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

  • Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs

    wondertwins/jev-benchmark · Python

    81
    python
  • Community-maintained history of Jev / TypeSafe System One APIs, SDKs, agent guidance, and engineering best practices.

    chenrui333/jev-docs · Python

    80
    agentic-aiai-agentsai-engineeringdeveloper-toolsdocumentationllmsdk
  • Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels

    inanna-malick/jev-dsl · Haskell

    80
    haskell
  • Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.

    Nainish-Rai/jev-frontend-qa · Python

    80
    browser
  • Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.

    arunav25/jev-mcp · JavaScript

    80
    javascript
  • TypeSafe Jev (System One) にブラウザ上のマインスイーパーを解かせるデモ

    comoc/jev-minesweeper · JavaScript

    81
    javascript
  • 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
  • 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
  • jev-vllm: TypeSafe Jev ecosystem repository.

    umianta/jev-vllm · Python

    81
    python
  • Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities

    cablehead/jev.nu · Nushell

    81
    nushell
  • 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
  • Unofficial Go client for the TypeSafe AI System One API (Jev) — typed questions in, calibrated answers out.

    devbackend/jevgo · Go

    80
    api-clientclassificationgollmsdk
  • Pac-Man driven by the jev decision model

    joch/jevman · TypeScript

    815
    pacman-gametypescript
  • An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support.

    NSStudent/JevSwiftSDK · Swift

    80
    api-clientasync-awaitioslinuxmachine-learningmacos
  • Record linkage for economists: write the match rule in plain English, get a probability per pair, audit it, cite it. Python, CLI, Stata and R.

    keltokhy/jlink · Python

    81
    economicsentity-resolutionfuzzy-matchingrecord-linkagestatapython
  • LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

    WiktorB2004/llama-index-jev · Python

    82
    llamaindexpostprocessorpythonragrerankerselector
  • Turn any local LLM into a Jev-style System One decision engine: type-safe answers with raw softmax probabilities. 100% offline, zero API cost.

    lookski/openjev · Python

    83
    classificationdecision-modelhugging-facellmllm-inferencelocal-llmsoftmax
  • Question-guided evidence highlighting for research papers, powered by Jev.

    YiLight0/paperfocus · JavaScript

    82
    javascript
  • 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
  • Emoção da fala em tempo real: transcrição ao vivo com Gemini 3.5 Transcribe Live e seis emoções avaliadas pelo Jev (TypeSafe) a cada 0,5 s. Projeto aberto da illumi.

    illumi-ai/sentimento-em-tempo-real · TypeScript

    82
    geminiportuguesreactrealtimesentiment-analysisspeech-emotion-recognitionspeech-to-text
  • Jev Playground

    sugarforever/tryjev · Svelte

    85
    svelte
  • Confidence-gated incident routing with TypeSafe Jev

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

    81
    python
  • TypeSafe Jev Playground - idiomatic .NET port of typesafe-ai/typesafe-sdk-js v0.6.0

    laurentkempe/TypeSafeJevPlayground · C#

    80
    c#dotnet
  • zanity: TypeSafe Jev ecosystem repository.

    benomahony/zanity · Zig

    80
    zig
  • zod-jev: TypeSafe Jev ecosystem repository.

    jomatsu/zod-jev · TypeScript

    80
    typescript
  • High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking

    opaielsheikh/ai-elo-ranker · Python

    72
    python
  • Curated Jev and System One papers, models, datasets, benchmarks and SDKs, with versioned sources and transparent verification levels. English / 中文.

    reacher-z/Awesome-Jev · HTML

    71
    ai-agentsawesomeawesome-listbenchmarkcalibrationcurated-listdecision-model
  • A curated, auto-updated list of System One decision models and open Jev alternatives: Laya, Kev, Von, Decider, Tev1 and more.

    yanng981/awesome-system-one · JavaScript

    70
    awesome-listclassificationdecision-modellayamachine-learningjavascript
  • A Go TUI that uses Jev to classify documents, assess sensitivity and urgency, and determine whether action is required.

    glamboyosa/docket · Go

    70
    bubbleteabyokgotui
  • Library of specialized IT domain agents following Anthropic's effective agent design patterns

    chrishuffman5/domain-expert · Shell

    73
    shell
  • 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
  • Fast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev. Catches leetspeak, character spacing, and romanized profanity across languages including Kannada, Telugu, Tamil, Hindi, and Bengali. ~50-500ms latency.

    ItisShikhar/gg-friggin-ez · TypeScript

    70
    bad-wordscontent-moderationgame-chathindihinglishindic
  • 534gut
    Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.

    Kungie/gut · Python

    70
    llmpythonsmall-language-modelszero-shot-classification
  • 535jev
    A Go client for the TypeSafe AI's System One API and its model, Jev.

    kataras/jev · Go

    73
    ai-codingai-toolsgo
  • Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.

    Foadsf/jev-for-engineers · Python

    70
    pythoncadcaecalibrated-confidence
  • A helper which use JEV to play ra2web(WannaFire Version)[王二火大]

    ra2web/jev-helper · JavaScript

    74
    javascript
  • Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence

    mahlernim/jev-korean-benchmark · Python

    70
    python
  • A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval

    y0usaf/jev-lm · TypeScript

    72
    typescript