-and-effort-router

  gholtzap · Model Routing

  Copy and paste this into your coding agent:

• jev-mode

  ddfeyes · CLI & Pipelines

  I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.

• jev-rust-review

  kindintelligence · MCP & Integrations

  Rust-aware code review for Claude Code and coding agents, powered by TypeSafe Jev

• pi-fast-jev-compaction

  KamilPostrozny · Context GC

  Fast JEV compaction extension for pi

• jev-android

  dougsong · SDK & Decision Frameworks

  A Kotlin Android SDK for UI automation powered by TypeSafe Jev, with an accessibility runtime and sample app.

• jev-browser-skill

  zurfyx · Browser & OS Action

  Let Jev, TypeSafe's ~100ms decision model, drive your browser. A plug-and-play skill for Claude Code and Codex.

• jevcore

  litshing · SDK & Decision Frameworks

  A judgement primitive for TypeSafe **System One / Jev** — ask N things × K typed questions in bounded, cheap, fail-open requests — plus the **JEV harness**, the closed boundary in code that makes a Jev answer safe to consume. Standard library only.

• jev-skills

  laguagu · SDK & Decision Frameworks

  Practical agent skills and examples for building with Jev. API setup, routing, ranking, and evidence checks.

• mcp-server-jev

  MattiooFR · MCP & Integrations

  Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.

• let-jev-speak

  suidouble · Creative Tools

  TypeSafe's `/v1/systemone` endpoint classifies text — it returns a `choice`, a `score`, or a probability. It does not generate prose. This library makes it generate prose anyway: every word of the answer is a separate `choice` question over a vocabulary, and the loop feeds its own output back in as the prefix.

• deepseek-harness-jev-pre-compaction

  wjw66 · Context GC

  A pre-compaction advisor for DeepSeek Harness. Runs before the standard `compaction-basic` backend, using TypeSafe JEV to safely prune low-value tool results from model context. Original session events stay in the append-only log; only the model-visible view is replaced with compact markers or archive pointers to reduce context bloat.

• jevernetes

  sunil-sadasivan · Domain Tools

  Live Kubernetes log analysis, contextual investigation, and agent handoff powered by Jev.

• jevframe

  ktaletsk · Data & Search

  Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev.

• Working-Memory-Jev

  AustinAWay · Domain Tools

  Edit `.env` locally and replace the placeholder with your own key. Keep this file private; Git ignores it. Do not paste the key into frontend code, a browser field, an issue, or a command that will be saved in shell history.

• JevOps

  endomorphosis · SDK & Decision Frameworks

  Jev is a **gate**, not a generator. This package does **not** write Lean. Lake (or another oracle) lives in the implementation that *uses* the kernel.

• jeview

  andududu · SDK & Decision Frameworks

  An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.

• jev-rs

  yijunyu · SDK & Decision Frameworks

  System One judgments (noul/choice/score) from any LLM in one prefill — a Rust, Jev-compatible /v1/systemone engine

• jevchess

  choxos · Domain Tools

  Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.

• jev-edge

  kiwi0719 · Security & Guardrails

  Typed-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev. Fail-open, cached, hot-reloadable.

• jevriel

  thehan-co · SDK & Decision Frameworks

  **Codex · Claude Code · Portable skill** | [Apache-2.0 code and docs](LICENSE) | Early release

• jev-codex-plugin

  integrate-your-mind · MCP & Integrations

  Open-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review

• typesafe-jev-examples

  rajivkuriakose · SDK & Decision Frameworks

  Worked examples for TypeSafe's Jev System One decision model, runnable today through OpenRouter

• jev-browser-pilot

  aidil2105 · Browser & OS Action

  A bounded decision layer for browser and desktop automation: a decision-only model picks one next step; the code owns perception, content, actuation and verification.

• laya-jev-lab

  yibie · Model Routing

  Independent measurements of typed-decision models: Jev (TypeSafe API) vs Laya (open weights), and a local-first cascade that matches Jev's accuracy at 1.8x the speed

• jevtown

  gaborishka · High-Frequency / Games

  A check costs from half a cent (a text that dies in the first wave) to ten cents (one that reaches all 10,000), and takes from 3 seconds to a minute. The interface comes in Ukrainian and English, and so do the personas: a text is read by the crowd that speaks its language, 10,000 Ukrainians or 10,000 English speakers, so there is nothing to choose.

• JevEmon

  daniel4x · Domain Tools

  Verified milestones so far: Jev can leave the Player's House, cross Pallet Town, deliver itself through Route 1 (fighting and winning any wild encounters along the way), and reach Viridian City. Further legs of the journey (Oak's Parcel, the first Gym) aren't built yet — the walk currently ends the run once it reaches Viridian City.

• jev-browser-qa

  jonymusky · Browser & OS Action

  Browser QA where Playwright drives and films, and TypeSafe Jev judges. JSON-flow CLI for agents, run dashboard, agent skill.

• jev-gamepilot

  newuser7171 · High-Frequency / Games

  **Jev-GamePilot** is a universal autonomous AI gaming agent powered by **Laya (local sub-30ms System One inference)** and **TypeSafe's Jev System One** (`Choice`, `Score`, `Noul`). It captures real-time gameplay at 60+ FPS, fuses instant local reflexes with high-level strategic reasoning, and executes physical hardware inputs across Windows PC games and connected Android phones.

• Jev4Mellea

  SoundBlaster · SDK & Decision Frameworks

  This is an unofficial, synchronous adapter. Jev evaluates text; it does not generate or repair it.

• pi-jev-compaction

  nourhelmi · Context GC

  Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.

• jev-mcp

  CodeIA-Academy · MCP & Integrations

  MCP local que expone Jev (TypeSafe) como herramienta para Claude Code, Codex, Hermes y cualquier agente: ask_jev y list_jev_models, sin dependencias

• jev-lab

  q93304989-bit · SDK & Decision Frameworks

  This repository provides a single-page classifier demo that sends text with choice questions to Jev and displays the request JSON, probability distribution, confidence, latency, and token usage.

• jev-eyes

  LeddoEngano · MCP & Integrations

  Also in the state: `image` (size, source), `blocks` (`[x, y, w, h]` boxes with OCR confidence) and, if installed, `labels`. `see(img, compact=True)` keeps only `image`, `text` and top label names when tokens matter more than positions.

• jev-trading

  EthanAlgoX · Domain Tools

  **Jev Trading is a stock decision service that runs on your computer.** Use the web workbench or call it from your own software over HTTP. It sends market data, indicators, fundamentals, and news collected by AIStock to a model, then returns a structured decision with a record of the evidence.

• jev-agent-toolkit

  reiswaffel78 · MCP & Integrations

  Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents.

• openclaw-jev-compaction

  SqaaSSL · Context GC

  Verbatim context compaction for OpenClaw: a context engine powered by TypeSafe's Jev. Drops stale tool calls and results, never summarizes.

• jev-preflight

  muse0509 · Security & Guardrails

  A bounded Jev risk check for Claude Code: eight risk axes, one request, one optional reinspection.

• jevinf

  zerodegress · SDK & Decision Frameworks

  An inference engine for decision models of the Jev kind: each candidate path runs as segmented forwards with prefix reuse, and the Jev wire contract is served on top. NanoJev is the backend wired up today.

• jev-console

  wenchenxi · CLI & Pipelines

  Jev does not generate text. You send it a **state** plus a set of **typed questions**, and it answers each one with a typed value and a calibrated probability:

• switchboard

  ruban-24 · Model Routing

  Switchboard is a local Claude Code and Codex router. It assesses a new conversation's task with Jev, applies deterministic confidence rules to select the model and reasoning effort, and pins that route through follow-ups, tool calls, and resume to avoid unnecessary prompt-cache disruption.

• jev-skill

  wuyoscar · SDK & Decision Frameworks

  This project is a collection of Jev use cases, workflows, and agent skills with a stdlib-only Python decision wrapper.

• solar-mini4-jev

  hunkim · SDK & Decision Frameworks

  A drop-in wrapper that exposes Upstage **Solar Mini4** through the TypeSafe Jev System One API shape.

• agi-jev-containment

  carlosedm10 · Security & Guardrails

  **Open-source AI agent monitoring, malicious-agent detection, and escalate-only containment** for sandboxed LLM agents. Local HackSpain 2026 stack (AngryRobot dashboard): FastAPI, React/Vite, Neo4j. Classifies a *chain of actions*, not a single tool call. A model never pulls the plug.

• everything-about-jev

  qingshungLI · SDK & Decision Frameworks

  tell you everything about jev,TypeSafe AI's System One model for typed decisions.

• jev-assist

  glud123 · CLI & Pipelines

  Don't burn your expensive main model on grep-and-guess grunt work — let jev rank the whole repo, and save the main model for reading the right files and writing the right code.

• ego-jev

  jiangkoumo · Browser & OS Action

  Drive the ego lite browser with Jev (TypeSafe System One): one indexed element table in, one operation + target out, single process. ~2x faster than a per-step LLM loop in our measurements.

• jev-information-extraction

  abhishekmamdapure · Data & Search

  Ask questions about a PDF. Use Jev to rank the source text that answers them. Inspect each match, its probability, and its location on the original page.

• jevbus

  zkjoie · Model Routing

  A streaming event bus whose routing, subscription and consumption are decided by a probabilistic judge. The reference judge is TypeSafe AI's Jev (System One) model: send it a payload and a set of typed questions, get back calibrated probabilities instead of prose.

• jev-2048

  ARCJ137442 · Domain Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• typesafe-ai-jev-example

  ItBayMax · SDK & Decision Frameworks

  This repository provides six runnable Python demos and four notes covering TypeSafe Jev primitives and composition patterns, with offline mock mode and committed live samples from jev-1.13.0.

• tempo-jev-demo

  mychaelangelo · Domain Tools

  I created Tempo with OpenAI's Codex, using Astra and GPT-5.6 Sol, with my direction and guidance. Codex also came up with the name Tempo. I haven't personally reviewed all of the code. This is an experimental demo so don't use it for anything serious. It may contain bugs, unexpected behaviour, and issues I'm not aware of. More details on how to get started below. Have fun!

• jev-mcp

  Songokou1983 · MCP & Integrations

  Local MCP server exposing TypeSafe Jev (System One decision model) as native Claude Code / Codex tools

• jev-mcp-spring

  Ashfaqbs · MCP & Integrations

  On success each tool returns its typed result directly. On failure the tool call fails at the MCP protocol level (`isError: true`) with a short, safe message — no response body or stack trace is ever echoed back.

• typesafe-jev-mcp

  anasbekheit · MCP & Integrations

  This repository is an MCP server for TypeSafe Jev that provides a single evaluate tool taking state plus typed questions and returning noul, choice, or score answers with probabilities.

