TypeSafe Jev / System One モデルの無料 GitHub プロジェクト集公式 SDK、エージェントツール、オープンソースの代替実装と Jev の最新ニュースを紹介

データ更新

開発ツール

Jev プロジェクトの開発に役立つツールやユーティリティを探せます。

  • Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation

    thiago-ss/jev-review · Python

    10
    python
  • Finds the turns where Claude Code should have loaded one of your skills and did not, judged by TypeSafe's Jev. Audit CLI plus the mod that fixes it live.

    karanb192/jev-skill-scout · JavaScript

    10
    javascript
  • Chrome extension + local relay that labels X posts with a Jev (TypeSafe) hype-over-substance probability

    SylphAI-Inc/jev-slop-detector · JavaScript

    10
    javascript
  • jev-sort: TypeSafe Jev ecosystem repository.

    CMaintz/jev-sort · TypeScript

    11
    bulk-classificationclassificationclicsvdata-labelingdata-processingdeveloper-tools
  • Organize Chrome tabs and groups by meaning with a single Jev API request.

    proshunsuke/jev-tab-order · TypeScript

    12
    chrome-extensiontabswxttypescript
  • AI columns for CSV/JSONL files with TypeSafe's Jev — typed answers, confidence, review queue, resume and cost preview. Local-first, BYO key.

    dtduc-git/jev-table · Python

    10
    classificationclicsvdata-labelingllmpython
  • Run only the tests your change touched: import graph + ownership rules first, Jev decides the ambiguous rest, fail-safe to the full suite. Replay benchmark with real ground truth.

    criguex/jev-test-impact · TypeScript

    10
    ciplaywrightqa-automationtest-impact-analysistypescriptvitest
  • jevgrep: TypeSafe Jev ecosystem repository.

    thehumanworks/jevgrep · Rust

    10
    rust
  • Claude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model

    Jhonnyr97/JevGuard · TypeScript

    10
    agent-securityagent-skillsai-agentsclaudeclaude-codecodex
  • Codex plugin that preserves useful conversation excerpts alongside the summary after context compaction. (TypeSafe Jev / System One).

    hatt-io/jevkeep · TypeScript

    10
    ai-agentscompaction
  • jevkit for JavaScript/TypeScript: static linter and shared record format for building on TypeSafe's Jev (System One) model. Unofficial.

    pjdurden/jevkit-js · TypeScript

    10
    linterllmtypescript
  • Jev decision visualisation and debugging panel for coding agents. MCP server + local web timeline, confidence alerts and trace export.

    a742987/JevLens · TypeScript

    10
    typescript
  • Auditable Jev decisions through OpenRouter. A macOS-first TypeScript CLI with Keychain credentials, recorded costs, and conservative retries.

    richardskypixel-max/jevrail · TypeScript

    10
    audit-trailclicoding-agentsopenroutertypescript
  • Turn acceptance criteria into Appium tests. A decision model (Jev) explores the app once, then jevvium writes a plain, deterministic WebdriverIO test.

    AndresCarreonDiaz/jevvium · TypeScript

    10
    ai-testingandroidappiumiosmobile-testingqa-automationtest-automation
  • 1453jevvy
    Source-linked review of comments, functions and tests for Pi, powered by Jev.

    timbrinded/jevvy · TypeScript

    10
    typescript
  • 1455jfind
    Find files by describing them in plain English: find(1) with a semantic --like predicate, answered by TypeSafe.ai's jev model

    religa/jfind · Python

    10
    ai-apiclassificationclicommand-line-toolconfidence-aware-aideveloper-tools
  • Calibrated picks for Neovim, judged by TypeSafe Jev. First source: effect-error-pretty.nvim

    rashedInt32/jury.nvim · Lua

    10
    ai-assisteddeveloper-experiencediagnosticseffecteffect-tsllm-toolslsp
  • Pipe anything in, get one decision out. A justfile that asks TypeSafe's Jev from the shell.

    yfe404/just-jev · Just

    10
    just
  • 1473lisa
    LISA: Leak, Injection & Simplicity Auditor. GitHub Action that uses TypeSafe Jev (a system one model) to flag secrets, security vulnerabilities, and unneeded complexity in pull requests

    turenlabs/lisa · Python

    10
    github-actionssastsecuritysecurity-automation
  • A code review check that learns from reviewer rulings without fine-tuning. Jev (TypeSafe AI) judges each diff hunk against your team's guidelines; a Meko datapack (powered by YugabyteDB) holds the guidelines, the rulings, and a trace of every decision. Companion repo for the blog post "Jev and Meko Make Code Review Feedback Stick".

