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

  • Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

    aaddrick/building-with-typesafe-jev · Python

    15612
    agent-skillsai-agentscalibrationclassificationclaude-codeclaude-code-plugin
  • Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

    leepokai/jev-guard · JavaScript

    15325
    javascriptai-agentsclaude-codecodex
  • Automatic project memory for Claude Code. Also works with Cursor and Codex.

    Avinash-jetwani/jevmem · TypeScript

    1518
    ai-memoryclaude-codecodexcursordeveloper-toolsmcp
  • an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

    kyegomez/open-jev · Python

    15127
    anthropicattentionchatgptclaudegpttransformers
  • A source-backed Jev / System One knowledge map: projects, papers, evaluations, robotics, and social discovery.

    Promethe-us/awesome-jev

    14913
    ai-agentsai-researchawesome-listdecision-modelembodied-aillm-resourcesmachine-learning
  • Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.

    UditAkhourii/quicksilver · JavaScript

    14212
    ai-agentsclaudeclaude-codedeveloper-toolsllmskillstokens
  • Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.

    Dicklesworthstone/skillranker · Rust

    14212
    ai-agentsskills
  • grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.

    keltokhy/jgrep · Python

    1415
    cligrepopenroutersemantic-searchpython
  • Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.

    kevinbadi/jev-voice · Python

    13824
    python
  • Open Jev implementation with custom finetuning

    daseinlabs/open-jev · Python

    13826
    python
  • Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

    Shanghua-Gao/RSI-Jev · HTML

    13712
    ai-agentsautonomous-researchdecision-modelllmrecursive-self-improvementtyped-decisions
  • Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

    Ying-Kai-Liao/jev-browser · JavaScript

    13625
    javascriptbrowser-automationllm-agentsmcp
  • Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

    qkal/Canny · TypeScript

    13518
    typescript
  • jev-pokemon: TypeSafe Jev ecosystem repository.

    christianmat/jev-pokemon · TypeScript

    13411
    typescript
  • A small extension that demos the combination of Jev x WebMCP

    sdras/jev-webmcp-extension · JavaScript

    1349
    chromeextensionextension-chromewebmcpjavascript
  • lint text in code by jev scorerer

    mizchi/jev-lint · TypeScript

    1324
    typescript
  • Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model

    savka777/jev-use · Swift

    13219
    accessibilityai-agentsbrowser-usecomputer-useharnessmacos
  • A linter to codify code taste using Jev

    codegirl-007/jevlint · Go

    1295
    go
  • A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework.

    peterfriese/system-one-foundation-models · Swift

    1264
    swift
  • hey-jev: TypeSafe Jev ecosystem repository.

    henryklunaris/hey-jev · Python

    12532
    python
  • MedJev: TypeSafe Jev ecosystem repository.

    JunMa11/MedJev · Python

    12523
    python
  • CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr

    nidhi-singh02/agent-router · TypeScript

    12316
    ai-agentsclaude-codeclicodexcodingdeveloper-tools
  • Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.

    openlayer-ai/jevals · Python

    12013
    ai-agentsevaluationguardrailsllmllm-evaluationragas
  • Bounded TypeSafe Jev workflows for coding agents.

    devagrawal09/stanley-code · TypeScript

    1207
    typescript
  • OpenDecision is an open-source semantic decision engine like typesafe's jev.

    deepanwadhwa/OpenDecision · Python

    1163
    automationnlinli-taskspython
  • Curated Jev resources and runnable examples for typed AI decisions.

    AppitStudio/awesome-jev · Python

    11526
    pythonawesome
  • Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.

    marcreichel/laya-php · PHP

    1152
    classificationdecision-enginedecision-modeljev-apilaravel
  • A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.

    GhalebDweikat/winnow · Python

    11512
    ai-agents
  • Using Jev as an evaluator.

    danielgshea/jev-as-a-judge · Python

    11417
    python
  • Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.

    nassim-arifette/jevgrep · TypeScript

    11412
    ai-agentsclicode-navigationcode-searchcoding-agentsdeveloper-toolsmcp
  • Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit

    ChetasLua/jevmeter · Python

    11313
  • High-throughput synthetic and pretraining dataset sifter for TypeSafe Jev. Rust streaming core, Parquet and JSONL I/O, typed Choice/Score/Noul judgments, speculative fan-out, 24.0 rows/sec measured.

    AkashPriyadarshii/jev-curate · Rust

    11214
    arrowclidata-cleaningdata-engineeringdataset-curationeval-harnessfine-tuning
  • Codebase search powered by Jev from @typesafe-ai

    ellipsis-dev/blink · TypeScript

    10510
  • TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

    PerryLink/jevcore · TypeScript

    1051
    ai-agentscordisdecision-modeldeepseekdeepseek-harnessdshdsh-plugin
  • Open-source AI email triage for Gmail. Sorts your inbox into Needs reply, Updates, Promos, Sales and Spam with Jev, TypeSafe AI's decision model, via Vercel AI Gateway. Read-only, runs locally, 1,000 emails in about a minute for 3 cents.

    fazlerocks/jevmail · TypeScript

    1059
    ai-email-assistantai-sdkemail-classificationemail-sorteremail-triagegmailgmail-api
  • Free Rust SEO and GEO toolkit powered by TypeSafe Jev: 58-rule audits, site crawls, AI citation checks, rank drift, CI gates, 15-tool MCP. Zero cost.

    AkashPriyadarshii/jev-seo · Rust

    10217
    ahrefs-alternativeanswer-engine-optimizationclaude-codeclicoding-agentsgenerative-engine-optimizationgeo
  • A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev.

    pithings/advocaat · TypeScript

    1012
  • 收集全网优秀 case 的收藏库 | A curated collection of excellent cases from across the web (TypeSafe Jev / System One).

    Hiwoniu/Jev-Case · TypeScript

    1005
  • Micdrop is a set packages for node and browser that simplify voice conversations with AI systems.

    Godefroy/micdrop · MDX

    978
    mdx

101–150 of 3054