보안 및 콘텐츠 검토

68 · 각 항목의 검토 근거를 확인하세요. 수록은 독립적인 실행 검증을 뜻하지 않습니다.

• safer-with-jev

  andrelandgraf · 보안 및 콘텐츠 검토

  Jev로 본문을 검사하고 조건을 충족하면 HTTPS 대상에 전달하는 게이트웨이.

• pi-jev

  y0usaf · 보안 및 콘텐츠 검토

  Pi 도구 실행 전 위험을 알리고 실행 후 비밀 정보와 오류 유형을 확인하는 확장.

• pi-jev-auto-mode

  jomatsu · 보안 및 콘텐츠 검토

  Pi의 명령과 파일 작업을 규칙으로 확인한 뒤 추가 판단이 필요한 작업을 Jev가 평가한다.

• jev-judgment

  HyunjunJeon · 보안 및 콘텐츠 검토

  코딩 Agent에 권한, 작업 위험, 실패 원인 판단을 추가한다.

• jev-guard

  leepokai · 보안 및 콘텐츠 검토

  코딩 Agent의 도구 호출에서 동작 위험·사용자 의도·프롬프트 주입 징후를 검사한다.

• hermes-jev-approvals

  anpicasso · 보안 및 콘텐츠 검토

  Hermes의 auxiliary.approval만 대체하는 실험적 명령 승인 플러그인.

• jev-tool-permissions

  NicolasMontone · 보안 및 콘텐츠 검토

  Vercel AI SDK에 도구 호출 승인과 도구 목록 필터링을 추가한다.

• agentgateway

  agentgateway · 보안 및 콘텐츠 검토

  webhook으로 모델 요청·응답을 점검하는 Agentgateway의 Jev 가드레일 예제.

• interlinked-cli

  QuentinCody · 보안 및 콘텐츠 검토

  Interlinked는 로컬 코딩 Agent 검사에 선택형 Jev 판단과 근거 확인을 더한다.

• pi-warden

  DevMortimer · 보안 및 콘텐츠 검토

  Pi Agent에 프로젝트 규칙, 범위 밖 작업, 반복 실패, 완료 선언 검사를 추가한다.

• unclutter

  kitze · 보안 및 콘텐츠 검토

  광고, 홍보, 구독 팝업을 Jev로 판단해 재사용 가능한 숨김 규칙을 저장하는 확장.

• oc-plugins

  OpeOginni · 보안 및 콘텐츠 검토

  OpenCode 플러그인 모음의 oc-auto-perms가 자연어 규칙에 따라 도구 작업 의도를 Jev로 확인한다.

• jev-block-android-ad

  ufec · 보안 및 콘텐츠 검토

  로컬 인증 코드 규칙을 먼저 적용한 뒤 Jev로 광고성 잡음을 판단하는 Android 필터.

• jev-cvss

  Red5d · 보안 및 콘텐츠 검토

  취약점 설명에서 Jev가 CVSS 지표를 고르고 Python이 v3.0·v3.1·v4.0 점수를 계산한다.

• Jev-Moderation-Bot

  brainstormity · 보안 및 콘텐츠 검토

  Jev로 스팸·사기 링크를 확인하고 로컬 규칙으로 경고·타임아웃을 적용하는 Discord Bot.

• Agent

  AgentiLoop · 보안 및 콘텐츠 검토

  TypeSafeKit을 갖춘 네이티브 macOS Agent 내부의 선택적 Jev 명령 위험 고문.

• captaincore

  CaptainCore · 보안 및 콘텐츠 검토

  WordPress 운영 도구 CaptainCore의 Jev 명령으로 구조화 질문과 악성 코드 탐지 결과 우선순위를 처리한다.

• jev-experiments

  dabit3 · 보안 및 콘텐츠 검토

  스테이징 diff를 의미적으로 검사하는 Commit Sentry 등 Jev 개발 도구 실험 모음.

• is-malicious

  luantak · 보안 및 콘텐츠 검토

  실행 전 소스 코드, 빌드 스크립트, CI 설정에서 의심스러운 동작을 Jev로 탐지하는 CLI 보안 스캐너입니다.

• antivirus

  newuser7171 · 보안 및 콘텐츠 검토

  파일 정적 특징으로 state를 만들어 Jev에게 판정, 0–4 심각도, 몇 가지 예/아니오 지표를 받게 한 뒤, 로컬 규칙이 격리, 통과, 재확인을 정한다.

• jev-pii-checker

  coo-quack · 보안 및 콘텐츠 검토

  텍스트를 TypeSafe Jev에 보내 PII 종류 Noul과 민감도 Score를 받은 뒤, 정규식과 분절로 구간을 표시하는 CLI.