    YugabyteDB-Samples/meko-jev-code-review-agent · Python

    10
    agent-memoryai-agentscode-reviewmcpmekopython
  • Model Picker: JEV-powered Codex model and effort recommendations as task scope grows. Manual switching, private local state, MIT licensed.

    Tatendaz/model-picker · Python

    10
    ai-codingcodexcodex-plugindeveloper-toolshooksllmmodel-routing
  • AI code review against your repository's rules, powered by TypeSafe AI's Jev.

    jpowersdev/neuralint · HTML

    11
    html
  • Model-judged permission gate for OMP: classifies bash commands and spawn-bearing eval payloads before they run, prompts on risk, fails closed

    STRML/omp-classifier · TypeScript

    11
    typescript
  • Jev-powered context compaction plugin for opencode: prune stale tool calls and results before every request, keep the rest verbatim.

    quinnjr/opencode-jev-compaction · TypeScript

    12
    typescript
  • OpenCode V2 plugin that uses TypeSafe JEV to classify prompts before LLM reasoning

    murilogteixeira/opencode-jev-pre-llm · TypeScript

    11
    openaiopencodeplugintypescript
  • OpenCode plugin that classifies shell commands, reads, and edits with TypeSafe Jev (System One) and folds the result into permission decisions.

    schemaitat/opencode-plugin-auto-classifier · TypeScript

    11
    typescript
  • Jev (TypeSafe)-backed decision layer for Orca Lab: judges what agents are about to run, and stays out of the way otherwise.

    ab2webco/orca-jev-advisor · TypeScript

    12
    typescript
  • Find any frame in a Pen (pen.dev) design file by describing it. Jev ranks every node by meaning; your AI agent only reads the top matches. CLI + Claude Code plugin.

    adelghaenian/pen-find · JavaScript

    10
    ai-agentsclaude-codeclaude-code-pluginclidesigndesign-toolsmcp
  • pi-jev-anti-slop: TypeSafe Jev ecosystem repository.

    BubbatheVTOG/pi-jev-anti-slop · TypeScript

    10
    typescript
  • Ultra-lean supervisor for Pi coding agent using local regex filters, verification state tracking, and TypeSafe Jev semantic gate

    bismawy/pi-jev-eye · TypeScript

    10
    ai-agentsguardrailspi-packagetypescript
  • pi-jev-score: TypeSafe Jev ecosystem repository.

    marszhongx/pi-jev-score · TypeScript

    10
    typescript
  • Triage every open pull request of a GitHub repo in minutes: Jev typed questions, local Ollama descriptions, git test-merge, take / consider / skip board

    gentslava/pr-scout · TypeScript

    11
    code-reviewfastapigithubollamapull-requestsself-hosted
  • Analyze prompts with TypeSafe Jev before GitHub Copilot

    shubhangi013/prompt-oscilloscope · TypeScript

    10
    typescript
  • Checks a coding agent's final reply against the project's writing rules with TypeSafe Jev (Claude Code, Codex, Muse Code)

    vgeshel/prose-check · TypeScript

    10
    typescript
  • 1528s1kit
    Test, calibrate and route System One decision models (Jev, Laya, kev, llama.cpp, Ollama) on your own data.

    Eliot5566/s1kit · Python

    10
    calibrationclidecision-modelgithub-actionslayallm-evaluationllm-routing
  • Enrich fields in Sanity with an instant feedback utilising the decision model Jev from Typesafe. Show a score to the editors realtime on things like readability, tone, trustworthiness, credibility or anything else.

    frederikvonsperling/sanity-plugin-jev-fields · TypeScript

    10
    typescript
  • Find the LLM calls you should move to JEV — scan logs & code for decision-shaped calls, price the migration, calibrate decision models, generate the migration PR. Zero deps, fully local.

    yzbcs/Should-I-Jev · Python

    10
    cost-optimizationdeveloper-toolsllmpython
  • Skill Dash uses Jev to judge Claude Code and Codex skills and plugins: usefulness, redundancy, clarity, duplicates, safety. Local dashboard plus the corpus pipeline behind whichskills.dev. MIT.

    48Nauts-Operator/skill-dash · Python

    10
    agent-skillsai-safetyclaude-codeclaude-skillscodexdashboardprovenance
  • smcraft: TypeSafe Jev ecosystem repository.

    jgwill/smcraft · TypeScript

    10
    typescript

425 件中 201–250 件