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

智能体与自动化

查找使用 Jev 在工作流中进行类型化决策的智能体与自动化项目。

  • 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.

    Parth1811/JevFlow · Python

    120
    claudeclaude-codeclaude-code-hooksclaude-code-marketplaceclaude-code-pluginclaude-code-pluginsclaude-code-plugins-marketplace
  • Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.

    romiluz13/jevmory · Python

    120
    agent-memorycalibrated-confidenceclicoding-agentspythonsqlitezero-dependency
  • TypeSafe Jev as the pi coding agent's quiet decision layer

    HyunjunJeon/pi-quiet-ask · TypeScript

    120
    typescript
  • chainlesschain: TypeSafe Jev ecosystem repository.

    chainlesschain/chainlesschain · JavaScript

    117
    javascript
  • ⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable.

    imMamdouhaboammar/fable-jev · TypeScript

    119
    agent-routingai-agentsautonomous-agentsawesome-jevbunfast-compactionget-fable
  • Pi extension suite powered by Jev: selective context compaction and model routing

    iefnaf/pi-jev · TypeScript

    112
    ai-agentscompaction
  • One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast!

    xinwang-nwpu/jev-mobile · Python

    100
    mobile-agentpython
  • Build and regression-test conversational state machines powered by Jev. Inspect decisions, capture failing conversations as tests, and export runnable TypeScript for your app.

    priyankark/jev-state · TypeScript

    101
    ai-agentscode-generationconversational-aideveloper-toolsevaluationllm-evaluationlocal-first
  • Jev-powered MCP tool routing for Codex

    jackbarunz/jev-tool-router · JavaScript

    102
    ai-agentscodexmcptool-routingvercel-ai-gatewayjavascript
  • A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents.

    parkavenue9639/jevloop · Python

    100
    agent-runtimeai-agentsdockerllm-evaluationobservabilitypythonsandbox
  • Adaptive reasoning effort for OpenCode via Jev, with an in-process plugin and Responses API proxy

    robertn702/opencode-jev-router · TypeScript

    100
    code-agentllmopenaiopencoderesponses-apitypescript
  • When Jev meets LLM -- Pair a small local LLM (System 2) with Jev model (System 1) to make small model more faster and accurate — OpenAI-compatible, private, and almost free to run in Kilo code and Cline.

    j1s4nn/duomind · Python

    92
    claudecodeclinecoding-assistantduomindhaggingfacejev-api
  • A Home Assistant voice agent that decides with typed, calibrated judgements instead of an LLM. One ~300 ms call per command, and it asks when it isn't sure.

    the-sof/home-assistant-typesafe-conversation-agent · Python

    92
    assistconversation-agentcustom-componenthacshome-assistanthomeassistant
  • Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone.

    adarshmishra07/jcm-router · TypeScript

    91
    typescript
  • Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs

    kinde-starter-kits/jev-agent-authorization · TypeScript

    90
    agent-authorizationai-agentsauthorizationconvexkindellm-securitymcp
  • Model and reasoning routing for Codex Desktop and CLI, with a Windows service and validated updates

    ansidium/jev-codex-bridge · JavaScript

    91
    codexmodel-routingwindowsjavascript
  • Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

    AbdelStark/bicameral · TypeScript

    81
    typescriptharness-engineeringhybrid-machine-learningmachine-learning
  • Find, design, and evaluate TypeSafe Jev decision loops.

    karanb192/jev-architect · HTML

    86
    agent-skillsai-agentsclaude-codellmopenai-codex
  • Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.

    bestagentkits/jev-skillful · TypeScript

    83
    typescriptagent-toolingai-agentsclaude-code
  • Confidence-gated incident routing with TypeSafe Jev

    kyle-chalmers/typesafe-jev-incident-router · Python

    81
    python
  • Library of specialized IT domain agents following Anthropic's effective agent design patterns

    chrishuffman5/domain-expert · Shell

    73
    shell
  • A helper which use JEV to play ra2web(WannaFire Version)[王二火大]

    ra2web/jev-helper · JavaScript

    74
    javascript
  • 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.

    eran-broder/jev-skills · TypeScript

    71
    ai-agentsclaude-codecodexcontext-windowhookspluginskills
  • A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev.

    noplan-inc/limpet · Python

    71
    pythonai-agentsclaude-codecodex
  • Input moderation for Mastra agents on TypeSafe Jev — one file

    CodeAlive-AI/mastra-jev-moderation · TypeScript

    72
    typescript
  • Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini

    lhemerly/mcts-agent · Python

    70
    python
  • OpenCode plugin that adds an Auto (Jev) virtual model which routes each prompt to a configured real model using TypeSafe AI (Jev).

    jorgefspereira/opencode-auto-jev · TypeScript

    70
    typescript
  • A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent

    kaustav1996/reflex · TypeScript

    72
    typescript
  • Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev.

    akash-kamat/system-one-gemma · Python

    72
    pythoncalibrationdecision-modelgemma
  • Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

    abhishekswe/agent-fastpath · TypeScript

    62
    agentic-aiai-agentsbrowser-automationclaude-codecodexcoding-agentscontext-engineering
  • The intelligence layer for beads: typed, calibrated labels for your backlog

    harrymunro/beadsort · Python

    61
    python
  • 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.

    wjw66/deepseek-harness-jev-pre-compaction · TypeScript

    60
    typescript
  • Typed decision layer for coding agents — Claude Code, Codex, Antigravity, Hermes, VS Code. One MCP server, 20 tools, 36 recipes, per-provider calibrated gates.

    qualixar/jev-decision-layer · Python

    61
    agent-routingai-agentsanthropicclaude-codecodex-pluginlaya-mlxmcp
  • Agent Skill: send closed coding-agent judgments to TypeSafe Jev

    HyunjunJeon/jev-judgment · Python

    62
    python
  • Fast typed AI decisions on live crypto markets using TypeSafe AI Jev.

    zzsong1023/jev-market-reflex · TypeScript

    61
    ai-agentsbuncryptopaper-tradingreal-timetypescript
  • jev-router: automatic model and effort switching for Claude Code

    xafold/jev-router · Rust

    60
    rust
  • Fast deep research for the pi coding agent: reads up to 100 pages in full per round, Jev keeps only the passages that answer your questions.

    savka777/jev-search · TypeScript

    61
    deep-researchpi-packageweb-searchtypescript
  • Jev-powered decision skills for Claude Code and Codex. Opt-in, advisory, fail-open.

    n23eos/jev-skills · Python

    60
    agent-skillsclaude-codecodexdeveloper-toolsmodel-routingpython
  • Talk to your Mac and it does it — in any app, while you're still talking. Open-source voice agent that gets faster the more you use it.

    danielyedaniel/jevme · Python

    61
    accessibilityai-agentsanthropicautomationclaudecomputer-usellm

第 101–150 条,共 563 条