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。

  • Pre-commit hook where one Jev call judges whether the commit message matches the staged diff, plus checks for debug leftovers and unmentioned work. Warns on mismatches, blocks only on a detected secret.

    valentynkit/jev-commit · Python

    172
    pythoncode-review
  • Semantic lint rules for the code-review questions a deterministic linter can't express

    Ice-Hazymoon/jevlint · TypeScript

    171
    typescript
  • Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, claude extension, and more. Built with Effect + TypeScript.

    tyler-dot-earth/patdown · TypeScript

    163
    typescript
  • A browser extension that lights up the paragraph that answers your question

    tymscar/hunch · TypeScript

    156
    typescript
  • Jev-assisted retrieval and evidence-preserving inspection for local Markdown, Obsidian vaults, and Logseq Markdown graphs.

    Emlembow/jev-graph-search · JavaScript

    153
    logseqmarkdownobsidianjavascript
  • Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin.

    iamtoomas/JevLint · TypeScript

    150
    typescript
  • Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside DeepSeek Harness.

    HorusJiang/dsh-jev-tools · TypeScript

    132
    context-windowdeepseek-harnessdshdsh-pluginllmprompt-injection
  • 📏 Claude Code plugin that makes Claude follow your AGENTS.md: every reply and edit checked by TypeSafe Jev ✅

    erkamyaman/jev-enforce · TypeScript

    132
    claudeclaude-codeclaude-code-pluginclaude-mdcode-qualitydeveloper-tools
  • Jev + A2UI = ?

    dglazkov/jev2ui · TypeScript

    132
    typescript
  • CLI-first field-level anomaly detection for structured files and text, powered by Jev

    ai4curation/jevotron · Python

    132
    python
  • Evidence over eloquence. Unofficial Claude Code plugin that checks "done" claims and small judgement calls with TypeSafe Jev, and keeps receipts.

    ismaildasci/claude-referee · TypeScript

    123
    ai-agentsclaude-codeclaude-code-hooksclaude-code-plugindeveloper-toolsllm-as-a-judge
  • Catch AI slop before you ship.

    mblode/taste-lint · TypeScript

    123
    typescript
  • 使用 TypeSafe Jev 审查 Skill 与 MCP 可疑行为 | Review Agent Skills and MCP code with Jev, static evidence, and explicit coverage gaps

    win4r/jev-security-scan · Python

    111
    python
  • A Stop hook for Claude Code and Codex, for the turn that ends half-done — nothing done, an announced action never carried out, a promise to watch CI with nothing running — or in the wrong language. Every judgement is made by TypeSafe Jev.

    Nanako0129/stingray · Shell

    112
    shell
  • 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.

    sufianetaouil/every · Python

    101
    python
  • /fc for Claude Code: shrink old tool output in about a second — Jev keeps what's still needed, every cut saved to a file. Your /compact stays untouched.

    NodarDavituri/fast-compact · TypeScript

    102
    claude-codeclaude-code-plugincontext-compactionopenroutertypescript
  • PR Risk review, automated by Jev

    HexyeDEV/JevPR · Python

    102
    classificationpull-requestspython
  • DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

    justhalfbit/dsh-plugin-jev-effort-selector · JavaScript

    91
    ai-agentsdeepseek-harnessdeepseek-harness-plugindshdsh-pluginllmplugin
  • 469jeq
    What happens when jev meets jq? Intelligence you can pipe

    cristianoliveira/jeq · Go

    92
    ai-agentsai-codingai-toolsjqterminalunix
  • 479jevc
    Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler

    doronp/jevc · TypeScript

    90
    agent-securityai-agentsai-safetyai-sdkclaude-codecli
  • Smarter cron with Jev

    gordonbrander/jevgate · Rust

    92
    rust
  • Code-review gate for CI and coding agents: asks TypeSafe Jev small typed questions about functions, files, tests and docs, and reports findings with locations and probabilities

    Tech-Byte-Frontier/jevgate · Rust

    93
    ai-agentsciclicode-reviewdeveloper-toolsruststatic-analysis
  • 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

    sumleo/prompt2jev · Python

    92
    agent-skillsclaude-codedecision-makingllmpython
  • Claude Code plugin that scores review findings, debug hypotheses and design options with TypeSafe's Jev — calibrated probabilities instead of one more opinion.

    buchmark/claude-jev · TypeScript

    80
    antrophicclaude-plugintypescript
  • DiffJury — TypeSafe Jev PR risk router + code review coach

    raihankhan-rk/diffjury · TypeScript

    82
    typescript
  • Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.

    Nainish-Rai/jev-frontend-qa · Python

    80
    browser
  • Semantic code and document search CLI — BM25 recall + TypeSafe Jev calibrated precision

    romeromarcelo/jev-retrieval · Rust

    81
    bm25claude-codeclicode-searchcoding-agentsdeveloper-toolsdocument-search
  • Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

    ShivamPansuriya/jev-skill-gate · JavaScript

    81
    agent-skillsai-agentsai-toolinganthropicclaudeclaude-codeclaude-code-hooks
  • Neovim plugin that answers a plain-language question about the buffer: Treesitter splits it into functions, Jev scores each one, and the ranked answers land in the quickfix list.

    valentynkit/jev.nvim · Lua

    82
    luadeveloper-toolseditor
  • Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev.

    allebee/pytest-jev · Python

    81
    llmllm-evaluationpytestpytest-pluginpythontesting
  • zanity: TypeSafe Jev ecosystem repository.

    benomahony/zanity · Zig

    80
    zig
  • Jev-judged context compaction for DeepSeek Harness: semantic tool-result pruning + deterministic receipt compaction

    yangyu666/dsh-jev-prune · JavaScript

    73
    ai-agentscontext-compactioncordisdeepseek-harnessdsh-pluginjavascript
  • Jev-powered Playwright test selection

    arthurfiorette/jev-playwright · TypeScript

    70
    e2eplaywrightselectiontestteststypescript
  • opencode-auto-approval-plugin: TypeSafe Jev ecosystem repository.

    dyoshikawa/opencode-auto-approval-plugin · TypeScript

    76
    typescript
  • Grade page sections for clarity, writing and on-page SEO. WXT + TypeSafe AI Jev.

    kitze/pagegrade · TypeScript

    71
    typescript
  • A Jev based context curator for pi

    Shashank-H/pi-jev-context-curator · TypeScript

    72
    typescript
  • Jev-powered /effort advisor for Claude Code: tells you when to switch effort, per prompt

    Yaxin9Luo/spending-effort-with-jev · Python

    70
    python
  • shadcn-style reusable components and blocks for using TypeSafe AI.

    TypeSafeAI/typesafe-ui · TypeScript

    72
    typescript
  • Semantic end-to-end agent testing for iOS, Android, and web.

    gokulnair2001/Convoy · TypeScript

    61
    androide2e-testingiostest-automationtypescriptwebsite

425 件中 51–100 件