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

  • Search code and text by meaning with natural-language grep, powered by Jev.

    YehuiTang0316/jev-nlgrep · TypeScript

    40
    ai-agentsgrepinfrastructureragsemantic-searchtypescript
  • jev-plays: TypeSafe Jev ecosystem repository.

    mansicer/jev-plays · Python

    40
    python
  • Predict another skill's next closed decision with TypeSafe Jev — without running that skill.

    DanielKillenberger/jev-predict-skill · HTML

    40
    html
  • Rerank, filter, and compress JSON search results with TypeSafe AI's Jev.

    shinpr/jev-reranker · Rust

    41
    clicontext-compressiondeveloper-toolsinformation-retrievalllmragreranker
  • Jev Research Index is a bilingual catalogue of papers, software projects, interviews, public analyses, demonstrations, and social-media material related to Jev, the TypeSafe AI System One typed probabilistic decision model.

    AgenticAPP-Web/Jev-Research-Index · JavaScript

    41
    javascript
  • Local-first Markdown memory alignment and source-linked search with optional Jev judgments

    fellowship-dev/jev-second-brain · Python

    41
    knowledge-managementlocal-firstmarkdownobsidianrerankingsecond-brainpython
  • Semantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.

    caiovicentino/jev-shield · JavaScript

    40
    javascriptai-safetymcpprompt-injection
  • Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.

    himomohi/jev-skill-router · Python

    41
    agent-skillsclaude-codecodexcontext-engineeringllmmcppython
  • Practical agent skills and examples for building with Jev. API setup, routing, ranking, and evidence checks.

    laguagu/jev-skills

    41
    agent-pluginsagent-skillsclaude-codecodexevidence-verificationjavascriptllm-evaluation
  • Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines

    bitnovus/jev-spam-eval · Jupyter Notebook

    41
    jupyter-notebook
  • Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.

    hamakyo/jev-starter · TypeScript

    41
    confidence-routingdecision-enginedecision-workflowsfallbackhuman-in-the-loopllm
  • jev-trading: TypeSafe Jev ecosystem repository.

    EthanAlgoX/jev-trading · TypeScript

    40
    tradingtypescript
  • Uses typeful jev, zero sync to pull and sync large repositories for issue triage

    cephalization/jev-triage · TypeScript

    40
    typescript
  • Open-weight step verifier for computer-use agents: calibrated ground/skip/effect/done judgments from screenshots in ~160 ms, plus a benchmark with environment-derived labels

    sseanliu/Jev-Vision · Python

    40
    python
  • Telegram channel X-ray: Jev judges a year of posts, you get a card. One Cloudflare Worker.

    gaborishka/jev-wrapped · JavaScript

    42
    cloudflare-workerscontent-analysisd1openroutertelegramtelegram-channel
  • Jev walks a real Pokémon FireRed ROM.

    daniel4x/JevEmon · HTML

    40
    ai-agentsgbamgbapokemonhtml
  • Automated PR review pipeline using Jev (TypeSafe AI) as a millisecond decision layer over an LLM reviewer

    T7NCKE/Jevest · TypeScript

    40
    typescript
  • Claude Code plugin that scores how well you prompt a coding agent, and shows whether your habits are improving. Runs on TypeSafe's Jev model. Zero added latency.

    CrowdLinker/JevPromptCoach · TypeScript

    42
    ai-coding-assistantclaude-codeclaude-code-plugincode-qualitydeveloper-toolsllmprompt-engineering
  • Jev-guided monkey tester: $0.35 and 5 minutes to find missing features, validation gaps and dead controls before QA

    Todmy/jevqa · Python

    40
    github-actionsllmplaywrightqatestingpython
  • DeepSeek proposes the next token, TypeSafe's Jev chooses it: a decision model used as a sampler

    blingdivinity/jevseek · Python

    40
    deepseekllmsamplingpython
  • Teach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.

    lazniak/jevskill · Python

    41
    agentic-aiai-agentsclassificationclaude-codecodexcoding-agents
  • A Medplum Provider + Jev integration demo for detecting conflicts in clinical notes

    vintasoftware/medplum-provider-jev · TypeScript

    41
    healthcarehipaamedplummodalrxnorm
  • Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.

    Grivn/mnemon-memory-agent · TypeScript

    40
    agent-memoryai-agentscontext-engineeringdeepseek-harnessdsh-plugindual-processllm-agents
  • Three measured experiments on RAG hallucination: quote-checking, TypeSafe's Jev, and IBM's STAIR. 850+ graded questions, raw responses included.

    aryanchauhanoffical/no-hallucination · Python

    40
    benchmarkevaluationhallucinationllmragretrieval
  • 725omg
    A System One style decision model runtime in Rust.

    bokuweb/omg · Rust

    40
    rust
  • Continuous verbatim context pruning for OpenCode, powered by TypeSafe Jev. Port of fast-jev-compaction adapted to OpenCode's context hook.

    hoshinodis/opencode-context-pruner · TypeScript

    40
    ai-agentscontextcontext-engineeringcontext-windowllmopencodeopencode-plugin
  • Fast and cheap agent evals. jev as judge.

    memovai/openevals · TypeScript

    40
    ai-agentsevaluationlangchainlangfuseobservabilitytypescript
  • Open, local, zero-cost reimplementation of the Jev decision layer for job postings

    DECRUX9812/openjev · Python

    40
  • AI life-and-civilization simulation: TypeSafe Jev makes every decision (typed, probabilistic, auditable); LLMs plan — OpenAI-compatible APIs, local models (Ollama, LM Studio), Claude Code, Codex.

    JacquesGariepy/ORIGIN-CIVILIZATION · HTML

    40
    ai-agentsartificial-lifeclaude-codecodexllmlm-studio
  • 730otto
    Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning.

    NobleSpartan6/otto · TypeScript

    40
    typescript
  • paseo-spacedock: TypeSafe Jev ecosystem repository.

    audreyt/paseo-spacedock · TypeScript

    40
    typescript
  • Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.

    nourhelmi/pi-jev-compaction · TypeScript

    42
    context-engineeringpi-extensionpi-packagetypescript
  • Pi extension: auto-approve routine Bash commands with a System One (Jev) decision model, escalate the rest to a human

    Davidasx/pi-typesafe-approve · TypeScript

    40
    approvalpi-extensiontypescript
  • Experimental plugin to convert protobuf into Jev code

    bufbuild/protoc-gen-jev · Go

    40
    golanjev-aprotobuprotocprotoc-pluginpythontypescript
  • Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each

    adtyavrdhn/pydantic-jev-examples · Python

    41
    python
  • Jev-style typed decisions from Qwen3.5-2B logits — one forward pass, zero decoding, zero fine-tuning.

    Embodied-AI-System/Qwen3.5-OneForward · Python

    41
    fastapilogitsqwenqwen3-5self-hostedtransformers
  • Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.

    ursuciprian/reflex · JavaScript

    40
    agent-securityai-coding-agentsautonomous-agentsclaude-codeclaude-code-hookscodexcodex-cli
  • Self-hosted gateway for LLMs and decision models. Claude Code, Codex, OpenCode and any OpenAI/Anthropic SDK app reach any provider (OpenRouter, Groq, Ollama…) with context pruning; Jev and open-rlcd System One decisions get audit and calibration. Live dashboard, single Go binary.

    JimmyWesley/rlcd-gateway · Go

    41
    ai-gatewayanthropicclaude-codecodexcoding-agentscontext-pruningdecision-model
  • Testing lib for asserting the real requirement.

    mondaychen/semantic-assert · TypeScript

    40
    ai-sdkplaywrightplaywright-bddtestingtesting-toolstypescript