• jev-routing-experiment

  TokenTrim · Model Routing

  Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena

• jev-seo

  AgriciDaniel · Domain Tools

  **PDF: how the audit was made, the scorecard and the priorities**

• jev-arena-nanojev

  liao96312 · High-Frequency / Games

  Jev Arena is a fully local grid tactical game arena where NanoJev, rule agents and search algorithms make per-step move, attack, shoot, heal, dash and environment-interaction decisions across multiple levels with a Chinese Pygame interface.

• jevspeak

  MM-sheng · Creative Tools

  Jev can't generate text. So I made it talk anyway. A conversational interface built from probabilistic decisions and a deterministic language compiler — no generative LLM.

• jevaluate

  ElshinQ · Browser & OS Action

  Jevaluate: evaluate before you trust. Field notes, runnable scripts and an agent skill for TypeSafe Jev: gated evals, a browser loop, a product walk with DeepSeek vision, a UI text judge and a first-click tree test. Co-authored with Claude Fable 5.1.

• jev-labs

  copyleftdev · SDK & Decision Frameworks

  Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

• claude-jev-warden

  connectedGraph · Security & Guardrails

  Real-time quality gate and Art Director Warden for Claude Code powered by TypeSafe Jev 1.13 non-autoregressive decision model

• jev-flappy-bird

  jaibhasin · High-Frequency / Games

  Jev learns to play flappy-bird game with physics based context and without it

• jevex

  jimmyhealer · Code Navigation

  One MCP tool that returns the files a coding agent should read.

• jev-market-reflex

  zzsong1023 · High-Frequency / Games

  Fast typed AI decisions on live crypto markets using TypeSafe AI Jev.

• Jevs-Garage

  JGalego · SDK & Decision Frameworks

  System One turns unstructured or structured state into fast probabilistic judgments. Instead of asking for free-form prose, these demos ask `Choice`, `Score`, and `Noul` questions and receive typed values with uncertainty that application code can reason about.

• claude-jev-mod

  chrishan17 · SDK & Decision Frameworks

  Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API.

• jev-carryforward

  Dharundp6 · Context GC

  What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.

• pi-observational-memory-jev

  willfish · Context GC

  Jev decides what to keep. Compaction never rewrites the transcript.

• jev-frontier-100

  softpudding · CLI & Pipelines

  **Jev scores 77.0%; Qwen3.5 2B with a 2,048-token thinking budget scores 82.0%; Qwen3.5 4B with the same budget scores 96.7%.** This small benchmark makes Jev's observed reasoning limits tangible through nine local-model settings.

• jev-mcp-server

  wangkuangkuang · MCP & Integrations

  MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

• alphaoptimizer

  alpha-tales · Context GC

  AlphaOptimizer is an open-source tool from AlphaTales that helps Codex work with large command and tool outputs. Instead of sending a huge log or search result straight into the context window, AlphaOptimizer keeps the useful parts visible, keeps the original output available for a limited time, and uses Jev to help rank what matters when an API key is configured.

• vector-graph-rag

  zilliztech · Data & Search

  Milvus-based multi-hop retrieval library with two-stage Jev relation selection and full-passage reranking, achieving 86.07% average Recall@5 on MuSiQue and 2Wiki.

• memsearch

  zilliztech · Data & Search

  A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

• GPTCache

  zilliztech · Data & Search

  Semantic cache with a Jev evaluator that uses Noul judgments to check whether a cached response can serve an incoming request.

• deep-searcher

  zilliztech · Data & Search

  Open Source Deep Research alternative with Jev search-stopping evaluation.

• bootcamp

  milvus-io · Data & Search

  Runnable search tutorials using Gemini embeddings, Milvus retrieval, and Jev judgments for reranking, filtering, and routing.

• discern

  doeixd · SDK & Decision Frameworks

  A semantic control-flow library for Effect: Jev's `Choice` / `Noul` / `Score` answers become typed branches. Thresholds are caller-supplied, and an answer below them takes an explicit `Uncertain` branch the compiler forces you to handle rather than being rounded up to the top label. Procedure routing filters candidates with deterministic predicates first and skips the model call entirely when one candidate survives.

• jev-by-example

  ReallyArtificial · SDK & Decision Frameworks

  Ten runnable Jev examples for agent decisions: memory conflicts, tool-result checks, recovery, context selection, and handoffs. JavaScript, zero dependencies.

• stuntdouble

  ReallyArtificial · Model Routing

  Drop-in /v1/systemone proxy that shadows Jev with local decision models (Kev, Laya) and reports whether you can swap

• jev-voice

  kevinbadi · Browser & OS Action

  Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

• jev-lint

  mizchi · CLI & Pipelines

  lint text in code by jev scorerer

• jevals

  openlayer-ai · Security & Guardrails

  Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

• clash-jev

  bytelabs-oss · Domain Tools

  A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state

• jev-to-answer

  csskrtao · SDK & Decision Frameworks

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev_project_context

  poiuyjie · Domain Tools

  Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

• wechat-jev-assistant

  yushen100 · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jevmory

  romiluz13 · Domain Tools

  Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.

• jev-guard

  muratcakmak · Security & Guardrails

  Probability-scored guardrails for Claude Code: deny rule-breaking edits and unasked-for deploys, route your docs into each prompt, and check the final answer against the turn's own evidence.

• jevgo

  devbackend · SDK & Decision Frameworks

  Unofficial Go client for the TypeSafe AI System One API (Jev) — typed questions in, calibrated answers out.

• claude-jev

  0x7067 · Decision Tools

  Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing

• pi-jev-context

  Nyarlathoteppppp · Context GC

  Model performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact.

• dejevu

  idovmamane · Model Routing

  Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page, one call to any open model, one action. Faster than the Jev demo on Google Flights.

• ego-jev

  ZephyrDeng · CLI & Pipelines

  Jev (TypeSafe System One) inner loop for ego-browser — one ~0.4s typed decision per DOM step instead of an LLM turn. Agent skill for ego lite.

• Jev-in-the-Loop

  Tongyun1 · Decision Tools

  Researching how Jev can accelerate tasks that rely on LLM decision-making.

• jev-chat-windows-deepseek-jev

  Aimark-dai · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• dbt_jev

  smithclay · Domain Tools

  Score a candidate pair after ordinary SQL has generated it:

• jev-as-quant

  jiayylu · MCP & Integrations

  Typed System-1 decisions (Laya/Jev) as the judgment layer of a quant research stack, with Claude as System 2. Requirements → design → code → experiments.

• ask-jev-ai

  waynesutton · SDK & Decision Frameworks

  Most AI demos generate text. Jev does not. It reads a sentence and returns typed answers with probabilities: a choice, a yes or no, a score. That makes it usable as a primitive inside ordinary code rather than a chatbot bolted onto a page.

• jev-slop-guard

  davertor · Decision Tools

  Jev Slop Guard — a Chrome extension that scores and stamps AI slop on your X and LinkedIn feeds as you scroll

• jev-sdk-java

  luigivis · SDK & Decision Frameworks

  Type-safe Java 21 client for the TypeSafe AI Jev (System One) decision API

• pytest-jev

  allebee · CLI & Pipelines

  Extra state goes in `context`, such as a policy or the documents a RAG app retrieved. A claim can name it in backticks:

• jev-ai-sdk-form-router

  vercel-labs · SDK & Decision Frameworks

  Route form submissions to the right people with Jev and AI SDK.

• jev-flappy-bird

  hosseintoussi · High-Frequency / Games

  A live demo of TypeSafe's Jev model playing Flappy Bird, one flap-or-wait decision at a time.

• jev-storyboard-lab

  jimmyliao · Domain Tools

  (`agent_framework.foundry.FoundryChatClient` is a different client this repo doesn't use — its `credential` parameter only accepts Azure AD token credentials, not an API key. If you only have a key-based Azure OpenAI resource, `OpenAIChatClient` is the path that actually works.)

• jev-codex-router-skill

  455-dIAO · Decision Tools

  Portable Codex Skill for Jev model and reasoning-effort routing, with safe installation and Chinese usage guides

• jev-connector

  juanlentino · Domain Tools

  WordPress connector for the TypeSafe System One API (Jev): typed questions, confidence-scored answers, core Connectors API key management

• VideoAdGuard-Jev

  xianggelila177 · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• claude-jev-plugin

  dr-dimitru · Security & Guardrails

  TypeSafe Jev semantic guardrails for Claude Code

• ego-jev-ultrafast

  shikaizhong-design · Security & Guardrails

  Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial.

• jev-skill-router

  himomohi · MCP & Integrations

  Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.

• jev-trip

  liaoyuhua · Domain Tools

  Jev Trip is an explainable day-trip planner. The LLM plans ahead; Jev chooses and checks. Deterministic code handles route facts, time calculations, validation, and versioning.

• jev-planner

  rxova · CLI & Pipelines

  With **N** agents, `--mode ultra` makes **2N + 1** agent calls: drafts, reviews, and final synthesis, plus **N** if Jev requests another review. The default `balanced` makes as few as **N + 1** and never more than `ultra`; `fast` makes **N**, or **N + 1** when it merges. Each Jev evaluation is a separate TypeSafe call.

• jevyoumean

  syumai · CLI & Pipelines

  Unlike an edit-distance `Did you mean?`, `jym` matches on *intent*: it hands Jev the candidate subcommand names plus their help descriptions. `remove → rm`, `list → ps`, `undo → restore` are close in meaning but far in spelling — that is the gap this experiment targets.

• jev-yaba-wechat

  wuxie888 · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-usecases

  kenhuangus · Domain Tools

  Production TypeSafe Jev (System One) use-case harnesses with confidence-gated decision logic

• jev-bot

  nssmd · Decision Tools

  Self-hosted Jev decision workbench and Feishu bot: automatic choices, probabilities, and experimental word/character writing.

• prompt2jev

  sumleo · CLI & Pipelines

  Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script

• typesafe-jev-opencode

  moisesfilho · MCP & Integrations

  Jev is not a conversational replacement for Gemini, Claude, or GPT. It evaluates application state against typed questions and returns structured answers and probabilities that an agent can use to route or gate work.

• jevopt

  Ramneet-Singh · CLI & Pipelines

  Making intelligent compiler optimisation decisions with Jev

• jev-chat-windows-laya

  ZJemYoung · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-synthetic-survey

  jjd-lab · High-Frequency / Games

  New to synthetic survey respondents? [Start here](#new-to-this-start-here). For the raw runs, the scored reports and the code, see [where to go](#where-to-go).

• jev-linkedin-slop-filter

  Arpit-Khandelwal · CLI & Pipelines

  Judges every LinkedIn post as it scrolls into view and slams a rubber stamp on it — **BAIT**, **CORP**, or **BRAG** — with the confidence score printed on the stamp. The post stays readable underneath.

• kojev

  ItisNoMatter · Domain Tools

  Kotlin Multiplatform client for Jev that returns your own enum/sealed types instead of string keys.

• jev-tab-order

  proshunsuke · SDK & Decision Frameworks

  **Organize the entire window with a single Jev API request.** Grouping and ordering decisions are evaluated together, regardless of the number of tabs.

