A free GitHub project directory for the TypeSafe Jev / System One model.Explore official SDKs, agent tools, open-source alternatives and Jev news.

Data updated

All tags

Projects tagged with “ai-agents”

Browse Jev GitHub projects tagged with ai-agents. Filter, sort and explore their source repositories.

  • 1905jev
    A wrapper that gets more value out of TypeSafe's JEV model: transcript compaction, cost-control modes, and a local usage ledger for Claude Code and Codex.

    imsukhe/jev · JavaScript

    00
    ai-agentsclaude-codeclicodexcontext-compactioncost-controldeveloper-tools
  • Classify a business's description of operations into one of 1,012 NAICS 2022 industries, or hold it for a person. No LLM writes anything: Postgres search and code-owned gates do the work, and TypeSafe Jev only picks from a closed list. The hybrid: 0 wrong codes on its eval sets.

    jmurray10/jev_naics · Python

    00
    ai-agentscensusdockerevaluationfastapifull-text-searchindustry-classification
  • Code when exact. Jev when useful. Agent when uncertain. A lightweight routing layer for computer-use agents, with real workflow benchmarks.

    ljy8072/jev-agent-router · Python

    00
    agent-toolsai-agentsautomationbenchmarkcomputer-usepython
  • Runnable demo of how Jev (TypeSafe System One) works: typed questions in, calibrated answers out, decisions in code

    georgeykalangi/jev-ai-demo · Python

    00
    ai-agentsllmpython
  • An independent, evidence-first field guide to Jev (TypeSafe AI's System One model) — for people and for coding agents. Not affiliated with TypeSafe AI.

    gorock007/jev-atlas · TypeScript

    00
    ai-agentsmcpmodel-context-protocolnextjsresearchtypescript
  • Let TypeSafe Jev play Brotato: local game bridge, autonomous menus, and recorded runs with probabilities, latency, tokens and cost.

    banjtheman/jev-brotato · Python

    00
    ai-agentsbrotatogodotpython
  • Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.

    KesavanKing/jev-browser · Python

    00
    pythonai-agentsautonomous-agentsbrowser-automation
  • Is TypeSafe AI's Jev calibrated? Reliability diagram, ECE and saturation split on 240 hand-labelled agent tool calls.

    themsquared/jev-calibration · Python

    00
    agentevalsagentgatewayai-agentsbenchmarkcalibrationllmpython
  • Jev + Claude Code, tested: a support-triage app and a Claude Code safety hook where TypeSafe's Jev makes the fast typed decisions and code owns the rest. Runs offline; --live for Jev.

    gsaini/jev-claude-code-case-study · Python

    00
    agentic-aiai-agentscase-studyclaude-codeclaude-code-hooksllmpython
  • Delegation-first Jev routing, deterministic code review, and preventive checkpoints for Codex Desktop.

    SomebooksIT/jev-codex · Python

    00
    ai-agentscode-reviewcodexcodex-plugindeveloper-toolsmodel-routingpython
  • 把 Jev(一个小而快的判定器)接进你的 AI 助手:一个多月的实战手册——接入 / 判定点 / 影子期评测 / 踩坑集

    zhaoyanan-pixe/jev-cookbook · Python

    00
    agent-skillsai-agentscookbookjudgmentllmpython
  • Corrective RAG where every decision gate is a typed System One model call instead of an LLM judge. 7x fewer LLM calls, 4x lower p50 latency.

    sudeshkar/jev-corrective-rag · Python

    00
    ai-agentsgroqllmpythonragretrieval-augmented-generation
  • 让 Agent 长出「操作杆」:用 System One 模型(Jev)承担高频判断、多模态模型当眼睛。给思路 + 可跑的参考实现(75 条离线断言,零依赖零 key)

