Awesome JEV

Search Jev / System One projects and read their recorded inclusion evidence.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)

Claude Code

claude mcp add --transport http awesome-jev 'https://awesomejev.cc/api/mcp'

JSON configuration (Claude Desktop, Cursor, VS Code)

{
    "mcpServers": {
        "awesome-jev": {
            "type": "http",
            "url": "https://awesomejev.cc/api/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents

Awesome JEV
Contents
Agents & automation
Browser & computer use
SDKs & integrations

Awesome JEV

A curated list of TypeSafe Jev / System One ecosystem projects — official SDKs, agent skills, browser & computer-use demos, MCP connectors, routers, and community awesome-lists. Independent open-source typed-decision alternatives are listed separately and are not presented as official or drop-in compatible. The site groups GitHub projects by primary use and presents Jev news separately.

Site: awesomejev.cc · Projects: data/github.json · News: data/news.json

Docs: Architecture · Data model · Collector · Contributing

Agents & automation
Browser & computer use
SDKs & integrations
Developer tools
Research & evaluation
Learning & resources
Project directories
Apps & demos
Open-source alternatives
Other
Site
Automated updates
Contributing
License

Agents & automation

**cua** - Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation. · Rust
**composio** - Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action. · TypeScript
**pydantic-ai** - How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. · Python
**baml** - The programming language for agents · Rust
**jev-trader** - One AI trade decision every Monad block — Jev on Kuru MON-USDC. · TypeScript
**openharness** - Follow your curiosity. Build across disciplines. Open-source software and hardware for polymaths in the making. · TypeScript
**hermes-jev-skills** - Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents $also Claude Code and Codex$ · Python
**foreman** - Software Factory Foreman based on TypeSafe Jev model. · Python
**pi-extensions** - A monorepo of Pi Coding Agent extensions · TypeScript
**jev-router** - Route to the cheapest model in Claude Code for your task using jev-router. · JavaScript
**JevRouter** - A lightweight Jev-powered router for models, tools, and subagents · TypeScript
**typesafe-mario** - A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state. · Python
**jev-gateway** - An easy way to use jev with your coding agent for tool calling reasoning · TypeScript
**deepdoc** - Deep research tool for local knowledge base. · Python
**jev-codex-router** - Per-turn model & reasoning routing for Codex, driven by Jev $TypeSafe System One$: picks the model, thinking depth and speed mode for every turn. · JavaScript
**jev-dsh-decision** - Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。 · JavaScript
**dsh-jev-plugin** - Native DeepSeek Harness $DSH$ plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selection, supervision, corrections, and approvals. · JavaScript
**OneJev** - 🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forward pass. · Python
**Jevmind** - Jevmind: TypeSafe Jev ecosystem repository. · Python
**neo4jev** - Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships · Jupyter Notebook
**jev-social** - Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports. · JavaScript
**system1-agents** - System 1 decision models $Jev, Laya, Cua-S1$ as brain for agents: Browser use, computer use, games and robotics · Python
**pi-warden** - Guardrails for Pi built on pi-typesafe that steer the agent instead of interrupting you: Jev judges irreversible and off-task tool calls, detects stuck loops, checks unverified done claims, flags slop · TypeScript
**pi-jev** - TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev\_ask for typed, calibrated answers · TypeScript
**skillranker** - 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. · Rust
**jev-pokemon** - jev-pokemon: TypeSafe Jev ecosystem repository. · TypeScript
**quicksilver** - 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. · JavaScript
**jev-voice** - Talk to your Mac. Local whisper.cpp + one Jev $TypeSafe$ call per command + macOS automation. · Python
**jev-guard** - 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. · JavaScript
**stanley-code** - Bounded TypeSafe Jev workflows for coding agents. · TypeScript
**agent-router** - CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdr · TypeScript
**winnow** - A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context. · Python
**jev-kit** - Everything you need to run TypeSafe's Jev with Claude Code: a tool-call guard, tier guard, file search, browser agent, review, belay, compaction and installers. · Python
**jev-libero** - Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks. · Python
**jevcrawl** - MCP server and CLI that crawls websites for AI agents: finds the answer page 2x more often than Crawl4AI, 10x cheaper per answer than letting Claude crawl. · Python
**openthai-systemone** - OpenThai-SystemOne: open Thai + English System One decision model $0.8B, 256-way slot head, Apache-2.0$ · Python
**pi-jev** - Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev · TypeScript
**jev-use** - Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev $TypeSafe's judgment model$ — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM · JavaScript
**laya-jev-GraphRAG** - A database-agnostic Agentic GraphRAG framework using swappable System One models $local Laya / cloud Jev$. A plug-and-play intelligence layer featuring a complete 4-phase pipeline, continuous evaluation and custom A\* traversal for any graph database. · Python
**jev-sift** - Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification. · JavaScript
**hermes-nerve** - Nerve is a supervisory nervous system for Hermes agents, adding typed System One decisions, ranking, verification, token-aware oversight, and an opt-in tool gate powered by TypeSafe Jev or Open Source Laya · Python
**jevify** - An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments. · Python
**ask-jev-skill** - Skill for Hermes, and other agents, to ask typesafe's jev · Python
**jev-cua** - Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop. · Swift
**pi-jev-skill-picker** - Rank Pi Agent Skills for the current task with TypeSafe Jev · TypeScript
**claude-router** - Claude Code plugin that auto-picks the right model for each turn — micro, low, medium, or high tier — using Jev routing. · JavaScript
**jev-harness** - A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt. · TypeScript
**pi-jev-auto-mode** - Jev $TypeSafe System One$ backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made. · TypeScript
**dsh-jev-interceptor** - ⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件 · TypeScript
**edgejev** - 离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev · Python
**jev-agent-skill-router** - Typed, confidence-aware agent skill routing with TypeSafe Jev. · Python
**lev** - Jolt implementation of Laya non-autoregressive System 1 decision engine · Clojure
**evoke** - Software, by reflex. A sentence becomes a call of a small program, chosen by Jev, TypeSafe AI's classifier, and run only when it is sure enough. Reflexes are recipes anyone can write, share and improve. A CLI you talk to, a package manager for reflexes from git, and a TypeScript SDK. · Rust
**toolgate** - A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler. · TypeScript
**omo-jev-plugin** - Jev-powered decision support for OmO and senpi agents · TypeScript
**jevvy** - Jev-powered plugins for coding agents · TypeScript
**jev-recipes** - 200+ plug-and-play Jev recipes: small, calibrated AI decisions that route, grade, gate, compare, and label text for agents, RAG, support, code review, and music. Import from JavaScript or TypeScript, or call the CLI with JSON from any language. · TypeScript
**jevwire** - Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin $TypeSafe AI's Jev$ · TypeScript
**dsh-jev** - Jev-powered decision layer for DeepSeek Harness · TypeScript
**jev-usecases** - Production TypeSafe Jev $System One$ use-case harnesses with confidence-gated decision logic · Python
**JevLoop** - The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed. · TypeScript
**laya-browser-agent** - Local, open-source Jev alternative: browser agent decisions with Laya $System One model$ on your own machine. No cloud, no API key. Playwright/CDP, MCP-friendly. · Python
**gatekeeper** - Routes each request to the right AI agent or skill before your AI picks one. Your rules decide what code can; Jev $TypeSafe$ makes the typed call. Installs as Claude Code hooks. · Python
**agent-chaperone** - Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools. · TypeScript
**kibu** - kibu: TypeSafe Jev ecosystem repository. · TypeScript
**jcr** - A Jev-powered resolver for agent harnesses to find deterministic commands and their context in a nested capability tree. · JavaScript
**jev-skill-router** - Claude Code plugin: asks TypeSafe Jev which installed skill fits each prompt and logs the answer $shadow-first$. A working reference for the skill-suggestion cookbook on Claude Code — the README records why it is unlikely to help a strong model as a router. · Python
**switchboard** - An open-source, model-agnostic decision router for Claude Code and Codex. · TypeScript
**jev-bot** - JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default · Python
**jev-router** - Pass-through model router for Claude Code and Codex CLI that picks a model tier per human turn with Jev, TypeSafe AI's decision model · JavaScript
**Helm** - Route every coding task to the best AI agent on your machine — Claude Code, Codex, Cursor, Gemini CLI, Aider, OpenCode. Installs as a Claude Code plugin, Gemini extension, or Agent Skill. · Python
**Jev\_steer\_or\_queue** - Let TypeSafe Jev decide whether a message you send mid-turn should steer, queue, or interrupt your coding agent. Claude Code plugin; Codex CLI in testing. · Python
**pi-jev-router** - Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway · JavaScript
**jev-harness** - Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter job. · TypeScript
**duomind** - When Jev meets LLM -- Pair a small local LLM $System 2$ with Jev model $System 1$ to make small model more faster and accurate — OpenAI-compatible, private, and almost free to run in Kilo code and Cline. · Python
**jev-me** - jev-me is grill-me with jev
**ego-jev** - Jev $TypeSafe System One$ inner loop for ego-browser — one ~0.4s typed decision per DOM step instead of an LLM turn. Agent skill for ego lite. · TypeScript
**typesafe-skill-router** - TypeSafe $Jev$ skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn. · Python
**super-jev** - A small, extensible decision-to-action harness for TypeSafe Jev · Python
**jev-router** - Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM · Python
**jev-askable-arm** - Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives. · Python
**jev-apply** - Memory-backed job-application skill: Jev selects, an LLM writes only new text, Playwright fills. Greenhouse + Ashby. · JavaScript
**jev-mobile** - Fast structured Android control loops with TypeSafe Jev and Mobile MCP · Python
**openvons** - openvons $open-Jev$: 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド · Python
**pi-heed** - Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev. · TypeScript
**jev-ai-sdk-form-router** - Route form submissions to the right people with Jev and AI SDK. · TypeScript
**Augustus** - Agent skill: design judgment-assisted systems with TypeSafe Jev $System One$. Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT. · Python
**pi-quiet-ask** - TypeSafe Jev as the pi coding agent's quiet decision layer · TypeScript
**jev-harness** - jev-harness — Jev / TypeSafe related project · Python
**omp-jev-compaction** - Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter · TypeScript
**JevGPT** - JevGPT: Thinking Fast and Slow in Autonomous Research · TypeScript
**dsh-jev** - Jev $System One decision model$ plugin suite for DeepSeek Harness $dsh$ · TypeScript
**jevelry** - Use Jev everywhere to make & track decisions · TypeScript
**guardrails-md** - opencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policy · TypeScript
**chainlesschain** - chainlesschain: TypeSafe Jev ecosystem repository. · JavaScript
**pi-jev-model-router** - Route pi prompts to task-appropriate model tiers with TypeSafe Jev typed judgments. Budget-aware, with automatic fallback. · TypeScript
**JevFlow** - A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all. · Python
**jevmory** - Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies. · Python
**pi-jev** - Pi extension suite powered by Jev: selective context compaction and model routing · TypeScript
**fable-jev** - ⚡ Sub-100ms cognitive reflexes for autonomous coding agents. Powered by TypeSafe AI's Jev & get-fable. · TypeScript
**jevloop** - A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents. · Python
**jev-router** - LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call. · TypeScript
**opencode-jev-router** - Adaptive reasoning effort for OpenCode via Jev, with an in-process plugin and Responses API proxy · TypeScript
**jev-codex-bridge** - Model and reasoning routing for Codex Desktop and CLI, with a Windows service and validated updates · JavaScript
**jev-tool-router** - Jev-powered MCP tool routing for Codex · JavaScript
**jev-agent-authorization** - Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs · TypeScript
**codex-jev-router** - Portable Codex subagent-routing workflow using Jev Choice/Noul and local confidence gates, with a Sol fallback; invoked through project instructions rather than an automatic spawn hook. · JavaScript
**home-assistant-typesafe-conversation-agent** - A Home Assistant voice agent that decides with typed, calibrated judgements instead of an LLM. One ~300 ms call per command, and it asks when it isn't sure. · Python
**jev-mobile** - One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast\! · Python
**bicameral** - Hybrid coding harness: System 2 writes, System 1 $Jev$ runs reflexes. · TypeScript
**jcm-router** - Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone. · TypeScript
**hermes-switchyard** - Jev-powered decision plugin for Hermes Agent: automatic skill selection, policy-constrained model routing, typed assessments, and approval-gated computer use on Windows, macOS, and Linux. · Python
**typesafe-jev-incident-router** - Confidence-gated incident routing with TypeSafe Jev · Python
**jev-state** - Build and regression-test conversational state machines powered by Jev. Inspect decisions, capture failing conversations as tests, and export runnable TypeScript for your app. · TypeScript
**system-one-gemma** - Open-source Jev-style System One decision model. Gemma 3 270M with a scoring head — fast, calibrated decisions in a single forward pass. No text generation. Inspired by TypeSafe.ai's Jev. · Python
**jev-skillful** - 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. · TypeScript
**mastra-jev-moderation** - Input moderation for Mastra agents on TypeSafe Jev — one file · TypeScript
**opencode-auto-jev** - OpenCode plugin that adds an Auto $Jev$ virtual model which routes each prompt to a configured real model using TypeSafe AI $Jev$. · TypeScript
**jev-architect** - Find, design, and evaluate TypeSafe Jev decision loops. · HTML
**mcts-agent** - Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini · Python
**agent-fastpath** - Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev $System One model$. Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor. · TypeScript
**typesafe-mod** - Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident. · TypeScript
**domain-expert** - Library of specialized IT domain agents following Anthropic's effective agent design patterns · Shell
**jevme** - Talk to your Mac and it does it — in any app, while you're still talking. Open-source voice agent that gets faster the more you use it. · Python
**jev-skills** - Skills without the context tax. Claude Code and Codex plugin: TypeSafe's Jev decides on every turn which skills the model sees. Always-on context cost: 0 tokens. · TypeScript
**beadsort** - The intelligence layer for beads: typed, calibrated labels for your backlog · Python
**jev-judgment** - Agent Skill: send closed coding-agent judgments to TypeSafe Jev · Python
**reflex** - A coding agent and personal assistant with System One reflexes $TypeSafe Jev$ on top of the Pi coding agent · TypeScript
**jevcraft** - Jev-powered Minecraft bot · JavaScript
**limpet** - A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev. · Python
**jev-decision-layer** - Typed decision layer for coding agents — Claude Code, Codex, Antigravity, Hermes, VS Code. One MCP server, 20 tools, 36 recipes, per-provider calibrated gates. · Python
**jev-helper** - A helper which use JEV to play ra2web$WannaFire Version$\[王二火大\] · JavaScript
**jev-search** - Fast deep research for the pi coding agent: reads up to 100 pages in full per round, Jev keeps only the passages that answer your questions. · TypeScript
**wakegate** - Ask Jev whether a sleeping agent's wakeup is worth a full LLM turn before you resume it. A fail-open wake gate for long-running agents on Workers, Durable Objects and Node. · TypeScript
**jevriel** - Give your AI JEV wings. A skill and plugin to build with TypeSafe Jev, upgrade LLM-only workflows and measure the result. · JavaScript
**jev-router** - jev-router: automatic model and effort switching for Claude Code · Rust
**jev-market-reflex** - Fast typed AI decisions on live crypto markets using TypeSafe AI Jev. · TypeScript
**a0-typesafe-ai** - TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards. · Python
**typesafe-on-neon** - Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing. · TypeScript
**decisions-judge-mcp** - Typed decisions for AI agents as an MCP tool: yes/no probability $noul$, choice, and score in one fast request. Backed by the TypeSafe System One model. · JavaScript
**nitro** - Grok Build with TypeSafe Jev routing tool selection once per turn: 22 to 40% cheaper on the same tasks · Rust
**coding-orchestrator** - Orchestrator and subagent setups for Claude Code and Codex: routing, verification, and safe global installation. · Python
**jev-orc** - My JEV Orchestrator to supply my needs · TypeScript
**typesafe-computer-use-windows** - Windows port of typesafe-computer-use with Jev decisions, local OCR/UIA, and MCP host integration · Python
**jev-skills** - Jev-powered decision skills for Claude Code and Codex. Opt-in, advisory, fail-open. · Python
**jev-agent-toolkit** - Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents. · JavaScript
**jev-smart-router** - JEV Smart Router — a Databricks App that uses TypeSafe JEV to pick which model answers each message, then runs inference on the chosen Databricks Foundation Model API endpoint. · Python
**deepseek-harness-jev-pre-compaction** - A pre-compaction advisor for DeepSeek Harness. Runs before the standard \compaction-basic\ backend, using TypeSafe JEV to safely prune low-value tool results from model context. Original session events stay in the append-only log; only the model-visible view is replaced with compact markers or archive pointers to reduce context bloat. · TypeScript
**paseo-spacedock** - paseo-spacedock: TypeSafe Jev ecosystem repository. · TypeScript
**jev-predict-skill** - Predict another skill's next closed decision with TypeSafe Jev — without running that skill. · HTML
**ha-gutcheck** - Home Assistant integration that makes small judgment calls about your install · Python
**mnemon-memory-agent** - 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. · TypeScript
**jev-starter** - Typed, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps. · TypeScript
**jev-factorio-agent** - Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE · Python
**jev-harness-router** - Per-turn router for agent harnesses: one 350ms Jev call picks the model tier, effort, tools and skill, behind a hard deadline with a regex fallback. Claude Agent SDK adapter included. · TypeScript
**jev-oncall** - Incident triage on TypeSafe Jev — the model judges, plain code decides. Routing on probability distributions with a human-review middle band and fail-open defaults. · HTML
**jev-chat-gate** - A framework-independent participation gate for AI agents in group chats, powered by typed Jev decisions. · JavaScript
**docsignals** - Ask typed questions of your documents. Get structured signals for agentic workflows, with the page each answer came from. · TypeScript
**jev-claw** - Typed model routing for OpenClaw agents, powered by TypeSafe Jev · JavaScript
**reflex** - 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. · JavaScript
**jev-compaction** - A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline. · Python
**open-jev-approvals** - Binary approval gate for Codex and Claude Code — every intercepted tool call is reviewed by TypeSafe JEV and composed through a versioned local policy, with scoped authorization. · Go
**jev-royal** - TypeSafe / Jev community project: Amrit-Nigam/jev-royal. · TypeScript
**jev-decisions-hermes** - Jev Decisions Plugin for Hermes $and other AI Agents$: tool risk reviews, human approval recommendations, evidence checks, a local decision