TypeSafe Jev / System One 模型的免费 GitHub 项目目录按用途查找官方 SDK、智能体工具、开源替代实现与 Jev 最新资讯

数据更新

  • 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.

    shimo4228/jev-skill-router · Python

    203
    agent-skillsclaude-codeclaude-code-pluginhookspython
  • 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.

    Ray-Hughes/jevalyn · Ruby

    201
    decision-modelllmrailsrubyrubygem
  • Ask TypeSafe's Jev decision model questions about your data from inside Snowflake. dbt package plus a Terraform module.

    KranzL/Jevflake · Python

    202
    dbtdbt-packagessnowflaketerraformpython
  • Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis.

    reachjalil/jevlogs · JavaScript

    204
    typescript
  • Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results

    anandi1989/awesome-jev-usecases

    195
    ai-agentsawesome-listbenchmarkbrowser-agentscalibration
  • 306jcr
    A Jev-powered resolver for agent harnesses to find deterministic commands and their context in a nested capability tree.

    NiazMorshed2007/jcr · JavaScript

    191
    ai-agentsmcpjavascript
  • Library that uses Jev by TypeSafe AI as the decision layer for phone calls

    rayanweragala/jev-call-router · HTML

    196
    asterisk-pbxjev-apipbxsiphtml
  • Small dependency-free CLI for TypeSafe Jev

    tumf/jev-cli · Python

    192
    clipython
  • Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome.

    jiawei686/jev-ultrafast-mcp · Python

    196
    python
  • Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients

    zhulinchng/jevper · Python

    195
    classificationconfidencellmlogprobsopenaipydanticpython
  • 311kibu
    kibu: TypeSafe Jev ecosystem repository.

    madhurjyadc/kibu · TypeScript

    190
    typescript
  • TypeSafe structured-output provider for RubyLLM 2

    kieranklaassen/ruby_llm-typesafe · Ruby

    191
    ruby
  • Awesome list of Jev use cases. Compared with GPT Models (LLMs) across on cost and speed.

    whyashthakker/awesome-jev-use-cases · HTML

    184
    rlcdrlhfhtml
  • 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.

    Larkspur-Wang/Jev_steer_or_queue · Python

    182
    ai-agentsclaude-codeclaude-code-plugincodexhookspython
  • JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default

    bl888m/jev-bot · Python

    187
    pons-v2pythonrobinhoodtrading
  • Chrome extension: a badge rating how well-argued an article is, via the Jev API.

    cadeos/jev-grounds · JavaScript

    183
    javascript
  • A fuzzy linter for coding agents. It checks the code your agent writes against your team's best practices while the agent is still working, not at code review.

    ckorhonen/jev-lint · HTML

    181
    lintertoken-efficiencytoken-optimizationtoolhtml
  • Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.

    hev/jev-rerank · Python

    180
    python
  • Fast, typed browser automation powered by Jev and Playwright

    filedcom/playjev · TypeScript

    183
    browser-automationplaywrighttypescript
  • An open-source, model-agnostic decision router for Claude Code and Codex.

    ruban-24/switchboard · TypeScript

    182
    claude-codeclicodexmodel-routingreasoning-efforttypescript
  • Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen 上训练 JEV 风格的 System 1 决策模型。

    shibing624/train-jev · Python

    183
    calibrationdecision-modeldistillationfine-tuningllmloranlp
  • A curated list of tools, integrations, and experiments built on Jev, TypeSafe AI's System One model for fast, typed decisions.

    ckaraca/awesome-jev · Python

    177
    ai-agentsawesomeawesome-listcomputer-usellm
  • 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.

    ZephyrDeng/ego-jev · TypeScript

    171
    agent-skillsai-agentsbrowser-automationclaude-skillscodex-skillsskill-mdjavascript
  • 324Helm
    Route every coding task to the best AI agent on your machine — Claude Code, Codex, Cursor, Gemini CLI, Aider, OpenCode. Installs as a Claude Code plugin, Gemini extension, or Agent Skill.

    Jimuelle07/Helm · Python

    171
    agent-orchestrationagent-routeragent-skillsai-agentsaiderclaude-codeclaude-code-plugin
  • 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
  • Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move.

    romaluev/jev-ego · TypeScript

    172
    typescriptai-agentsbrowser-agentcdp
  • 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.

    WXK-AI/jev-opus · TypeScript

    172
    ai-agentsclaudeclaude-codeclaude-code-plugineffortopusprompt-caching
  • Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and reproducible benchmarks.

    aifabrice/jev-rag · Python

    174
    agentic-searchbm25embeddingsfts5hybrid-searchjev-ragjevrag
  • 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

    dirien/jev-router · JavaScript

    174
    claude-codecodexllm-gatewaymodel-routerollamajavascript
  • 330osso
    Just the bone. A Chrome extension that strikes the filler out of every page you read.

    Fars29/osso · TypeScript

    170
    typescript
  • Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway

    mejiasd3v/pi-jev-router · JavaScript

    171
    javascript
  • An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.

    sosopop/jev_stock · Python

    165
    pythonfinancial-datafinancial-machine-learningllm
  • The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for the world's first System One AI model.

    paramjeetn/jev-cookbook · Python

    163
    agentic-aiai-agentsai-engineeringclassificationcookbookdecision-enginellm
  • Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows

    jmanhype/jev-dspy-lab · Python

    162
    python
  • if you're experimenting with jev it will be easier from here

    utk2103/jev-studio · Python

    160
  • Semantic lint rules for the code-review questions a deterministic linter can't express

    Ice-Hazymoon/jevlint · TypeScript

    161
    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
  • Claude skill for VLM Run CLI

    vlm-run/skills

    160
  • A Swift client for TypeSafe AI's Jev — typed judgements, not text

    d-date/swift-jev · Swift

    160
    foundation-modelsjev-apiswift

第 301–350 条,共 3056 条