    1816586742-stack/jev-craft · JavaScript

    00
    ai-agentsdecision-makingdeepseekdshllmminecraft
  • An 11-level crash course on Jev, TypeSafe AI's System One decision model — runnable examples against the real API, plus a capstone project with unit tests and evals. Works with any LLM provider via LiteLLM.

    nadyth/jev-crash-course · Python

    00
    ai-agentscrash-courseevaluationlitellmllmpython
  • 让 AI Agent 直接调用 TypeSafe AI「Jev」决策模型的 Skill —— 免 API key,纯标准库 CLI。Agent Skill for TypeSafe AI Jev (System One).

    alaithuy385-byte/jev-decision-skill · Python

    00
    agent-skillsai-agentsclaude-codedecision-modelworkbuddypython
  • A Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode.

    prestonkakukdev/Jev-Defense · Python

    00
    ai-agentsai-safetyclaude-codeguardrailsllm-securityprompt-injectionpython
  • JEV Studio is a small Next.js evaluation lab for turning natural-language input into structured signals with the Typesafe SystemOne API.

    darrenli6/jev-demo · TypeScript

    00
    ai-agentstypescript
  • Goal-driven AI agent that records walkthrough videos of any web app and writes the user guide. Powered by Jev (TypeSafe AI) + Playwright, driven from Claude Desktop via MCP. Open-source alternative to Supademo/Scribe and manual testing.

    kaivalpatel6350/jev-docs-agent · Python

    00
    ai-agentsarcade-alternativebrowser-automationclaude-desktopdocumentation-generatore2e-testinginteractive-demo
  • Sort your Gmail inbox into categories you write in plain English. TypeSafe's Jev makes each call with calibrated probabilities; uncertain mail gets a Review label. Built on One, runs with zero keys.

    withoneai/jev-email-classifier · TypeScript

    00
    ai-agentsemail-classificationgmailwithonetypescript
  • A Claude Code skill of field notes on Jev: which question shape fits which job, how to test a use before trusting it, and the traps. Companion to TypeSafe's official skill.

    NaluKicks-808/jev-field-guide-skill

    00
    ai-agentsclaude-codeclaude-skills
  • A pre-registered field trial of Jev (TypeSafe's judgment model) on a second brain and Claude Code history: 20 tests, bars written first, failures included, and the tools to repeat it.

    NaluKicks-808/jev-field-trial · Python

    00
    ai-agentsclaude-codeevaluationsecond-brainpython
  • Six calibrated gates for Claude Code, judged by TypeSafe Jev: rules, scope, intent, done, claims, and commit honesty. Each one escalates, none ever approves.

    rashedInt32/jev-gates · JavaScript

    00
    ai-agentsclaude-codeclaude-code-plugindeveloper-toolsguardrailshooksllm-tools
  • Three gates for any coding agent: a deterministic approval gate before irreversible actions, a completion gate that demands evidence instead of «done», and a rubric regression gate. Powered by TypeSafe Jev (System One). Works with Claude Code, Codex, DeepSeek Harness, Cursor, opencode, Hermes, plain shell and CI.

    cwjechw98-lang/jev-gates · JavaScript

    00
    agent-harnessagent-safetyai-agentsai-verificationclaude-codecodexcoding-agents
  • Steer a 3D box with plain-language goals: an LLM (System 2) plans each instruction, TypeSafe Jev (System 1) makes every move, turn and jump decision in real time. Three.js + TypeScript.

    blakeandrewwood/jev-goal-reflex · TypeScript

    00
    ai-agentsgame-aillmreal-timesystem-twothreejs
  • Get coding agents to write Jev questions that work the first time: rules measured on 57 labelled suites.

    BarakChamo/jev-kit · JavaScript

    00
    agent-skillsai-agentsbenchmarkcalibrationclaude-codeclaude-code-pluginclaude-code-skill
  • Do I need to look at what Claude Code just did? A calibrated verdict per stop, judged by TypeSafe Jev. Pairs with jev-lens.nvim

    rashedInt32/jev-lens · JavaScript

    00
    ai-agentsclaude-codeclaude-code-plugincode-reviewdeveloper-toolshooksllm-tools
  • MCP server exposing one tool: ask Jev a typed question and get a short answer back.