journal, local decision supervision, and learned corrections. · Python
**hermes-jev** - Hermes Agent plugin: route each turn to the one skill that fits, via TypeSafe Jev on the Vercel AI Gateway. Fail-open, opt-in, stdlib only. · Python
**skill-router-mod** - The skill-router mod: Jev picks and loads the skills each prompt needs. · TypeScript
**jev-skill-router** - Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool. · Python
**tiershift** - Shift every LLM call to the cheapest model that can handle it. Routing decided by TypeSafe Jev in ~180 ms. No training data. Policy in plain YAML. TypeScript and Python. · TypeScript
**typesafe-assist** - Home Assistant Assist conversation agent powered by TypeSafe's Jev $System One$ model · Python
**jev-mermaid** - jev-mermaid: TypeSafe Jev ecosystem repository. · JavaScript
**jevskill** - 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. · Python
**todo-jev** - ⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev $System One$ · Python
**jev-route** - jev-route: TypeSafe Jev ecosystem repository. · Python
**jev-gate** - Not every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary. · TypeScript
**jev-agent-hooks** - TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing · JavaScript
**astra-jev-harness** - Agent Skills for Codex Desktop and Claude Code, plus a Codex CLI harness. Jev-assisted context selection. / Codex Desktop・Claude Code向けAgent SkillsとCodex CLI用ハーネス。Jevでコンテキストを選別。 · Python
**jev-compaction** - Context compaction for Hermes sessions: every tool call scored by TypeSafe Jev; stale calls dropped, kept context stays verbatim. · JavaScript
**clay-jev-people-ranker** - Agent Skill and Python workflow for Clay lead scoring, B2B prospect qualification, and people-search ranking with TypeSafe JEV. · Python
**pi-fast-jev-compaction** - Verbatim context pruning for the pi coding agent, scored by TypeSafe Jev: stale tool calls and results are dropped or truncated, everything kept stays verbatim. · TypeScript
**jev-builder-loop** - Grok skill: Jev as a judgment sensor in a builder-agent loop $priors × probabilities → next act$ · Python
**jev-flash-router** - open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works · TypeScript
**pi-jev-task-router** - Per-prompt model routing for the Pi coding agent: classify each prompt with Jev, pick a model tier, and switch before the turn runs. · TypeScript
**mem-jev** - Deterministic procedural memory for agents · Go
**jev-android-super** - jev-android-super: TypeSafe Jev ecosystem repository. · Kotlin
**jev-nethack** - TypeSafe's Jev model plays NetHack 5.0: code lists the legal moves, Jev picks one, no LLM in the loop · Python
**jevselector** - OpenCode v2 plugin that uses Jev $TypeSafe AI$ to dynamically select relevant skills and tools per turn, reducing context window usage. · TypeScript
**risk-analysis-server** - An autonomous risk-monitoring MCP server. Define a risk profile — a topic, the geographic locations to watch, and the policy triggers that matter — and the server runs an agentic sweep: live web search scoped by a judgment model $Jev$, source scoring, and a Markdown briefing you can read from any MCP client. · TypeScript
**jev-uipath-coded-agent** - FINS demo: a UiPath coded agent for AML alert triage where every decision is made by TypeSafe's Jev model $Noul/Score/Choice$ instead of an LLM · Python
**home-assistant-typesafe** - Home Assistant conversation integration powered by the Jev / TypeSafe AI API for fast, structured intent routing and device control · Python
**astrbot\_plugin\_reply\_gate** - Decides whether a message should reach the LLM at all, using TypeSafe Jev choice probabilities. · Python
**jev-architect** - Makes Claude Code and Codex ask whether a step needs a generative LLM at all — or whether it belongs on Jev, TypeSafe's System One model. Architecture arbitrage before the code is written.
**switchboard-ai** - Adaptive multi-model AI orchestration runtime using Jev for cost-aware routing, confidence-based escalation, tool selection, and model execution · JavaScript
**dgui-hypermem** - 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. · TypeScript
**modelrudder** - Experimental local LLM router for OpenAI Codex CLI and Claude Code. Automatically selects models per task using TypeSafe Jev. Free, MIT-licensed, bring your own provider account. · TypeScript
**decidex** - Industrial-grade Decision Foundation Layer for System One Game-Playing Models $Jev / NanoJev$ · JavaScript
**lightjev** - Read pages with Lightpanda, decide where to go with Jev — a self-steering crawler for tiny budgets · Python
**pi-auto** - Automatically select thinking effort for each task useing Jev · TypeScript
**jev-py-integration** - Jev System one AI model, very fast decision making engine. Jev AI will use input tokens but no output tokens · Python
**JevTicktRouter** - A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev. · C#
**skillpick** - Pick the right agent skill for every prompt with TypeSafe's Jev. Hooks for Claude Code, Codex, Gemini CLI, Droid, OpenCode, Amp. · TypeScript
**openclaw-jev-plugin** - Jev as a message gate to determine if agents should respond · TypeScript
**opencode-intent-gate** - TypeSafe Jev-powered intent gate for OpenCode: confirm intent before the agent dives into underspecified requests. · TypeScript
