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

  • MCP server and skill that let an agent drive an Android phone naturally over adb

    FZ2000/android-jev · Python

    20
    adbai-agentsandroidandroid-automationautomationclaude
  • Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines

    logicrw/ask-jev · Python

    20
    agent-architectureagent-evaluationagentic-workflowai-agentsclaude-codeclicoding-agents
  • Decides whether a message should reach the LLM at all, using TypeSafe Jev choice probabilities.

    AstrBotDevs/astrbot_plugin_reply_gate · Python

    21
    astrbotastrbot-pluginpluginpython
  • A curated list of Jev / TypeSafe System One projects, SDKs, tutorials, and evaluations. English and 简体中文.

    majiayu000/awesome-jev · Python

    25
    ai-agentsawesomeawesome-listbrowser-automationmodel-routing
  • A collection and survey of Jev

    youzizzz1028/Awesome-Jev · TeX

    21
    tex
  • Jev-powered AI agent skills for Codex and Claude Code: code review, testing, debugging, extraction and QA evidence. Open source, MIT.

    Pleo2/awesome-jev-agent-skills · Python

    20
    agent-skillsai-agentsclaude-codecode-reviewcodexdebuggingdeveloper-tools
  • Open-source projects built on TypeSafe's Jev decision model: open replicas, agents, dev tools, SDKs and MCP servers, apps. By type, each security-graded. English / 中文.

    zhuyansen/awesome-typesafe-jev

    20
    ai-agentsawesome-listdecision-modelmcp
  • Piloto de agentes de backoffice: LLM gera e raciocina, Jev (TypeSafe AI) decide, roteia e verifica

    lucianoon/backoffice-agents · Python

    20
    python
  • A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse

    elpumberto/barrunto · TypeScript

    20
    typescript
  • Measure when to use Jev and other models on your data, then route accordingly.

    FirasSX914/calibre · Python

    20
    pythonbenchmarkcalibrationconfidence
  • Jev Bayes, No? Testing TypeSafe AI's Jev against Bayesian-optimal strategies, and testing if Jev can effectivly use Bayesian priors.

    TomRichner/can-jev-bayes · Python

    20
    python
  • Jev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API (mirror of opencode-openjev, live-only MCP)

    darwintechlab/claude-jev · JavaScript

    20
    javascript
  • Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.

    Shakibuzzaman3104/claude-jev-funnel · Python

    20
    classificationclaude-codeclaude-code-pluginclaude-skillsllm-toolsopenrouter
  • VS Code Codex Plugin for Jev-gated tool output integration

    PhilippElhaus/Codex-Decision · Rust

    21
    codexpluginpython
  • Evidence selection and quota-aware recovery for Codex. Optional Jev reranking, local privacy controls, exact source reads. Keep your coding model.

    Hyper-AI-Lab/codex-jev · JavaScript

    20
    ai-codingcodexcontext-engineeringcontext-managementdeveloper-toolsmcpmodel-context-protocol
  • AI model routing for Codex subagents. Let Jev choose the model and reasoning effort for each mission, using your own task profiles.

    guilhem/codex-subagent-router · JavaScript

    20
    agent-orchestrationagentic-aiai-agentscodexcodex-pluginllm-routing
  • Safe Python-like script node with a System One decision model: ask yes/no, choice, and score questions via TypeSafe AI's Jev API, with local GGUF LLMs as a fallback. Multiple inputs and outputs let one node handle math, logic, text editing, conditional routing, resolution selection, filename generation, and more.

    kantan-kanto/ComfyUI-ScriptFlow · Python

    21
    python
  • A Taboo-style parlour game for design systems, refereed by Jev (TypeSafe System One model)

    southleft/component-charades · TypeScript

    20
    design-systemsgamenextjstypescript
  • A library to chain Jev calls, for the deranged and enlightened

    Fox-Islam/composable-jev · PHP

    20
    php
  • Industrial-grade Decision Foundation Layer for System One Game-Playing Models (Jev / NanoJev)

    dengyie/decidex · Python

    20
    python
  • Open, CPU-sized Jev-style (System One) decision model: situation + question + options → calibrated probabilities. 122M, ~20 ms on one CPU core, runs in your browser.

    amyrmahdy/decima · Python

    20
    calibrationdecision-modeljev-alternativemultilingualonnxtyped-decisions
  • Turn context into typed decisions and pre-declared actions.

    youyo/decio · Go

    21
    automationclaude-codeclidecisiongohooks
  • Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.