    CodeCampusCo/jev-mcp · TypeScript

    00
    ai-agentsclassificationmcpmodel-context-protocolnodejstypescript
  • MCP server for decision models with TypeSafe Jev, Cloudflare Clef, OpenRouter, and local providers.

    drmedia/jev-mcp · TypeScript

    01
    ai-agentscloudflare-clefdecision-modelmcpmcp-servermodel-context-protocolopenrouter
  • Route bounded decisions through Jev and hand open-ended work to Mistral.

    gbesse/jev-mistral-reflex · JavaScript

    00
    ai-agentsmistral-aitool-routingjavascript
  • A retail multi-agent system where TypeSafe's Jev acts as the System One decision layer inside a LangGraph orchestrator it will multiple agents using A2A Servers, Google ADK, Langgraph, Claude Agent sdk and Microsoft agent sdk

    anjijava16/jev-multiagent-retail · Python

    00
    ai-agentsagent-frameworkagent-memoryagent-orchestrationagent-skillsagentic
  • Jev (TypeSafe System One) plays Pac-Man in real time: structured state in, one legal direction out. No screenshots, no fine-tuning.

    tetsuya-dev-jp/jev-pacman · TypeScript

    00
    ai-agentsgame-aillmnextjspacmantypescript
  • AI agent that plays Super Mario Bros with TypeSafe Jev - a typed decision model reading NES RAM instead of pixels, verified by emulator rollback search. Clears 1-1 to 1-4 and 2-1 for ~$0.02.

    VBS2004/jev-plays-super-mario-bros · Python

    00
    ai-agentsdecision-modelemulatorgame-aillm-agentsnespython
  • Cursor and Hermes marketplace for the four published JEV Labs routers.

    Pinutss/jev-plugins

    00
    ai-agentsrouter
  • Turn an investment idea into an evidence-backed stock list: Jev reads ~20k global companies and checks official annual reports. 主题选股 / 产业链 / 年报证据 — runs locally via your AI agent.

    YuanTong-Wu/jev-screen · Python

    00
    a-sharesai-agentsannual-reportsclaude-codeinvestment-researchllmstock-screener
  • Route each task to the one tool an agent should call, with Jev — with confidence. Single-file, no build. Use free: jevtypesafeai.com/tools/jev-skill-router

    codaaiteam/jev-skill-router · HTML

    00
    agent-toolsai-agentsdecision-apillm-routersingle-file
  • Learn JEV, TypeSafe AI's decision model, in ~2.5 hours: one customer-support assistant built up in 12 runnable steps, each compared live with an LLM-only version on speed, cost and accuracy

    ease-my-work/jev-step-by-step · Python

    00
    adkadk-pythonai-agentscustomer-supportdecision-modeldesk-buddy-agentgemini
  • Autonomous dinosaur ecosystem where code runs the physics and TypeSafe's Jev decides each creature's intent from prose laws. Pixel-art web UI with a live Jev monitor (JSON in/out per tick), interchangeable brains (hybrid / full Jev / offline). Experimental Jev integration.

    ChristianTracy/jev-terrarium-dinosaurs · Python

    00
    ai-agentsautonomous-agentsfastapillmpixel-artpythonsimulation
  • Fast 'System One' reflex for reasoning LLMs: typed probabilistic second opinions from Jev via OpenCode Zen, with PII-minimizing state redaction.

    OmarAlaaeldein/jev-verifier-skill

    00
    agent-skillsai-agentsllmopencodeprivacy
  • Event-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions

    glebmish/jev-watchdog · Python

    00
    ai-agentsai-safetyclaude-codeclaude-code-hooksguardrailsllm-as-a-judgepython

301–350 of 368