**pi-jev-skill-suggestion** - Pi extension that removes the inlined skill list and asks TypeSafe Jev which skill to load · TypeScript
**langgraph-jev-router** - A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model $\Jev\$. It enables ultra-fast $sub-500ms$, schema-safe routing between specialized agents. · Python
**keeled** - keeled: TypeSafe Jev ecosystem repository. · TypeScript
**ask-jev** - Ultra-fast, fail-open advisory decisions and verbatim extractive reading view for AI coding agents and CLI pipelines · Python
**llm-lan-party** - A language model plays Unreal Tournament 99 on real Windows 98 hardware by answering small typed questions, several times a second. Any OpenAI-compatible model or Jev. · TypeScript
**toolgate** - Agent tool/MCP call gate — allow / ask\_human / deny via TypeSafe Jev · TypeScript
**opencode-jev-router** - opencode-jev-router: TypeSafe Jev ecosystem repository. · TypeScript
**ohmyjev** - Jev, batteries included, for Claude Code, Codex, pi and omp: no permission prompts for safe commands, long output trimmed, the right skill loaded, and destructive commands $rm -rf, force push$ or data exfiltration stopped until you say yes. · TypeScript
**actiongate-jev** - Open-source Jev tool-calling authorization gateway for AI agents: deterministic policy, exact-action single-use permits, MCP and HTTP enforcement. · TypeScript
**jev-scout** - Agent Skill that finds where TypeSafe Jev decision models would pay off in a codebase. Works in Claude Code, Codex, Cursor and other Agent Skills hosts. · TypeScript
**jev-cli** - Agent-facing command line for Jev, TypeSafe AI's System One model: ask typed questions, get calibrated probabilities. Unofficial, built on jev-sdk. · Rust
**jevarena** - JevArena — two Jev agents duel in click-only browser games $Browser Use + TypeSafe Jev$ · TypeScript
**Fast-Jev-Agents** - High-performance verbatim context compaction for coding agents $Claude, Codex, Antigravity, Gemini, OpenCode$ · TypeScript
**jev-bot** - Computer Use Agent developed with Jev · TypeScript
**jeffrey** - A coding agent CLI where Jev $TypeSafe System One$ or Laya decide what to do next and a configurable LLM does the work. · TypeScript
**Footwork** - 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. · Python
**ailerix** - Type-safe model router. Jev $System One$ banks each request to a typed catalog route. · TypeScript
**siege** - SIEGE: 200 people vs one agent. A typed action gate $TypeSafe System One$ that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026. · TypeScript
**jev-agent-kit** - jevkit: fast typed decisions for agents. CLI and MCP tools $route, triage, guard, grep, rank, compact, judge$ on TypeSafe Jev. Zero dependencies. · JavaScript
**paperclip-plugin-jev** - Community Paperclip plugin for Jev-powered issue triage and automatic routing. · TypeScript
**jevrouter** - Drop-in decision/routing layer powered by TypeSafe Jev $System One$ — typed Choice/Noul/Score routes with production safety gates. · TypeScript
**decide** - Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks. · Python
**jev-bouncer** - Claude Code plugin: a 3-cent bouncer for your agent's shell. Jev typed probabilities auto-allow routine commands, deny destructive ones, and flag prompt injection in tool results. · Python
**jevscript** - jevscript: TypeSafe Jev ecosystem repository. · JavaScript
**forge** - forge: TypeSafe Jev ecosystem repository. · Rust
**decision-circuits** - 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. · Python
**btx-skill-jev-judge** - Claude Code plugin and Python CLI: hand a judgment repeated over many items to TypeSafe's Jev, with redaction, rate limiting, a pilot and a flat-question check. · Python
**jev-hft-model-router** - jev-hft-model-router: TypeSafe Jev ecosystem repository. · Python
**decision-kit** - Agentic UI demonstrations for rapid, context-aware decisions with TypeSafe AI Jev, LLMs, and the GitHub Copilot SDK · JavaScript
**judging-with-typesafe** - Скилл для агентов Letta: суждения по критериям через TypeSafe System One $Jev$ · Python
**jevcore** - JevCore Agent — local coding harness $Jev decisions, Guard hard policy, MCP + CLI$ · JavaScript
**jev-triage** - Millisecond-class test-failure triage for coding agents: RETRY / FIX\_CODE / FIX\_ENV, powered by TypeSafe Jev. · Python
**jev-decision-maker-at-meteora** - Decision Maker at Meteora - a decision agent for Meteora DLMM liquidity on Solana. Named after Jev, TypeSafe AI's System One model $https://console.typesafe.ai/home$, which answers its typed Noul and Score questions. Ranks the live pool universe, runs live rug cards, and holds 3-5 pools under explicit hard gates and book rules. · Python
**taskpenny** - Frontier prices only for frontier work: each task goes to the cheapest model that does it well, a request is split only when that pays, and every result is checked. Decisions by Jev. · Python
**bouncer** - Jev-powered Judgment layer for Claude Code. Stops paying reasoning prices for if-statements: a PreToolUse hook scores every tool call against a YAML policy you own — allow / deny in ~100 ms, no LLM in the loop. TypeSafe Jev now, local models next. Dry-run by default, calibration table published. · TypeScript
**jev-triage** - Near-free GitHub issue triage powered by TypeSafe AI's Jev - typed, confidence-gated labels that escalate only the uncertain cases.