• cairn-jev-lab

  Cairn-ink · Domain Tools

  Use it to test a memory policy before letting it decide what an agent keeps. The lab includes editable cases, a reusable JavaScript entry point, and reports that retain both successful judgments and mistakes. Node.js 22+, no runtime dependencies.

• jev-in-mcp

  chy4pro · MCP & Integrations

  MCP relay that adds use_jev to every server: Jev picks the tool calls, the calling model writes the values Jev cannot choose, the relay executes. Built on jev-dev-kit.

• Jevatar

  AppChainAI · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• JevTools

  RileyCarney · Domain Tools

  A toolkit, knowledge base, web cockpit, and reference implementation for building AI applications with **Jev (TypeSafe System One)** via **OpenRouter Alpha Decisions** and **TypeSafe Direct API**.

• jev-browser-skill

  ChenYCL · Browser & OS Action

  Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP

• jev-model-router

  gualican · CLI & Pipelines

  Routes prompts to the right Claude tier (Haiku/Sonnet/Opus) using TypeSafe's Jev model

• jev-chrome-extension

  gavansmyth-arch · Security & Guardrails

  1. Open any website. 2. Click the Jev icon. The side panel opens on **Drive**. 3. Type a goal, e.g. *Search Wikipedia for "espresso" and open the article*, and press **Run**.

• typesafe-jev-incident-router

  kyle-chalmers · CLI & Pipelines

  Confidence-gated incident routing with TypeSafe Jev

• jev-lab

  Pasblinn · Model Routing

  Open lab: Jev (TypeSafe System One) routing in front of Claude Code - measured bugs, patch, and a hard fallback with alerts

• jev-laya-benchmark

  harrymunro · Decision Tools

  Speed and accuracy benchmark: TypeSafe's Jev API vs the local Laya MLX typed-decision model on synthetic tasks

• jevgrep

  allebee · CLI & Pipelines

  On the bundled sample (`examples/sample.log`, 200 lines):

• jev-test

  clduab11 · Domain Tools

  Pre-registered benchmark: can a 2B local model (Gemma 4 E2B) answer web questions without making things up when a decision model (TypeSafe Jev) makes every call? SearXNG for search, MemPalace for verbatim memory, seven arms including open local judges. Spec and thresholds fixed before any run.

• jev-agent-kit

  walidboulanouar · MCP & Integrations

  jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.

• jevcheck

  sathariels · CLI & Pipelines

  Probabilities and model versions move. A raw `0.94` is not a release decision. jevcheck records a **production contract** (baseline model + fixtures + expected answers) and evals a candidate against that fixture.

• typesafe-jev-ruby

  dtheofr · Decision Tools

  Ruby client for Jev, TypeSafe's System One model: typed questions, probabilistic answers. Zero runtime dependencies.

• jev-writer

  Kaos599 · Domain Tools

  Unlike generative writing assistants that flatter drafts, jev-writer enforces strict statistical safeguards: an observational power gate, date-confound controls, and Benjamini-Hochberg false-discovery corrections. It reports what it finds in plain English and refuses to state findings when sample sizes cannot support them.

• jev-agent-hooks

  onlyjq04 · Model Routing

  TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing

• jev-skills

  WanLanglin · CLI & Pipelines

  Claude Code & Codex skills powered by Jev, TypeSafe's System One model. 256 calibrated judgements for $0.0005 in 0.72s — 360x cheaper than Claude Opus 5. Includes the first published Jev calibration curve, measured on 4,995 real agent decisions.

• jev-triage

  ccai40359-wq · Decision Tools

  Millisecond-class test-failure triage for coding agents: RETRY / FIX_CODE / FIX_ENV, powered by TypeSafe Jev.

• jev-is-not-odd

  ItzSupra13 · SDK & Decision Frameworks

  A probabilistic, AI-powered utility to determine if a number is not odd (or not even) using TypeSafe's Jev model and the Vercel AI SDK.

• sabi

  vizuh · Model Routing

  Adaptive inference scheduling for AI agents — per-round model, effort and provider routing for coding harnesses: a Command Code mod or a local OpenAI-compatible proxy.

• jev-calculator

  pc418 · Domain Tools

  Vars live in `wrangler.jsonc`: `JEV_BASE_URL` / `JEV_MODEL` (gateway), `TYPESAFE_BASE_URL` / `TYPESAFE_MODEL` (direct fallback), `TURNSTILE_SITEKEY`, `TURNSTILE_HOSTNAMES`, `JEV_DISABLED` (kill switch). Rate limits are Workers Rate Limiting bindings: `API_LIMIT` per IP and `FALLBACK_LIMIT` for the direct route as a whole.

• jev-chat-windows

  jev-chat · Domain Tools

  A Windows companion reply assistant that captures WeChat Windows 4.x windows with local offline OCR, uses Jev to judge intent and generate three candidate replies, and fills the chosen text into the WeChat input box without auto-sending.

• 332_lab-jev-chat

  Liyucheng1997 · Domain Tools

  The Windows app reads visible WeChat chat text via UI Automation or local OCR, uses Jev for structured intent judgment, and optionally uses DeepSeek to generate three copyable reply suggestions.

• laya-vs-jev

  virajbhartiya · High-Frequency / Games

  Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording

• Jev-Mem

  libingzheren · Context GC

  **Better memory for long-running AI agents—with fast decisions and focused reasoning.**

• jev-calibrate

  smkrv · CLI & Pipelines

  Jev is the typed-decision model from TypeSafe: it takes a `state` and a set of questions (`noul`, `choice`, `score`) and returns probabilities instead of text. How well a question works depends on its wording, on your data and on the threshold you cut at, and none of the three can be read off a single good-looking answer.

• jev-papers

  stas4000 · Data & Search

  1,000 arXiv AI papers classified with one Jev decision each, checked against an LLM judge. Open rebuild, MIT.

• muse-jev-playbook

  Bodila51 · Model Routing

  Jev decision layer for Muse: a fast, cheap TypeSafe AI gate before expensive agent work — confidence policy, recipes, reference router, honest measurement.

• jev-compaction

  Waxmell114514 · Context GC

  A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.

• jev-engineering

  codejunkie99 · Security & Guardrails

  Jev Engineering: Typed Decision Systems for Reliable Agent Workflows. Paper, diagrams, and companion examples by Av1dlive.

• jev-bigquery-cloudrun

  jeffonelson · Data & Search

  Classify support tickets in BigQuery with Jev and Cloud Run

• jev-guard

  ClemensSchartmueller · Security & Guardrails

  High-speed, cross-agent safety gate plugin for **Claude Code**, **Codex CLI**, and **Antigravity**.

• jev-model-router

  satviksinha · Model Routing

  Model router for Claude Code using Jev

• browser-use-with-jev

  garry-schuette · Browser & OS Action

  **Keep Browser Use's execution engine. Move bounded decisions to Jev.**

• jev-mobile

  xinwang-nwpu · Browser & OS Action

  One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast!

• emoji-jev

  colinmcdermott · Creative Tools

  The app sends typed text to Jev to get parallel emoji Choice, emotion Choice, Score, and Boolean results displayed as an emoji keyboard.

• jev-geo-audit

  stas4000 · Domain Tools

  300 public pages audited for AI citability with Jev decisions, checked against an LLM judge: agreement, cost and latency, measured

• jev-skill-selection

  redreamality · Context GC

  Pre-message hook: use TypeSafe Jev to keep/drop skills and shrink agent context

• jev-smart-router

  rmosleydb · Model Routing

  JEV Smart Router — a Databricks App that uses TypeSafe JEV to pick which model answers each message, then runs inference on the chosen Databricks Foundation Model API endpoint.

• jev-rl

  Bring-AI · High-Frequency / Games

  JEV Reinforcement Learning: four classic games trained with JEV-powered rewards, reproducible experiments and checkpoint replays.

• openclaw-jev-plugin

  herval · Model Routing

  A silenced message never reaches the language model, so it costs one Jev call and no model tokens. Direct messages always get an answer unless you choose to gate them too.

• typesafe-jev-tools

  wotai-dev · CLI & Pipelines

  A Claude Code hook that asks whether the decision you are writing needs a model at all. Includes a measured 149-row comparison of TypeSafe Jev against Claude Haiku 4.5.

• jev-browser-skill

  wanghai673 · CLI & Pipelines

  This Codex Skill lets Codex drive Chrome through Jev to complete multi-step browser tasks from a goal description with preset inputs.

• codex-jev-preflight

  wellkilo · CLI & Pipelines

  Fail-open Codex UserPromptSubmit hook that injects TypeSafe Jev pre-task routing metadata.

• jev-go-sdk

  ajayk · SDK & Decision Frameworks

  Dependency-free Go client for TypeSafe AI's System One API and the Jev model

• jev-msw

  royalpinto007 · SDK & Decision Frameworks

  Mock Jev API decisions with MSW for deterministic tests without real API calls or credits.

• jev

  kataras · SDK & Decision Frameworks

  A Go client for the TypeSafe AI's System One API and its model, Jev.

• typesafe-jev-traffic-demo

  trycatchkamal · High-Frequency / Games

  This is a **simulation**. It is not connected to, and cannot control, any real traffic signal — Hong Kong's Transport Department publishes no write API for that, only a read-only feed of sensor data. Everything downstream of that feed (the phase timing, the amber/all-red clearance, the safety limits) runs entirely in this process's own memory.

• jev-screen-mcp

  jiawei686 · MCP & Integrations

  Single-purpose MCP server (one tool, one job): a content-moderation gate powered by TypeSafe Jev (System One decision model).

• jev-review-mcp

  jiawei686 · MCP & Integrations

  Single-purpose MCP server (one tool, one job): a code-review gate powered by TypeSafe Jev (System One decision model).

• jev-paste

  Anson-gzy · Creative Tools

  Contextual, inline clipboard decomposition for macOS — Tab-to-paste with full history and time-decay ranking. Powered by TypeSafe JEF.

• jev-router

  AABBAASS1 · CLI & Pipelines

  Route any task to the right AI agent in under 1 second using Jev (TypeSafe System One). Supports Claude, ChatGPT, Cursor, and Antigravity with auto-launch on macOS, Windows, and Linux.

• jev-skill-router

  shimo4228 · Decision Tools

  Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer (shadow-first). A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router.

• jevsearch

  kylemclaren · CLI & Pipelines

  Site search that understands the question. Ranked by TypeSafe's Jev model.

• jev-mcp

  ieee0824 · MCP & Integrations

  A Rust MCP server for TypeSafe AI Jev structured decisions

• jev-zork

  Resadan-dev · CLI & Pipelines

  Jev (TypeSafe System One) plays Zork I: one Choice per move over Jericho's valid actions, with its confidence on display. French dashboard.

• jev-prompt-optimization

  j341nono · Domain Tools

  automatically optimizing the instructions and decision criteria of TypeSafe Jev Choice from labeled data

• jev-graphrag

  neo4j-field · Code Navigation

  Small demos + use-case backlog: TypeSafe AI's Jev as a calibrated decision layer for GraphRAG pipelines on Neo4j.

