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

  • Reproducible experiments evaluating Jev as an automated judge across benchmarks and tasks.

    carlaiau/judge-jev · TypeScript

    00
    evaluationinformation-retrievalllm-as-judgetrectypescript
  • DeepThink meets llm as judge. Use heavy prefill caching to run the same request in parallel and let Jev give you the best result.

    BingelsWorth/JudgeJev · TypeScript

    00
    typescript
  • Agent-friendly Go library and JSON-first CLI for TypeSafe AI's Jev and System One API

    Mentioum/judgement · Go

    00
    ai-agentscligo
  • Typed client, CLI and MCP server for TypeSafe's Jev (System One) judgment model

    Alberto-Codes/judgevet · Python

    00
    python
  • A typed, reviewable AI judgment map for contract analysis with TypeSafe.

    curajorge/judgment-map · JavaScript

    00
    javascript
  • 2606juna
    A lean Pi coding agent profile that keeps context small, with TypeSafe Jev pruning tool output

    safzanpirani/juna · TypeScript

    00
    ai-agentscoding-agentscontext-engineeringexallmpi-coding-agentprompt-caching
  • Skills used to analyze the current workflows/automations/agents and integrate jev if it helps!

    JyothiKumar03/just-jev-it · Python

    00
    python
  • 2608kahn1
    High-throughput, sub-20ms System 1 decision engine on LLM logits. Zero text generation, calibrated probabilities, vLLM prefix caching.

    Okura66/kahn1 · Python

    00
    decision-enginefast-inferencellm-inferencepaged-attentionprobability-calibrationpythonqwen2-5
  • Benchmarking TypeSafe Jev for reactive navigation of PAL's Kangaroo biped (MuJoCo + RL locomotion + YOLO)

    OscarMrZ/kangaroo-systemone · Python

    00
    python
  • kanji-reading-checker: TypeSafe Jev ecosystem repository.

    Masa1984a/kanji-reading-checker · TypeScript

    00
    typescript
  • A Jev-compatible System One decision model

    TriusAI/Kapteeni · Python

    00
    python
  • Japanese house keeper

    smapira/kaseifu · Rust

    00
    rust
  • 2613kblam
    kblam: the knowledge base for LLM-assisted mereology. it's a flat-file research/knowledge storage system with enforced organization (using heuristics, semantic similarity, and Jev evaluation) to prevent document drift, internal contradictions, incorrect data gleaned from reading superseded sections out of context, and other LLM bullshit. not done

    hungryboygeorge/kblam · Python

    00
    agent-memoryagentic-aiagentic-workflowknowledge-baseknowledge-distillationknowledge-managementknowledgebase
  • KenteiScript: a small JSON language for quizzes and tests, written by an LLM (DSL as Harness). People answer in their own words; a decision model (TypeSafe JEV) grades them. Includes MulmoKentei, a sample runtime on Cloudflare.

    receptron/kenteiscript · TypeScript

    00
    typescript
  • krillion-clone: TypeSafe Jev ecosystem repository.

    dylanydai/krillion-clone · TypeScript

    00
    typescript
  • 2616krino
    Krino (κρίνω) — probing, analysis, and replication toolkit for JEV-class decision models

    Oaklight/krino · Python

    00
    calibrated-probabilitydecision-modelkrinorerankerpython
  • Loopfour workflow steps rebuilt with Jev (TypeSafe) instead of an LLM

    jfelipeff/l4-jev-workflows · TypeScript

    00
    typescript
  • POC de estudo do Jev (TypeSafe AI): triagem de atendimento com decisões tipadas e confiança calibrada

    Alanmc021/laboratorio-jev · HTML

    00
    html
  • System One gateway with Lambda and Jev

    saddam-azad/lambda-decide · TypeScript

    01
    awsaws-lambdatypescript
  • LaneBreak — support ticket priority+routing via TypeSafe Jev

    ndolinschi/lanebreak · TypeScript

    00
    typescript
  • laptop-voice-control: TypeSafe Jev ecosystem repository.

    Soumya-prog-tech/laptop-voice-control · Python

    00
    python
  • A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.

    0x963D/last-exit · JavaScript

    00
    javascript
  • laya-api: TypeSafe Jev ecosystem repository.

    benwyrosdick/laya-api · Python

    01
    python
  • Local computer use on macOS with Laya decisions — read any window's Accessibility tree, let a local System One model pick the control, execute via cua-driver. No screenshots, no vision, $0. Sibling of laya-browser-agent.

    ChenneyZhuang/laya-computer-use · Python

    00
    accessibilitycomputer-usecuadesktop-agentlayalocal-firstmacos
  • Guardrails de input, tool call y output para agentes de IA con un modelo System One tipo Jev (laya-pt-es-typed) autoalojado en una NVIDIA L4: 5 ms por check frente a 140 ms de un LLM-as-a-judge.

    javimp2003/laya-guardrails · Python

    00
    ai-safetyfastapiguardrailslayallm-agentsllm-as-a-judgenvidia-l4
  • laya-voice-browser: TypeSafe Jev ecosystem repository.

    VIVAAN-DHAWAN/laya-voice-browser · JavaScript

    00
    javascript
  • 2627leash
    Jev-powered guardrail that keeps a coding agent's output quality on a short leash: judges every turn against your un-lintable project rules and tells it which one it broke. Ratcheted, advisory, never a gate.

    CMaintz/leash · TypeScript

    00
    agent-hooksai-agentsclaude-codeclicode-qualitycode-review
  • C++17 library for typed semantic operators, confidence-aware decisions, flows, filtering, and reranking, with TypeSafe/Jev integration.

    jasonduncan/libsemop · C++

    00
    c++
  • top down arena shooter where jev picks each bot's next position from options a planner lays out. code aims, paths, and fires. a small experiment in putting a fast decision model at the top of a game controller.

    ak2k2/liljevduel · JavaScript

    00
    javascript
  • LinkedIn feed AI-slop detector using TypeSafe Jev API

    pawelmamcarz/linkedin-ai-slop · TypeScript

    00
    typescript
  • linkedin-radar: TypeSafe Jev ecosystem repository.

    ganeshariyur-web/linkedin-radar · TypeScript

    00
    typescript
  • 2632Lintel
    A change gate for AI coding agents: the agent proposes, TypeSafe's Jev reviews, and you approve before any code is written. Works with Claude Code, Codex, Cursor and Gemini CLI.

    Capzay/Lintel · Go

    00
    go
  • A writing editor that re-scores 15 typed rubric dimensions on every typing pause — one Jev System One call per pause, ~$0.000004 each.

    jose-troche/live-rubric · TypeScript

    00
    typescript
  • A Rust implementation of the System One API for structured question answering with DiffusionGemma and llama.cpp (OpenJev - Open, Jev Compatible).

    zojeda/llama-cpp-system-one · Rust

    00
    rust
  • llm2jev: TypeSafe Jev ecosystem repository.

    smanx/llm2jev · HTML

    01
    html
  • 2636lmr-rs
    lmr-rs: TypeSafe Jev ecosystem repository.

    faulker/lmr-rs · Rust

    00
    rust
  • local-jev: TypeSafe Jev ecosystem repository.

    nohunt-bot/local-jev · Python

    00
    python
  • local-judge: TypeSafe Jev ecosystem repository.

    alanfong93/local-judge · Python

    00
    python
  • local-laya: TypeSafe Jev ecosystem repository.

    binbandit/local-laya · TypeScript

    00
    typescript

2601–2650 of 3056