• pi-jev-sentinel

  harshwasan · 보안 및 콘텐츠 검토

  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-secret-detection

  teyhouse · 보안 및 콘텐츠 검토

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

• jevvy

  PanAchy · 보안 및 콘텐츠 검토

  Jev-powered plugins for coding agents

• jev-security-scan

  win4r · 보안 및 콘텐츠 검토

  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-auto-approve

  metalbear-co · 보안 및 콘텐츠 검토

  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:

• pi-jev-guard

  Reindeer-AI · 보안 및 콘텐츠 검토

  Check Pi code edits against repository Markdown rules with TypeSafe Jev

• jev-model-tokengate

  Thanh-Mathieu95 · 보안 및 콘텐츠 검토

  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.

• open-jev-approvals

  alexj11324 · 보안 및 콘텐츠 검토

  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.

• dsh-jev

  zhangxaochen · 보안 및 콘텐츠 검토

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

• actiongate-jev

  omkarghugarkar007 · 보안 및 콘텐츠 검토

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

• jev-phishing-bench

  anisselbd · 보안 및 콘텐츠 검토

  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`.

• traffic-guard

  hemanth · 보안 및 콘텐츠 검토

  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.

• pkg-gate

  hemanth · 보안 및 콘텐츠 검토

  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.

• profanity-checker

  4rays · 보안 및 콘텐츠 검토

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

• jevshield

  lgy1027 · 보안 및 콘텐츠 검토

  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-decisions

  bojansandhaus · 보안 및 콘텐츠 검토

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

• jev-edge

  kiwi0719 · 보안 및 콘텐츠 검토

  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.

• jev-preflight

  muse0509 · 보안 및 콘텐츠 검토

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

• agi-jev-containment

  carlosedm10 · 보안 및 콘텐츠 검토

  **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.

• claude-jev-warden

  connectedGraph · 보안 및 콘텐츠 검토

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

• jevals

  openlayer-ai · 보안 및 콘텐츠 검토

  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.

• jev-guard

  muratcakmak · 보안 및 콘텐츠 검토

  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.

• claude-jev-plugin

  dr-dimitru · 보안 및 콘텐츠 검토

  TypeSafe Jev semantic guardrails for Claude Code

• ego-jev-ultrafast

  shikaizhong-design · 보안 및 콘텐츠 검토

  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-chrome-extension

  gavansmyth-arch · 보안 및 콘텐츠 검토

  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**.

• jev-engineering

  codejunkie99 · 보안 및 콘텐츠 검토

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

• jev-guard

  ClemensSchartmueller · 보안 및 콘텐츠 검토

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

• reflex

  kaustav1996 · 보안 및 콘텐츠 검토

  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.

• JevPR

  HexyeDEV · 보안 및 콘텐츠 검토

  PR Risk review, automated by Jev

• guardrail-chatbot-jev

  taman-spirit · 보안 및 콘텐츠 검토

  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.

• jev-reasoning-navigator

  AndreuVM · 보안 및 콘텐츠 검토

  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-kit

  jonathanavis96 · 보안 및 콘텐츠 검토

  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-enforce

  erkamyaman · 보안 및 콘텐츠 검토

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

• grok-jev-guard

  0xwhrari · 보안 및 콘텐츠 검토

  `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:

• dsh-jev-verify

  xienda · 보안 및 콘텐츠 검토

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

• opencode-jev-guard

  CogFlux · 보안 및 콘텐츠 검토

  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.

• momus-review

  brianluby · 보안 및 콘텐츠 검토

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

• jev-engineering

  eugeniughelbur · 보안 및 콘텐츠 검토

  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 · 보안 및 콘텐츠 검토

  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-baselines-eval

  ickma2311 · 보안 및 콘텐츠 검토

  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.

• jev-test

  cgbarlow · 보안 및 콘텐츠 검토

  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-safety-gateway

  dark-hxx · 보안 및 콘텐츠 검토

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

• jev-risk-check-provider

  caiovicentino · 보안 및 콘텐츠 검토

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

• laya-browser-guard

  pateti-hub · 보안 및 콘텐츠 검토

  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.

• medula

  JoaquinRuiz · 보안 및 콘텐츠 검토

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

• pi-jev-eye

  bismawy · 보안 및 콘텐츠 검토

  Ultra-lean supervisor for Pi: zero-token regex guardrails, test verification tracking, and TypeSafe Jev semantic slop gate.

• jev-home-assistant-sentinel

  bojansandhaus · 보안 및 콘텐츠 검토

  Home Assistant 스마트홈을 위한 안전 경계로, Jev 어댑터 체인을 통해 자동화 작업에 대한 정책 검토와 결정론적 상태 검증을 수행합니다.