• jev-gateway

  TexasOct · Model Routing

  Session-aware OpenAI-compatible model-routing gateway powered by JEV

• jev-research-pipeline

  shimo4228 · Data & Search

  **Code owns the loop, Jev judges, Qwen writes: a daily research monitor for standing questions.**

• reflex

  kaustav1996 · Security & Guardrails

  A coding agent and personal assistant built on the Pi coding agent. Jev checks every tool call, turn and voice transcript, and code decides what happens next: allow, ask or block an action, which model tier to use, and whether a "done" was actually verified.

• jev-dataops

  RenaGao · Data & Search

  An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.

• jev-test-filter

  mizchi · CLI & Pipelines

  Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understand

• JevPR

  HexyeDEV · Security & Guardrails

  PR Risk review, automated by Jev

• jev-agent-browser

  forvela · Browser & OS Action

  Fast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.

• swift-jev

  d-date · SDK & Decision Frameworks

  A Swift client for TypeSafe AI's Jev — typed judgements, not text

• JEV-Paper-Radar

  Eliot5566 · Domain Tools

  In GitHub Actions the links point at your own repo automatically (`GITHUB_REPOSITORY`), so a fork needs no configuration. Locally, set `output.feedback_repo = "owner/name"` or run `paper-radar harvest --repo owner/name`.

• jevlang

  sumanmichael · SDK & Decision Frameworks

  The simplest way to write decision workflows in Python. Python with a smart if.

• open-bonsai-jev

  NicolaiLassen · SDK & Decision Frameworks

  openjev's mechanism, Bonsai's weights: typed decisions read straight from one forward pass of a 1.75-bit 27B model. Credit to TheoLeeCJ (SemIf/OpenJev) and PrismML.

• ask-jev

  kuhung · Domain Tools

  Ask Jev is a Neo-Brutalism style web app where users enter everyday dilemmas and receive direct decisions from Jev.

• jev-browser

  Mrlyk · Browser & OS Action

  Browser automation CLI for AI agents, powered by the Jev model's millisecond decisions and near-zero inference costs

• jevsql

  sarathi-aiml · Data & Search

  Text-to-SQL where the model never writes SQL — typed, calibrated decisions (TypeSafe Jev) + code-assembled queries

• jev-dspy-lab

  jmanhype · SDK & Decision Frameworks

  Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

• Jev_Ontology

  dagfinndybvig · Domain Tools

  We built a working MVP that pairs an LLM-authored ontology with Jev's calibrated classification, tested it against the live Jev API on 78 unique tickets across 5 sessions (86 classifications -- Session 4 re-runs Session 2's eight tickets), closed the feedback loop, and ran a 3-iteration convergence experiment. Total cost: $0.0085.

• jev-cli

  joshLong145 · CLI & Pipelines

  A CLI wrapper written in python for Jev

• chat2jev

  Chandler-Sun · Model Routing

  Convert OpenAI-compatible Chat Completions requests into TypeSafe System One (Jev) **State / Questions**, compare generated text with structured judgments, and publish reusable question sets as proxy routes.

• jev-layer

  typakon4 · SDK & Decision Frameworks

  Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.

• guardrail-chatbot-jev

  taman-spirit · Security & Guardrails

  It is a library, not a service. You call it, you get a verdict, and your code decides what to do. It runs in **Python and TypeScript**, both reading the same policy file, so the two sides of your stack cannot drift apart. Neither package has a third-party dependency.

• jevpdf

  kylemclaren · Data & Search

  `server/index.ts` is a small Bun server that serves `dist/` and the `/api/jev` proxy, which uses the same forwarding code as dev (`server/jev-upstream.ts`). Because the live proxy spends real credits, it only accepts same-origin POSTs from the app, pins the model, caps request size, and rate-limits each IP.

• jev-demo

  PenglongHuang · Browser & OS Action

  A zero-dependency local web demo for TypeSafe's **Jev (System One)** decision model: send a state plus typed questions, get choices, scores and calibrated probabilities back.

• jev-reasoning-navigator

  AndreuVM · Security & Guardrails

  En lugar de depender de heurísticas matemáticas frágiles o distancias vectoriales locales de coseno, `JEV-Reasoning-Navigator` utiliza **TypeSafe AI (`typesafe-sdk`)** como motor único y autoritativo de decisión cognitiva:

• jev-toolkit

  jbt95 · MCP & Integrations

  MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

• jev-kit

  jonathanavis96 · Security & Guardrails

  Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers.

• jev-factorio-agent

  CompleteDotTech · High-Frequency / Games

  Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE

• dsh-jev

  Excalibur9527 · Context GC

  This DeepSeek Harness plugin sends each round's latest user message to the systemone (Jev) API for emotion and intent classification and injects the result as plugin-sourced runtime context, with API Key and all parameters configured in the GUI settings page.

• jev_playground

  JYeswak · SDK & Decision Frameworks

  Jev answers typed questions about a state with calibrated numbers. This repo is where we find out which of those numbers deserve to drive code, and where a regex or a constant does the job better.

• jevpolicy

  Sanoy24 · SDK & Decision Frameworks

  JevPolicy is an open-source TypeScript decision runtime that turns probabilistic judgments from Jev, accessed through Vercel AI Gateway, into versioned, deterministic, replayable, observable application decisions.

• jev.tg

  Wing9897 · Context GC

  Local Telegram filter stores channel messages locally and sends them in batches to Jev or a local model to keep only messages matching natural-language conditions.

• stuntd

  bladedevoff · Model Routing

  Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

• jevk5

  allebee · High-Frequency / Games

  An open model that answers the same typed questions Jev answers — yes/no, choice, score — in one forward pass with zero generated tokens (~13 ms on an H100), plus a head-to-head harness that puts Jev and the open model on the identical board and question so the two can be compared directly. It serves TypeSafe's `/v1/systemone` wire format, so a Jev client can point at it unchanged.

• jev-retrieval

  romeromarcelo · Data & Search

  Grep-shaped Rust CLI for coding agents that finds files matching a plain-language concept: a local BM25 pass recalls candidates, Jev verifies each file window-by-window with Noul gates, and one listwise Choice per lane reranks the kept files into `path:line score` output with calibrated probabilities. (Author-submitted: I am the maintainer.)

• jev-toolspace

  xuan7zhang · Context GC

  Jev answers yes/no (`noul`) questions about a shared state and returns an independent probability for each one. One API call scores every tool in a menu with one question per tool, and a tool's score does not compete with the others.

• jev-does-not-play-dice

  KantaHayashiAI · SDK & Decision Frameworks

  Code, recorded outputs, and analysis scripts for probability-output experiments with Jev: fair random draws, Noul (Yes/No) questions, and forecast documents.

• jev-blindspot

  jsk4581 · CLI & Pipelines

  A side panel for Claude Code and Codex CLI that shows the blind spots of each prompt you submit: what the request would have needed to consider and shows no sign of. Jev decides, in one call per prompt, whether the prompt is worth a second look; only then does the agent's own headless mode read the project and return the items. Nothing blocks the prompt, nothing is added to the session.

• JevRev

  Alex314618-create · CLI & Pipelines

  Your LLM can imagine, write, test, and revise. It should not have to make every cheap routing decision by itself.

• go-jev

  mattn · SDK & Decision Frameworks

  Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model

• duckdb-jev

  prasanthj · Data & Search

  High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL.

• typesafe-jev-calibrate-for-code-review

  Selmar · CLI & Pipelines

  About calibrating Jev for code reviews

• jev-triage

  boldbug1 · CLI & Pipelines

  Message triage CLI in Go, built on the Jev decision model from TypeSafe AI. Categorizes messages, scores urgency, and flags low-confidence ones for human review.

• Jev_steer_or_queue

  Larkspur-Wang · CLI & Pipelines

  Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex CLI in testing.

• jev-skills

  eran-broder · Context GC

  Skills without the context tax. Claude Code and Codex plugin: TypeSafe's Jev decides on every turn which skills the model sees. Always-on context cost: 0 tokens.

• jev-enforce

  erkamyaman · Security & Guardrails

  📏 Claude Code plugin that makes Claude follow your CLAUDE.md: every reply and edit checked by TypeSafe Jev ✅

• heyreach-jev-bot

  matthew004-web · Domain Tools

  Signal-based LinkedIn outbound scoring for HeyReach, running on Jev (TypeSafe System One).

• jev-architecture-research

  g0runmezadam · SDK & Decision Frameworks

  Black-box reverse engineering research archive for the Jev decision model

• bes-kelime-jev

  mahmut-gundogdu · Creative Tools

  Jev bir sohbet modeli değil, **evaluation** modeli. Serbest metin üretmez; tipli sorulara `choice` / `score` / `boolean` cevapları döner. Bu, "sadece şu 5 kelimeden birini söyle" kısıtını *prompt'la rica etmek* yerine **tip sistemiyle garanti altına almayı** mümkün kılıyor: model 5 kelimenin dışına çıkamaz, çünkü API'nin döndürebileceği değerler bunlar.

• n8n-nodes-jev

  rahulthakore16 · MCP & Integrations

  Jev by TypeSafe AI for n8n: typed decisions, probabilities, and confidence-aware workflows

• CUA-JEV

  ZJU-REAL · Browser & OS Action

  The [experimental open-task paths](docs/OPEN_TASKS.md) separate model planning from Jev's typed action selection. They discover browser DOM elements or Windows UI Automation controls dynamically and offer grounded structured-tool / physical-GUI alternatives without a site- or app-specific click sequence. A twelve-action browser-to-VS-Code research case now runs end to end with a model and Jev, but **arbitrary-task generalization is not claimed**.

• jev-pilot

  h0j5bz0adh0-stack · SDK & Decision Frameworks

  Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)

• jev-A-share-trader

  Eric-Zhou-0302 · Domain Tools

  A Jev-powered technical analysis workspace for China A-shares, supporting AKShare/Tushare, market scans, and Buy/Hold/Sell assessments with time horizons and traceable evidence.

• jev-route

  mcftira · Model Routing

  **Run it. Log it. Distill it. Own it.**

• grok-jev-guard

  0xwhrari · Security & Guardrails

  `grok-jev-guard` sits immediately before a meaningful Grok Bot tool sequence. It receives a compact description of the pending operation and returns one explicit action:

• jev-table-tennis

  LiuHao-1443 · High-Frequency / Games

  Table tennis vs. TypeSafe's Jev (System One). Every paddle move on the right is a live model decision — no local prediction, just a lookup table and a servo.

• DataJev

  zzz1YAO · Data & Search

  ⚡ DataJev LLM → Analyze Jev → Continue / Switch / Verify / Stop System-1 control for System-2 data agents

• jev-drive

  Alpha-Harper-Franklin · Domain Tools

  Jev + autonomous driving: structured decisions, multimodal baselines, recovery research, and measured API diagnostics.