**jev-loop-detector** - Catch an AI agent stuck in a loop — Jev grades each step progress/repeating/stuck/escalate. Single-file, no build. Use free: jevtypesafeai.com/tools/agent-loop-detector · HTML
**jev-triage** - Jev, TypeSafe AI's decision model, triages every message before your OpenClaw agent's main model runs. · JavaScript
**grok-jev-router** - Jev decides, Grok Bot executes, humans control irreversible actions. A decision router for Grok Bot built on TypeSafe AI's Jev. · Python
**jev-usher** - The doorman for Claude’s context window. JEV-powered model routing and recoverable context filtering for Claude Code. · TypeScript
**jev-pi-skills** - pi extension: TypeSafe Jev decisions as tools $search, rerank, supervise, pick$ and hooks $skill select, compaction$ · JavaScript
**jev-harness** - Jev $TypeSafe$ as the decision layer for Claude Code: permission gate, skill routing, conditional instructions, effort-tiered subagents, context packs. Tested PoC with evals. · Python
**cribrix** - A precision-first RAG orchestrator: filters before it generates, verifies before it answers. · Python
**jev-voice-agent** - A realtime voice agent with no LLM in the loop: Deepgram Flux ends the turn, TypeSafe's Jev picks the reply, Deepgram Flux TTS speaks it. · TypeScript
**gev** - Jev from DiffusionGemma · TypeScript
**agent-harness-with-jev-llm** - A small multi-agent harness built around the pattern from LangChain's post: use a fast, non-generative "System One" classifier $TypeSafe AI's Jev$ for structured in-loop decisions -- routing and risky-tool-call gating -- and reserve a real chat LLM for the genuinely open-ended reasoning. · Python
**thinkdial** - thinkdial — per-task reasoning effort for Claude Code, decided by TypeSafe's Jev: main loop, Claude subagents and Codex delegations. Effort-only by design: model switches break the prompt cache. · TypeScript
**typesafe-as-a-judge** - Unofficial community MCP plugin for Codex and Claude Code using TypeSafe Jev for bounded routing, ranking, extraction, verification, and escalation · JavaScript
**jev-cua** - Voice-controlled Mac computer use on TypeSafe Jev: speech to typed decisions to verified accessibility actions, no screenshots to a big model · Swift
**jev-agent-skill** - Decisões tipadas em milissegundos com o Jev $System One da TypeSafe$ via OpenRouter — state + perguntas noul/choice/score entram, decisões calibradas saem. Validação pesada baseada nos conceitos do modelo, bandas auto/hitl/abstain, deteção de prompt injection e servidor MCP. Zero dependências $Node ≥20$. · Python
**android-jev** - MCP server and skill that let an agent drive an Android phone naturally over adb · Python
**jevmate** - A fast decision layer for coding agents: Jev ranks files, picks tests, sorts failures and reviews diffs, so the expensive model reads only what matters. CLI, MCP server and Claude Code plugin. · Python
**stepwarden** - Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept · TypeScript
**pi-jev-control** - System-One control plane for Pi Coding Agent powered by TypeSafe Jev. · TypeScript
**codex-subagent-router** - AI model routing for Codex subagents. Let Jev choose the model and reasoning effort for each mission, using your own task profiles. · JavaScript
**browserjev** - Low-memory autonomous web classification with HTTPX, Lightpanda and Jev · Python
**jev-skill** - jev-skill: TypeSafe Jev ecosystem repository. · JavaScript
**jev-router** - Jev picks the right Claude or OpenAI model, effort and skill for each prompt. Claude Code plugin + TypeScript/Python router + Codex launcher · TypeScript
**jev-dingtalk** - 钉钉信息 Jev 分拣器（jev-dingtalk）：把钉钉邮件与聊天分拣成 Now / Today / Queue / Ignore 清单——谁在等回复、谁需要人看一眼。dws 取数、Jev 分类、报告本地渲染，可直接作为 Agent 技能使用。\| DingTalk mail & chat triage with Jev. · Python
**Jev-Orchestrated-Decision-Mesh** - Jev-Orchestrated Decision Mesh $CIDM$: training-free GPT-6 Luna/Sol routing with checked gates, source-linked evidence, and reproducible benchmarks. Created by Kenneth Vic A. Caber. · Python
**pi-software-factory** - pi-software-factory: TypeSafe Jev ecosystem repository. · TypeScript
**karnak** - Jev picks Claude Code's reasoning effort before every step. Low for routine, high when recovering. · TypeScript
**laya-jev** - laya-jev: TypeSafe Jev ecosystem repository. · TypeScript
**pi-jev-permit** - A Jev $TypeSafe System One$ permission gate for the Pi coding agent: judges every bash / write / edit call before it runs · TypeScript
**kz-harness** - kz-harness: TypeSafe Jev ecosystem repository. · JavaScript
**JEV-Trading-BOT** - An order-flow trading bot whose decisions are