    Barneyjm/decision-circuits · Python

    21
    ai-agentscalibrationdecision-circuitsguardrailslangchainllmpython
  • Rate and spend limits for code that calls Jev and other decision models

    zachlandes/decision-gate · JavaScript

    21
    javascript
  • Use DeepSeek/llamacpp like Jev

    lenML/deep-jev-seek · TypeScript

    20
    apideepseektypescript
  • DGUI-HyperMem (DeckerGUI HyperMemory) - self-hosted hybrid memory MCP server on Cloudflare Workers with a JEV (Choice/Noul/Score) reasoning layer and a HuggingFace training-brain flywheel.

    ctaxnagomi/dgui-hypermem · TypeScript

    20
    ai-agentscloudflare-workersd1deckerguilong-term-memorymcpmcp-server
  • High-performance verbatim context compaction for coding agents (Claude, Codex, Antigravity, Gemini, OpenCode)

    satiricalguru/Fast-Jev-Agents · TypeScript

    20
    ai-agentsantigravityclaude-codecontext-compactiongeminillmopenai-codex
  • Fork of tamaratran/fast-jev-compaction: Jev via OpenRouter with zero data retention (zdr, data_collection: deny)

    ingebyd/fast-jev-compaction-openrouter · TypeScript

    20
    typescript
  • Use Jev to review a PR diff against the ten rules of Five Lines of Code

    jamescazzetta/five-lines · Rust

    20
    clicode-reviewfive-lines-of-coderefactoringrusttree-sitter
  • A verified browser agent: a cheap Jev guard (evidence-checked completions, a destructive gate) in front of any LLM browser driver, with Jev taking the mechanical steps in dual mode. Built on browser-use; every number pre-registered and measured.

    Tom-R-Main/Footwork · Python

    21
    browser-agentbrowser-automationbrowser-usedual-processllm-agents
  • Ask Jev typed questions about text and get calibrated probabilities back, then turn them into decisions with fuzzy rules (AND, OR, NOT, hedges, Mamdani outputs) and draw the rule base as SVG. A CLI and a Rust library (native and wasm32).

    dsaad68/fuzzy-jev · Rust

    20
    agent-skillsagent-toolsclicli-toolfuzzyfuzzy-logic
  • Decision infrastructure for autonomous software engineering, powered by typed System-1 decision models (Jev). No heuristic fallbacks - real, auditable model decisions.

    ApexYash11/Gatewise · Python

    20
    autonomous-agentsdecision-makingfastapigithub-appllmobservability
  • Hybrid AI Architecture on Google Cloud: Sub-100ms Gateway with TypeSafe Jev (System 1) and Vertex AI Gemini (System 2) on Cloud Run

    rominirani/gcp-gemini-decisions-hybrid-gateway · Python

    20
    html
  • Select Git changes for staging with a plain-language description.

    ibrahemid/git-jev-stage · TypeScript

    20
    claude-codeclicoding-agentsgittypescript
  • 935gits
    Gits is a browser extension powered by Jev to search the leads data on the Google Maps

    satyawikananda/gits · TypeScript

    21
    browser-extensionvuetypescript
  • Godot 4.7+ addon that wraps TypeSafe AI's Jev System One HTTP API to evaluate game state.

    AlvianEka/godot-jev · GDScript

    20
    godotgodot-addongodot-enginegodot4
  • Client for TypeSafe's SystemOne API for Jev

    robertjndw/gosys1 · Go

    20
    go
  • Scores public job postings against my resume using TypeSafe's jev via the Vercel AI Gateway. Daily Vercel cron.

    mcgalleg/grokbot-jev-jobs · TypeScript

    20
    typescript
  • Judgments from TypeSafe Jev that read like Rust control flow: a yes/no is an if, a choice is an exhaustive match, a score is a comparison.

    pedro-pscunha/guideme-rust · Rust

    21
    api-clientasyncjudgmentllmobservabilityopentelemetry