• jev-practice-speed

  tubone24 · High-Frequency / Games

  A WebGL demo where you play the card game Speed against a CPU whose brain is TypeSafe AI's Jev. The whole point of the app is to measure and show Jev's decision speed and decision accuracy in real time.

• jev-wrapped

  gaborishka · Domain Tools

  The browser asks for up to four pages at a time (the plan says how many), which makes up to 24 Jev requests in flight, and shows every answer as it arrives. If a page comes back throttled, it goes to the end of the line and the run drops to three pages at a time, then two. There is no shared queue: every visitor's run is paced by their own browser, and the only shared ceilings are the daily ones below.

• jev-lab

  llt22 · SDK & Decision Frameworks

  Hands-on research lab for TypeSafe's Jev (System One model): reproducible benchmarks of Noul/Choice/Score primitives, confidence gating, fan-out latency, agent control — plus a living audit of the Jev ecosystem.

• can-jev-bayes

  TomRichner · High-Frequency / Games

  How well can Jev make sequential decisions under uncertainty, and how can Bayesian methods help it learn and act more effectively?

• dsh-jev-verify

  xienda · Security & Guardrails

  Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.

• jevcode

  miounet11 · CLI & Pipelines

  This repository provides an Astro-based multilingual documentation site explaining Jev's Choice, Score, and Noul decision primitives with architecture patterns and usage examples.

• jev-toto

  maxlibin · CLI & Pipelines

  Counting and comparison happen in Rust, because Jev is documented as unreliable at arithmetic. Jev receives per-number facts plus plain-English labels and answers two questions per number in one request: a yes/no probability for "drawn in the next draw" and a five-level cold-to-hot score with confidence. Module layout and commands are in `CLAUDE.md`.

• typesafe-jev-plugin

  arnab621 · CLI & Pipelines

  Jev from Typesafe.ai is a "System One" AI model that returns **typed, calibrated judgments** instead of generating text. You define what to classify (a Choice), score (a Score), or verify (a Noul), and Jev returns a structured answer with a probability distribution — fast, cheap, and directly consumable by code.

• tictacjev

  darthblanc · Domain Tools

  A tic-tac-toe app where one player is Jev, TypeSafe AI's System One Model with live confidence scores and probabilities.

• jev-tmmluplus-eval

  lianghsun · CLI & Pipelines

  Jev is not a chat model. You hand it a `state` plus a map of typed questions, and it returns one typed answer each — with calibrated probabilities and **no generated text**.

• milvus-model

  milvus-io · Data & Search

  A library integrating embedding and reranker models from OpenAI, SentenceTransformers etc for semantic search in vector database.

• JevIntent

  Nisaka520 · Domain Tools

  It is a FkWeChat plugin that analyzes a long-pressed WeChat text message with the Jev model for intent, emotion, urgency and reply posture and shows the result in local Toasts.

• jev-judge-mcp

  PyModel · MCP & Integrations

  Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

• laya-jev-GraphRAG

  bodepudimuneendra-netizen · Data & Search

  Agentic GraphRAG engine using swappable System One decision models (local Laya / cloud Jev). Features a complete 4-phase pipeline (Ingestion, Pre-Retrieval, Traversal, Post-Retrieval) and evaluation across Neo4j, Memgraph, Apache AGE, and Kùzu driven by a custom A* traversal algorithm.

• jev-agent-design-with-topk-logits-choices

  6Mikao9 · SDK & Decision Frameworks

  Research design for a Jev-native agent system: tool integration, speculative parameter proposals, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.Feature:Jev naturallanguage conversation prototype using external helper logits and dynamic Top-k token selection.

• JevBystander

  Nisaka520 · Domain Tools

  This Android accessibility app reads visible WeChat one-to-one chat text and uses Jev to judge intent, emotion, urgency and reply posture, showing the result as 3 Toasts without generating or sending replies.

• jev-for-all

  emirbartu · Model Routing

  Jev for every agentic development workflow — the System One decision model wired into whatever harness an agent codes in: OpenCode today, Claude Code and Hermes adapters next.

• JevLight

  usail-hkust · Domain Tools

  Jev-powered traffic signal control on CityFlow with structured phase and green-time decisions.

• jev-benchmark

  YidiDev · SDK & Decision Frameworks

  Rubric-Based Zero-Shot Classification Benchmark: Jev vs Claude Haiku 4.5 vs Claude Sonnet 5 vs OpenJev on rubric-conditioned classification, chained decision execution, and exam grading -- with full price tracking.

• jev-music-tag

  xhongc · Domain Tools

  A minimal FastAPI and React workbench that sends local audio tags to Jev for decisions and writes the returned metadata updates back to the audio files.

• jev-claw

  trietphan · Model Routing

  Typed model routing for OpenClaw agents, powered by TypeSafe Jev

• jev-2048-selenium

  AMMIROSOH · Browser & OS Action

  Selenium 2048 player powered by expectimax search and TypeSafe Jev, with portrait FFmpeg recording.

• jevbrief

  Parthkomalwad · Context GC

  [Adapters](#adapters) &nbsp;·&nbsp; [Quick start](#quick-start) &nbsp;·&nbsp; [Game demo](#watch-jev-play-a-game) &nbsp;·&nbsp; [Python](#use-it-in-python) &nbsp;·&nbsp; [Viewer](#see-every-decision) &nbsp;·&nbsp; [How it works](#how-it-works) &nbsp;·&nbsp; [Benchmarks](#benchmarks) &nbsp;·&nbsp; [Build an adapter](#build-your-own-adapter) &nbsp;·&nbsp; [Contributing](#contributing)

• opencode-jev-guard

  CogFlux · Security & Guardrails

  When FarHand is active, the agent's commands run on a remote host through the `farhand_remote_shell` MCP tool instead of `shell`. OpenCode's permission request for an MCP tool carries no arguments, so the plugin takes the command (and its `cwd`) from the `execute.before` hook, which OpenCode runs first.

• jev-bot

  bl888m · Domain Tools

  JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default

• dsh-jev-decide

  nanami-0713 · SDK & Decision Frameworks

  This DSH plugin registers TypeSafe Jev as an Agent tool that returns calibrated probabilities for noul, choice, and score judgments without generating text.

• jevTrader

  Nachom3 · High-Frequency / Games

  A High Frecuncy Trader made in Rust using Jev as a decision maker.

• jev-pilot

  Akramovic1 · Model Routing

  Let Jev steer Claude Code: the right reasoning effort, subagent model and skill for every prompt. A Claude Code plugin powered by TypeSafe's Jev (OpenRouter / TypeSafe).

• jev-numeric

  Bring-AI · SDK & Decision Frameworks

  **Both are multiway decision trees; decimal-digit decoding is a ten-way instance.** On an aligned decimal grid, they can have identical branches and leaves, expressed through different prompts. The digit is a **Choice option**, not a vocabulary token; Jev returns the option probabilities directly.

• jev-inbox-queue

  tusharck · Context GC

  Turn an inbox into a short action queue with Jev (TypeSafe System One)

• playwright-jev

  dingw530 · Browser & OS Action

  This tool provides a Node CLI for goal-driven web E2E testing where Jev chooses the next step from a code-generated action space, playwright-cli observes and executes browser actions, and code controls inputs, deterministic assertions, and the final verdict.

• ego-jev

  flazouh · Browser & OS Action

  Drive ego-browser pages with TypeSafe Jev: code builds the allowed actions, Jev picks one, code acts and re-checks.

• jev-xiangqi

  Zafer-Liu · Domain Tools

  Play Chinese Chess (Xiangqi) against Jev - TypeSafe System One decision model as the AI. Score fan-out over legal moves.

• jev-claim-vs-measured

  Siim · High-Frequency / Games

  A post with ~400k views says TypeSafe's **Jev** is the fastest AI model ever built for trading, makes calibrated buy/sell decisions in under 100 ms, and shows how to build an HFT system on it. The article behind it contains no backtest, no P&L and no hit rate. So I ran the tests: on the raw tape at one decision per second, and at 15–60 minute horizons. It cost **$0.97** of API credit. Everything needed to check me is in this repository.

• jeves-desk

  dabaicai001 · Domain Tools

  This repository implements a configurable customer-service platform combining ChatKit UI, Jev decision-making, generative chat, RAG knowledge lookup, plugin Tools, MCP data access, and YAML-driven Agent dispatch.

• WindowsJev

  Teylersf · Browser & OS Action

  Token-efficient Windows automation and durable research MCP server for Codex and Claude Code, powered by TypeSafe Jev.

• jev-mcp-open-source

  baize7815 · MCP & Integrations

  Self-hosted Jev MCP on Cloudflare Workers with intent routing, retrieval reranking and batch judgments

• codex-jev-router

  suenot · Model Routing

  Portable JevRouter setup for cost-aware Codex subagent model selection, with English and Russian instructions

• momus-review

  brianluby · Security & Guardrails

  Code review on rust and javascript (+languages soon) applications. Following lenses correctness, security, reliability, compatibility and testGap.

• JevPulse

  jaygajera17 · Domain Tools

  Analyze the YouTube comments to gain insights into what the audience is saying from any video link.

• jebadiah

  getainode · SDK & Decision Frameworks

  Jebadiah, an open System One decision model: trainer, data builders, evals and every run record

• cube-lab

  ngocvychu38-web · Domain Tools

  Cube Lab is an interactive 3D Rubik's Cube app that generates candidate solutions with local planners and uses Jev to select moves across seven solving stages with animations and recorded turning sounds.

• jev

  feder-cr · SDK & Decision Frameworks

  jevos is an open-source, Jev-compatible alternative to TypeSafe's Jev for yes/no decisions that runs entirely on a laptop CPU. Send text plus a yes/no question over HTTP and get back P(yes) from a single forward pass of a 1B model — no text generation, no GPU required.

• sieve

  nothans · Data & Search

  Sieve checks a folder of Markdown notes against itself. Crosscheck compares every note with every other, from both sides, and lists the pairs that contradict each other, the pairs that make the same point twice, and the notes that have gone stale. It also ranks the whole folder by any plain-English question, and lints notes against plain-English rules in CI. No index, no embeddings, no generated text. Node, no dependencies.

• jev-engineering

  eugeniughelbur · Security & Guardrails

  A Claude Code tool-call gate. Clearly safe commands run with no permission prompt, clearly dangerous ones are blocked with the reason, and unclear ones get the normal prompt. Also ships review-router, a GitHub Action that routes AI code review to a full or quick read. Disclosure: I built and maintain it.

• building-with-typesafe-jev

  aaddrick · Security & Guardrails

  Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

• jev-pokemon

  christianmat · CLI & Pipelines

  Jev, an AI decision model, plays Pokémon Red. It beat the game in 37h 40m.

• jev-rules

  EliaAlberti · CLI & Pipelines

  **New in 0.5.0:** [one line under each prompt](#in-the-conversation) names the rules Claude was given and Jev's score for each, and the [rules pane](#the-rules-pane) switches on with one answer: the first time Jev picks a rule, Claude asks whether you want it.

• jev-browse

  danielnc · CLI & Pipelines

  Fast, cheap browser sub-tasks for Claude and other agents: TypeSafe Jev decisions on top of browser-harness

• jev-apply

  TheAdaply · Decision Tools

  In Codex, Claude Code, or another CLI agent:

• OneJev

  OmniJev · CLI & Pipelines

  🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass.

• jev-baselines-eval

  ickma2311 · Security & Guardrails

  Every latency number here is **wall-clock duration of one API call** measured in the client: a timestamp before the request, another after the full response body is read ([`code/run_b1.py:32`](code/run_b1.py), [`code/common.py:50`](code/common.py)). Non-streaming on both sides, so these are completion times, not time-to-first-token.

• openjev

  darwintechlab · Domain Tools

  OpenJev: An Opencode plugin that replaces text-generation decisions with Jev (TypeSafe System One).

• jev-demo

  kiler398 · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-rag

  aifabrice · Data & Search

  Local knowledge search with three modes: BM25 + Jev by default, agentic multi-query lexical search + Jev without vectors, and optional BM25 + embeddings/RRF + Jev, with grounded streaming answers.

• jev-tab-grouper

  AstonyCat · Domain Tools

  One-click AI tab grouping for Chrome — Jev typed decisions (~1s, whole window) or any OpenAI-compatible LLM that invents its own group names. Featured in awesome-jev.

• jev-riffs

  hazlema · Creative Tools

  Music pattern ripper: MIDI → interval tokens → code mines candidate motifs → Jev (TypeSafe System One) grades their significance. Web UI with piano roll, click-to-play, WAV export.

• Jev-PhoneControl

  ZTRRTUO · SDK & Decision Frameworks

  Visual Android automation powered by three agents: vision, a text-only supervisor, and TypeSafe JEV. Executes actions through ADB with a local web console.

• Jevstiller

  tomerglick57 · Domain Tools

  Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

• astra-jev-harness

  Oranquelui · Decision Tools

  The default `batch` policy retains an entire batch when any judgment is uncertain. The experimental `select --policy per-file` retains uncertain/unjudged files while omitting confidently irrelevant siblings. Dependencies and the global no-match fallback still apply. Compare before changing policy; fewer bytes alone do not establish correctness.

• jevlint

  Fox-Islam · Domain Tools

  A linting tool combining static analysis and Jev queries to help improve... Jev queries

• hermes-jev

  DoGMaTiiC · CLI & Pipelines

  Hermes Agent plugin: route each turn to the one skill that fits, via TypeSafe Jev on the Vercel AI Gateway. Fail-open, opt-in, stdlib only.

• voicevox-jev-proxy

  nemalabs · Creative Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-qa-demos

  gauravkhuraana · CLI & Pipelines

  Demos for the video "Jev explained for testers": TypeSafe AI's System One model, called through **Vercel AI Gateway** with the AI SDK's `experimental_evaluate`.

• jeverifier

  silvariasereneblossom · Context GC

  JeVerifier: cheap Jev (TypeSafe) checks that keep code maintainable and docs consistent, plus context retrieval — modest token savings

• jev-reviews

  halfspin-qc · Data & Search

  The flagship experiment in this workspace is **`jev-reviews`**: an automated pipeline that ingests Google Maps restaurant reviews from **Apify Storage**, stores and deduplicates them in **Supabase PostgreSQL**, and classifies them using **Jev (TypeSafe System One)** or traditional generative LLMs across 5 operational pillars, extracting dishes, customer highlights, and owner recommendations.

• jev-mcp

  codaaiteam · MCP & Integrations

  MCP server for Jev (TypeSafe AI's System One model) — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com

• jev-doom

  olivier-motium · SDK & Decision Frameworks

  Watch Jev play Freedoom in a local dashboard. TypeSafe direct and Vercel AI Gateway, inspectable decisions, and bounded spending.

• jev-playwright-mcp

  krw82 · MCP & Integrations

  Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

• jev-windows-agent

  VBS2004 · Creative Tools

  Windows UI Automation extension of arc-cua: a fast, JEV-powered decision loop for desktop computer-use agents

• jevskill

  lazniak · Context GC

  Teach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.

• jev-playground

  wustep · Creative Tools

  Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI.

• jev-claude-router

  Flam1ngFir3ball · Model Routing

  Model router for Claude Code using Jev

• jevtok-ts

  aarzhaev · Data & Search

  **No Python, network calls, API keys, native extensions, or runtime dependencies.** Vocabulary and lookup tables ship inside the package. Ordinary `o200k_base` tokenization is not interchangeable with Jev: `evidence` is three tokens and `2024` is four.

• jevgrep

  dzhng · Code Navigation

  Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context with exact excerpts and line numbers.

• jev-opus

  WXK-AI · Model Routing

  Claude Opus 5.5 with the effort level re-decided every step by the TypeSafe Jev reflex — without breaking the prompt cache. CLI + Claude Code plugin.

• usejev

  ali-master · SDK & Decision Frameworks

  Run Laya locally with Bun: native ONNX inference, a TypeSafe-compatible API, and a bilingual decision playground.

• jev-fuse

  0xshikhar · Domain Tools

  A governed execution layer between typed-decision models (TypeSafe Jev) and agent/AI tooling like Claude Code, MCP, and AI SDKs, turning probabilistic decisions into deterministic, policy-controlled, and auditable actions.

• jev-agent-tools

  jkudish · CLI & Pipelines

  Jev transport/provider layer: multi-provider transport layer that supports fail-closed validation. Used by jkudish/jev-browser and jkudish/jev-mcp.

• Jev_Onco_Statistical_Hierarchy

  SampleBias · CLI & Pipelines

  New prepares use `molecular-origin-v6`. The Choice, the two gated checks, and five boundary checks share the evidence and cannot read each other's answers. Boundary answers are reported with the result. Gates still use the leading score, its margin, sufficiency, and conflict. The parent of the leading class is a local lookup on the taxonomy. A request may use Jev's window: 64k tokens for the call, and 32k for the evidence plus the longest question.

• Jev-Persian-Benchmark

  ArmanJR · SDK & Decision Frameworks

  Benchmarks for **Jev** on **480 authored general Persian questions** and a **24-excerpt classical Persian poetry pilot** (48 main questions plus 48 controls). Related general questions are batched; poetry questions run individually. Raw responses are saved and answers are scored locally, without a runtime model judge. The general benchmark's historical Laya comparison is retained below.

• claude-jev-funnel

  Shakibuzzaman3104 · CLI & Pipelines

  Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.

• jev-phone

  Rajmeet · SDK & Decision Frameworks

  Drive a phone with a model that never writes a word. TypeSafe's Jev picks each action, phone-use runs it on iOS and Android.

• jev-router

  dirien · Model Routing

  Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model

• hermes-jev

  ourines · Model Routing

  Jev decision sidekick for Hermes Agent — TypeSafe and Cloudflare, explicit tools and official skill

• jev

  anilsenay · SDK & Decision Frameworks

  Unofficial Go client for TypeSafe's System One API and its model, Jev.

• jev-intent-classification

  viniciusfinger · Domain Tools

  JEV intent classification using Python

• here-we-go-jev

  creativoma · CLI & Pipelines

  The smoke test and the experiments call real APIs and cost a fraction of a cent per run. The experiments need the server running.

• fake-real-jev

  DansiDanutz · Decision Tools

  See link entry, the live scan timer, JEV's evidence-checking role, a saved REAL example, a saved FAKE example, and the linked sources. The live documentation scan shown ended without a verdict; its credit was returned. The coffee reports are clearly labeled saved examples, with their original analysis times.

• fuzzy-jev

  dsaad68 · CLI & Pipelines

  Ask Jev typed questions about text and get calibrated probabilities back, then turn them into decisions with fuzzy rules (AND, OR, NOT, hedges, Mamdani outputs) and draw the rule base as SVG. A CLI and a Rust library (native and wasm32).

• jev-route

  huzeyfe07 · CLI & Pipelines

  Async, typed intent & tool routing for Python agents: Jev decides, a confidence gate stops weak decisions before they reach a privileged tool.

• JudgeJev

  shyamsridhar123 · Model Routing

  The public site replays **17 real, recorded Jev evaluations** of fictional support cases. It starts with a false shipping guarantee that scored **15.1%**, alongside a correct control that scored **95.5%**. You can inspect raw requests and responses, adjust decision rules, and see why a five-pair candidate fails a release gate.

• jev-tool-search

  kachar · MCP & Integrations

  Tool search for LLM agents: BM25 vs embeddings vs rerankers vs Jev on 525 real MCP tools, plus an experimental Jev search engine

• jev-crawlers

  russfranky · Decision Tools

  Jev learns your repo's decision norms, then adversarially judges past decisions against them. Unix-style primitives (seed, expand, judge, verify, report, norms) with per-node typed judgments from typesafe-ai/jev.

• JevCode

  coasty-ai · Decision Tools

  JevCode - Jev can code. We want to dogfood JevCode

• openjev

  lookski · CLI & Pipelines

  Turn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.

• pi-Jev-browser

  laihenyi · Browser & OS Action

  Browser and macOS desktop agent for pi: Jev (TypeSafe System One) chooses each action from a structured observation in a bounded, surface-agnostic loop. Isolated Playwright tools, an allow-listed accessibility-tree tool, deterministic selectors, four-tier benchmarks.

• jev-resume-screening

  nanami-0713 · Domain Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• r2r-jev

  Thneoly · CLI & Pipelines

  Jev turns unstructured state into typed probabilistic decisions. Evidence Admission decides which observations are eligible to enter governance. R2R turns admitted evidence and events into persistent, replayable relation state.

• hermes-jev-router

  punkcanyang · Model Routing

  Hermes Agent plugin: TypeSafe Jev model routing + trim-then-compress

• jev-test

  cgbarlow · Security & Guardrails

  Prototype: AI-assisted NZQA marking from rubric criteria alone, using TypeSafe Jev for guardrails, criterion scores and confidence-based triage. NOT ENDORSED BY NZQA - CONCEPT ONLY

• jev-harness

  PromtEngineer · Data & Search

  A Pi agent harness built around TypeSafe's Jev (System One model): router, context picker, gate, verifier. Tested on Neon Postgres branches.

• jev-triage

  CMaintz · Domain Tools

  Near-free GitHub issue triage powered by TypeSafe AI's Jev - typed, confidence-gated labels that escalate only the uncertain cases.

• jev_projects

  X0EF · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-linter-action

  sable-inc · Decision Tools

  `glob` accepts one pattern or a newline-separated list. All matched files are reviewed together by default; `per-file: true` reviews each file independently. Missing inputs, malformed questions and ambiguous combinations fail before calls.

• jev-swap

  0xjba · SDK & Decision Frameworks

  Find the LLM calls in your codebase that are really decisions, see what they'd save on TypeSafe Jev, and prove it on live traffic before you swap. TypeScript, JavaScript, Python.

• jev-stock-decision-maker

  0xZee · Domain Tools

  JEV Decision is a live demo that turns market data into structured decisions. It pulls real-time prices, valuation ratios and sector context, then runs a 20-question against TypeSafe Jev model to score buy/sell conviction, financial health and risk

• jev-no-enem

  patryckalves · Decision Tools

  Reproducible benchmark evaluating TypeSafe AI's Jev (System One paradigm) on Brazil's ENEM 2025 standardized exam. Evaluates typed decision-making, domain-specific accuracy, and RLCD uncertainty calibration against open LLM baselines with an interactive GitHub Pages dashboard.

• omp-plugin-jev-router

  atulify · Model Routing

  Route Oh My Pi prompts between simple and advanced models with TypeSafe AI's Jev classifier.

• jev-triage

  ashafizullah · SDK & Decision Frameworks

  Automated issue & PR triage for open-source maintainers, powered by Jev (TypeSafe AI).

• JevDeepResearch

  sunyasheng · Data & Search

  GPT directs the research; Jev uses Choice and Noul to locate evidence across document regions concurrently, and code returns original passages for GPT to verify and continue. The released integration pairs Pi-Serini BM25 search with Jev batches of 20, 40, or 60 documents.

• hey-jev

  henryklunaris · CLI & Pipelines

  Open, quit, hide, minimise or switch to apps, open a new browser tab or a website ("open youtube.com in Brave"), Mac volume up / down / mute / set, Spotify volume, play / pause / next / previous, dark mode, lock or sleep the Mac. Two things in one sentence work too: "pause Spotify and open Slack".

• jevlint

  Ice-Hazymoon · Domain Tools

  Semantic lint rules for the code-review questions a deterministic linter can't express

• jev-anything

  grandamenium · Domain Tools

  Agent skill for designing, building, testing, and tuning bounded JEV decision layers

• jev-safety-gateway

  dark-hxx · Security & Guardrails

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• pi-jev-model-router

  da-vinci-noob · CLI & Pipelines

  Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback.

• JevFlow

  Parth1811 · Domain Tools

  A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

• Jev-chat-assistant

  QCJLchina · Decision Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• tryjev

  sugarforever · CLI & Pipelines

  A playground for Jev, TypeSafe AI's fast decision model: preset scenarios on the left, an editable state plus typed questions in the middle, typed answers with probabilities on the right. Bring your own key and pick a provider: OpenRouter (`typesafe/jev-1.13`, `alpha.decisions`), Vercel AI Gateway (`typesafe-ai/jev`, AI SDK `experimental_evaluate`) or TypeSafe's own API (`jev-latest`, `POST /v1/systemone`).

• Jev-Model-Router-Claude-Code

  AlexPEClub · Model Routing

  Begleitmaterial zum Video „Jev + Claude Code: 3 Use Cases".

• dsh-jev

  noetion · Decision Tools

  DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers.

• jev-demos

  DataGobes · Decision Tools

  Every demo lives in its own folder with its own README, dependencies and instructions. Most run without an API key in a clearly labelled `SIMULATED` mode; put `TYPESAFE_API_KEY=...` in the demo folder's `.env` for live results.

• Jev-AI-Skill

  King4s · MCP & Integrations

  One AI skill + MCP server for Claude Code, Codex and Hermes: Jev (TypeSafe) gates large-model turns (event triage, review verdicts, owner questions, tool choice), runs build-and-repair loops with independent review, routes models and skills, and guards Git steps. Script-only watch mode and a shared HTTP server.

• jev_fsd

  BrendanH18 · High-Frequency / Games

  **An AI model drives a car through a real city, and you can watch every decision it makes.**

• jev-risk-check-provider

  caiovicentino · Security & Guardrails

  x402check — LIVE payer-intent risk checks for x402 agent commerce: typed decisions (TypeSafe Jev), ES256-signed attestations, mainnet USDC settlement. did:web:x402check.xyz

• jev-oncall

  mingleiw · Domain Tools

  Incident triage on TypeSafe Jev — the model judges, plain code decides. Routing on probability distributions with a human-review middle band and fail-open defaults.

• jev

  drpaneas · Creative Tools

  Constructors build reusable questions locally. `Ask` calls Jev; `Resolve` applies your confidence threshold locally. Choose thresholds using your own evaluation data.

• jevcut

  VBS2004 · CLI & Pipelines

  Auto-clipper that turns long videos (podcasts, talks, essays, comedy) into short standalone clips for Shorts, Reels and TikTok. Code lists every possible cut; an AI judge picks where each clip starts and ends. Benchmarked on 38 hand-labelled videos.

• codex-jev-native-router

  itscloud0 · Model Routing

  Experimental native Codex Desktop and CLI model routing with Jev and a configurable allowlist

• toolJev

  VishiATChoudhary · MCP & Integrations

  Code Mode for MCP, where the sub-model is a calibrated decision model (Jev), not an LLM. Benchmarked on MCPToolBench++, LiveMCPBench, When2Call and live Claude agents.

• xjevboost

  sedthh · Decision Tools

  Add as much tabular data as you want to Jev models using adaptive ensembles that learn to query only the rows and columns needed.

• JevLang

  TimMikeladze · Domain Tools

  A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.

• typesafe-jev-decision-studio

  Romain-Jochum · High-Frequency / Games

  Fast, calibrated System One decision platform powered by TypeSafe Jev via OpenRouter. Sub-second logprob scoring, transfer curves, zero hallucinations.

• jev-arena

  Eliot5566 · CLI & Pipelines

  That's the whole bot. No code, no coordinates, no if-statements.

• jevextract

  gabazureus · Domain Tools

  Grounded information extraction that cannot hallucinate: code proposes spans, Jev decides. An open-source alternative to LangExtract, with a bilingual benchmark and paper.

• jevmod

  ohernandezdev · MCP & Integrations

  Moderation for communities and apps: every message gets a probability for **spam, scam, harassment, nsfw, off-topic, self-harm, doxxing, sexual content involving minors**, and for **rules you write in plain English**. You set the thresholds and the actions. Every decision is logged with its numbers.

• jev-skill

  marcodicesare-dev · CLI & Pipelines

  Jev skill for Claude Code and Codex: TypeSafe System One guide, Python CLI, 5 tested recipes, and findings from 19,367 Jev calls.

• cursor-clijev-compaction

  kleosr · CLI & Pipelines

  TypeSafe Jev-scored context recovery for Cursor CLI (agent). Capture tool I/O, score keep/drop, re-inject after native compact.

• jev-mcp

  Afloat16 · MCP & Integrations

  `jev-mcp` exposes TypeSafe AI's Jev decision model as four conservative, read-only MCP tools for **bounded probabilistic decisions**.

• jev-switch

  ARCJ137442 · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-kiyafet-bul

  selmakcby · CLI & Pipelines

  Kod yerleri: `lib/filtre.ts` (Adım 1), `lib/regex.ts`, `lib/daralt.ts`, `lib/sirala.ts` (Adım 2 + sıralama), `lib/ara.ts` (hat), `lib/jev.ts` (istemci), `lib/kota.ts`, `app/api/ara/route.ts`, `components/` (arayüz).

• Codex-Jev

  PhilippElhaus · CLI & Pipelines

  VS Code Codex Plugin for Jev-gated tool output integration

• jev-humanizer

  snjrusmn · Domain Tools

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• 1-million-emojis

  cwdx · Creative Tools

  A shared 1000 × 1000 emoji canvas where humans paint and Jev paints alongside them: after each stroke, one Jev request chooses which emoji goes next to it and where, from typed options named against the stroke, and says whether the stroke is an unfinished shape.

• jev-visual

  hr98w · SDK & Decision Frameworks

  Local Jev-like visual inference experiment on Apple Silicon Mac. Scores and classifies single images across multiple questions with 3 playable game demos.

• harness-router

  Protocol-Lattice · MCP & Integrations

  Fast decision routing for agent harnesses — native MCP with Jev for tool selection and MCTS for multi-step decisions.

• laya-browser-guard

  pateti-hub · Security & Guardrails

  A passive, privacy-first Chrome security copilot that combines deterministic browser-visible checks with local Laya and official Jev typed decisions. It evaluates redacted evidence from scripts, resources, forms, headers, and DOM signals, then explains investigation priority without attacking the target.

• jev-cc-codex-router

  peterwanghot · Model Routing

  Per-turn model routing proxy for Codex: asks Jev which tier each task needs, rewrites the model, retries flaky upstream errors.

• sedum

  sedum-dev · Browser & OS Action

  Plain-English browser e2e tests cheap enough to run on every PR. Built on Jev and Playwright, open source, bring your own key.

• jev-playwright

  arthurfiorette · Browser & OS Action

  Shrinks Playwright suites in CI by letting Jev select tests related to code diffs.

• jev-book-tags

  iamjonatha · Decision Tools

  A free calibre plugin that suggests genre and subject tags for individual books, selected books or an entire library, with configurable thresholds and review controls.

• cribrix

  david96182 · Model Routing

  Self-hosted RAG service that uses Jev to decide which retrieved context reaches the generator and whether the generated answer is released.

• medula

  JoaquinRuiz · Security & Guardrails

  Suggesting Médula for the coding-agents domain. I'm the author.

• jevlint

  codegirl-007 · Domain Tools

  A linter to codify code taste using Jev

• pijev

  TypeLLM · SDK & Decision Frameworks

  pijev turns Jev's option-order variations into a single averaged prediction, with Brier score and log loss guaranteed no worse than the average across the included orderings. All permutations run in one `system_one` request. Keep the same calls and official response types; pijev handles the rest.

• jevcache

  kushals256 · CLI & Pipelines

  MorrowCache — skip the chat call when the question is the same. OpenAI-compatible proxy. npm: @kushalicious/jevcache

• xscout-jev

  ethan-ab · CLI & Pipelines

  xscout works for fields that are active on X: tech, AI, developer tools, crypto, finance, media, politics. Some markets barely post there; `validate --online` tells you early when most of the accounts you care about are missing or quiet.

• jevia

  assistant-ui · Model Routing

  outcome-aware & adaptive model routing for coding agents with deterministic cache powered by Jev

• opencode-jev-router

  robertn702 · Model Routing

  Adaptive reasoning effort for OpenCode via Jev, with an in-process plugin and Responses API proxy

• spending-effort-with-jev

  Yaxin9Luo · Decision Tools

  Jev-powered /effort advisor for Claude Code: tells you when to switch effort, per prompt

• jev-span

  lzq-0529 · Domain Tools

  Jev answers typed multiple-choice questions with calibrated probabilities, but it never returns entity spans on its own. **JevSpan turns it into an entity recognizer.** It cuts text at punctuation, offers every candidate window to Jev as an option, verifies what Jev nominates, and then lets Jev settle the exact boundaries and type. Every entity comes back with a probability and a trace of the questions that produced it.

• Jev-Desktop

  jacks3tr · CLI & Pipelines

  Jev Desktop lets AI agents use Windows applications through MCP or the command line. Hand off a task and let Jev observe windows, choose controls, type supplied text, and navigate locally. Your agent gets the result or a request for help instead of handling every click.

• dsh-jev-prune

  yangyu666 · Domain Tools

  Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

• jev-lens

  sahajamit · Domain Tools

  No scripted rules, no keyword lists, no cloud account of ours. Your API key, your profile, your browser.

• jev-handson

  jkf87 · CLI & Pipelines

  Jev 특강 실습 코드(1~3강): TypeSafe Jev를 Claude Code·Codex·OpenClaw에 붙이는 스킬·훅·라우터·활용 예제

• jev-php

  f-lombardo · CLI & Pipelines

  `ScoreAnswer::score` is a probability-weighted numeric score across the provided levels.

• jev-chat-gate

  pandore · Decision Tools

  A framework-independent participation gate for AI agents in group chats, powered by typed Jev decisions.

• JevTrace

  123wwwa · MCP & Integrations

  An MCP server that cuts coding-agent token usage by retrieving only the relevant JS/TS code using the TypeScript compiler and Jev.

• jev-nethack

  statico · Decision Tools

  TypeSafe's Jev model plays NetHack 5.0: code lists the legal moves, Jev picks one, no LLM in the loop

• jev-tools

  NomenAK · CLI & Pipelines

  Six evidence-oriented tools for pi and omp coding agents, compatible with the Jev API format.

• RSI-Jev-Slay-the-Spire-2

  yzxoi · SDK & Decision Frameworks

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-py-integration

  EmiRoberti77 · Domain Tools

  Jev System one AI model, very fast decision making engine. Jev AI will use input tokens but no output tokens

• jev-clean

  Kunyanli230 · Domain Tools

  decision-first data cleaning system powered by Jev

• Hinge-Jev

  satiricalguru · Domain Tools

  🎯 A Jev-powered decision engine and visual studio that prices uncertainty and asks the question that matters.

• jevtest

  Just-Betr · Browser & OS Action

  Plain-English end-to-end tests for Android and iOS apps, driven by TypeSafe's Jev. Deterministic, strict, CI-ready.

• JevScout

  yctimlin · MCP & Integrations

  Jev decides what reaches your coding agent: verbatim, recoverable context for Claude Code and reviewed operations for Codex. npm i -g jevscout

• claude-jev

  darwintechlab · Domain Tools

  Jev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API (mirror of opencode-openjev, live-only MCP)

• jev-mcp

  legostin · MCP & Integrations

  MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV (TypeSafe System One): ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace.

• jev-deep-dive

  LouisUltra · Domain Tools

  Start with a mismatch everyone has felt: chat models surpassed average humans at conversation years ago. So where is the automation? The launch post opens with exactly this question (M1).

• jevault

  taichocop · CLI & Pipelines

  Jevault suggests existing destination folders. You can explicitly select a suggestion and confirm a manual move of the classified note. Jevault never moves notes automatically.

• jev-prompt-enhancer

  joacotornello · Code Navigation

  Enhance your prompts using Jev by giving your coding agent a clearer task before it writes the first line.

• jev-local

  tapsin · CLI & Pipelines

  JEV-Local: System-1 decision engine for local LLMs. Mimics TypefAI JEV: structured choices only, no chatter, calibrated confidence. Works with Ollama, vLLM, llama.cpp, LM Studio.

• jev-charactor

  YichenBC · High-Frequency / Games

  Jev-Character: a TypeScript core for role-playing agents, autonomous game NPCs and AI towns. Agent memory, natural-language behavior authoring and programmatic dialogue, with a playable 2D multi-agent simulation.

• jev-tetris

  pinebit · High-Frequency / Games

  Tetris that plays itself: TypeSafe's Jev model picks every placement with one typed Choice call, with live probabilities, latency, and cost.

• pi-jev-eye

  bismawy · Security & Guardrails

  Ultra-lean supervisor for Pi: zero-token regex guardrails, test verification tracking, and TypeSafe Jev semantic slop gate.

• Codex_ChatGPT_JEV_Switch

  FlyPig23 · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-for-splunk

  sispehar · CLI & Pipelines

  Splunk app: the | jev search command asks TypeSafe Jev typed questions about your events and adds calibrated probabilities, choices and scores as fields, cached in the KV store.

• Jevometry

  Kunyanli230 · CLI & Pipelines

  an Information-Geometric Analysis Toolkit for any System-one (Jev, Jevlike) agent systems

• android-jev

  FZ2000 · MCP & Integrations

  Whichever way it reaches the server, the key never appears in a state, a log, a run folder or a transcript.

• jev-esketcher

  Faizullah9181 · Creative Tools

  Generative painting canvas where Jev, TypeSafe's calibrated decision model, picks paint materials and colour palettes for 105 procedural sketches. FastAPI + React + TypeScript.

• jev-codex-factory

  VyetGokyra · Model Routing

  Route smarter. Code in parallel. Resume what breaks. A Jev-powered multi-agent factory for Codex.

• typesafe-jev-playground

  saimahmedqazi · Domain Tools

  A BYOK playground for practicing TypeSafe's Jev — the first System One model — with your own LLM or native Jev API access. Experiment with Noul, Score, Choice, custom state, and structured decisions.

• jevkit

  MaxIvanyshen · CLI & Pipelines

  Self-hosted Jev (TypeSafe) tools for coding agents: /ask classification and /review diff triage, with CLIs, agent skills, and a Pi tool

• BizzJev

  havietkok-sys · Domain Tools

  The system detects all of them at once. Several signals may be present simultaneously; there is no winner-takes-all classification.

• github-star-classifier-jev

  mrkpatchaa · CLI & Pipelines

  Classify your GitHub stars into GitHub Lists with TypeSafe Jev, and review stars worth dropping

• jev-demo

  harsha89 · Decision Tools

  Showcase of TypeSafe JEV classifying emails: spam (noul), category (choice) and urgency (score) - Next.js + MUI app and Python script

• jev-gate

  adamwdff · CLI & Pipelines

  This project integrates Jev to provide structured decisions for its workflow. See the repository for implementation details.

• jev-netlify-mcp

  demircigoksu · MCP & Integrations

  Free, key-locked TypeSafe Jev via Netlify AI Gateway, plus an MCP server for Claude Code, Codex and Claude Desktop

• jev-buzzword-rush

  pochang6 · CLI & Pipelines

  A 25-second IT buzzword game to feel how fast and cheap Jev (TypeSafe System One) is — code + Jev only, no LLM.

• el-jev

  vijaycinn · Data & Search

  High-speed System One decision sidecar & Copilot CLI pre-turn hook powered by Azure AI Foundry Cohere with keyless Entra ID auth.

• jev-testbench

  Charlie-Wang-03 · Domain Tools

  `jev-testbench` is a lightweight Jev testbench built through **Agentic Engineering**.

• WaterSheep

  SamratDuttaOfficial · SDK & Decision Frameworks

  Open-weight Jev alternative that serves /v1/systemone locally, with calibrated Noul, Choice, Score and multi-label answers.

• jev4pg

  Sheltercosmo · Data & Search

  Semantic querying and gate decisions in PostgreSQL powered by Jev Noul predicates.

• FlightBench

  AlperKartkaya · High-Frequency / Games

  Fixed-wing aircraft landing simulator and benchmark where Jev Choice outputs actuator commands.

• mu

  qybaihe · Model Routing

  A coding agent built on pi and AionUi whose routine calls at 38 decision points are made by Jev.

• reticle

  reticlehq · Evaluation & Observability

  An end-to-end runtime perception and verification framework for coding agents that drives real apps and supports Jev as the harness driver for non-generative assertions.

• mcp-router

  Amantux · MCP & Integrations

  An open-source, Jev-based MCP router that catalogs, deduplicates, and dynamically filters tools using single-pass System One decisions.

• jev-home-assistant-sentinel

  bojansandhaus · Security & Guardrails

  A safety boundary for AI-assisted Home Assistant decisions, pairing explicit policy checks with chained Jev decision adapters.

• kairos

  kyaulabs · Domain Tools

  An experimental Python trading bot for Kraken and Alpaca combining Jev-assisted strategy decisions with deterministic risk controls.

• skillranker

  Dicklesworthstone · CLI & Pipelines

  A standalone Rust CLI powered by TypeSafe Jev that ranks agent skills for the next step using live session context, with local safeguards and feedback.

• fastbrowse

  agent-labs-dev · Browser & OS Action

  A fast browser agent: Jev picks each action from DOM elements on the page, an LLM plans, and claims cite verifiable page quotes.

• jevmem

  Avinash-jetwani · Context GC

  A Claude Code memory manager that uses Jev to filter decisions and rules from chat history into durable, per-repo memory.

• jev-chat-jarvis-mac

  jev-chat · CLI & Pipelines · Integration · Jev implementation · Implementation and descriptive material

  macOS chat overlay copilot that reads the current conversation and calls Jev to judge intent, risk, and reply suggestions.

• decide

  gopaljigaur · SDK & Decision Frameworks · Integration · Jev implementation · Implementation material

  pydecide is a Python client that calls Jev's /v1/systemone endpoint via TypeSafeBackend for typed decisions.

• phocinae-server

  Phocinae · SDK & Decision Frameworks · Integration · Jev implementation · Implementation material

  Local inference server implementing the TypeSafe System One wire format with /v1/systemone endpoints returning per-option probabilities.

• jev-chat-jarvis

  jev-chat · Voice & Conversation · Integration · Jev implementation · Implementation and descriptive material

  Android chat copilot that reads conversations, uses Jev to assess intent, risk, and next actions, and drafts and ranks reply suggestions.

• jev-chat-jarvis-ios

  jev-chat · Voice & Conversation · Integration · Jev implementation · Implementation and descriptive material

  iOS keyboard chat copilot that analyzes copied messages with Jev for intent classification, risk scoring, and reply ranking.

• Situation-Puzzle

  ZeroTang05 · Domain Tools · Integration · Jev implementation · Implementation material

  Turtle-soup puzzle game whose code implements a JevClient calling Jev to judge player questions and solutions, with real end-to-end tests.

• VideoAdGuard

  ZeroTang05 · Browser & OS Action · Integration · Jev implementation · Implementation and descriptive material

  Browser extension calling the Jev decision model to detect and mark ad segments in Bilibili videos for skipping.

• jev-measured

  WallerChen · Evaluation & Observability · Benchmark · Jev implementation · Implementation material

  Measured cost, latency and accuracy of the live Jev API across 12 use cases with multi-model comparison.

• decision-models-as-guardrails

  raxITlabs · Evaluation & Observability · Benchmark · Jev implementation · Implementation material

  Open benchmark evaluating 19 systems including Jev on 9,975 guardrail checks for balanced accuracy and cost.