made by Jev · Python
**jev-eyes** - Give Jev eyes — honest, local image perception for TypeSafe's text-only System One model. OCR + spatial layout → Jev state. CLI, MCP server, agent skill. · Python
**jev-free-router** - Dynamic per-turn model router on free OpenCode Zen + Go models $fork of gargpratyush/jev-router$ · JavaScript
**jev-unpack-hook** - A Jev powered hook that detects overloaded multi-topic multi-question messages and forces the agent to present issues one at a time, adding relevant context and missing info. · Python
**backoffice-agents** - Piloto de agentes de backoffice: LLM gera e raciocina, Jev $TypeSafe AI$ decide, roteia e verifica · Python
**omp-jev-extensions** - OMP / pi-coding-agent extensions that delegate acceptance gating and subagent routing to the Typesafe Jev decision API · TypeScript
**triagedy** - Alert triage as a UNIX filter: JSONL security alerts in, typed decisions out. Runs on TypeSafe Jev or a local model; policy routing stays in code. · Rust
**agent-kit** - Agent make dozens of silent judgments a turn: is this done, is this correct, do I have enough to decide, which way now. Made inside your own text stream, those judgments are uncalibrated and biased toward finishing, you tend to certify your own work. judge hands one such judgment to Jev. · Python
**jev-model-router** - Routes each Claude Code turn's model and reasoning effort with TypeSafe Jev, and keeps small-window models away from large sessions. · TypeScript
**openfront-agent** - A local OpenFront agent using TypeSafe Jev for bounded gameplay decisions. · JavaScript
**jevx** - jevx: TypeSafe Jev ecosystem repository. · Go
**pokemon-showdown-jev-agent** - Autonomous Pokemon Showdown battle agent powered by Jev AI $System One Model by TypeSafe AI$, with a validated poke-env harness, safe fallback decisions, and a live dashboard for transparent battle state, legal moves, probabilities, telemetry, and Jev decision history. · JavaScript
**jev-routing** - Go Jev harness for Claude Code, Codex, and Grok Build. No npx. Not an MCP server. · Go
**tacano** - tacano: TypeSafe Jev ecosystem repository. · Python
**codex-jev** - Jev-powered selective context handoffs for Codex, with a GitHub Copilot portability plan. · JavaScript
**jev-demo** - TypeSafe Jev（System One 决策模型）零依赖网页体验台：浏览器操作 / 意图识别 / Agent 上下文裁剪三大预设场景，发送状态与类型化问题，拿到带校准概率的结构化答案 · JavaScript
**jevgauge** - One-shot model and reasoning routing for Hermes Desktop. Manual control wins. Explicit upstream integration preview. · Python
**permit-mcp** - Stop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits. · Python
**JEV-Customer-Service-Decision-Workflow** - Support triage where a typed model decides, application code routes, and an open chat model only writes. · TypeScript
**dsh-just-enough-tools** - Nearly half the agent cost, with accuracy intact. Just enough tools is a DeepSeek Harness plugin that uses Jev to reveal tools and skills progressively. The main model starts with a clean planning step. Jev then selects which capabilities to add as the task unfolds. · TypeScript
**pi-jev** - a Jev classification layer for the Pi coding agent · TypeScript
**smart-router-chatbot** - smart-router-chatbot: TypeSafe Jev ecosystem repository. · Python
**jev** - jev: TypeSafe Jev ecosystem repository. · TypeScript
**conductor** - Run your Mac by voice: hold Fn, say a task, and Claude Code or Codex carries it out. Built on Jev Voice by TypeSafe. · Swift
**gavel** - Governed AI judgments for Salesforce. Works with TypeSafe Jev. · Apex
**openclaw-jev-compaction** - Verbatim context compaction for OpenClaw: a context engine powered by TypeSafe's Jev. Drops stale tool calls and results, never summarizes. · TypeScript
**agy-cli-jev-auto-mode** - A conservative Jev-backed auto-mode safety gate for Antigravity CLI tool calls · JavaScript
**jevguard** - Runtime guardrails for long-running AI agents · TypeScript
**JevLang** - A policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited. · JavaScript
**jev\_router** - Standalone TypeSafe Jev-based auto-routing for Agent Zero · Python
**hermes-jev-router** - Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending. · Python
**agent-tool-router** - agent-tool-router: TypeSafe Jev ecosystem repository. · TypeScript
**laya-router** - laya-router: TypeSafe Jev ecosystem repository. · JavaScript
**pi-jev-compaction** - Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully. · TypeScript
**pi-jev-wiki** - Agent managed wiki for a project's conceptual space, utilizing Jev to ensure legitmate, relevant, and robust information at scale. · TypeScript
**nocap** - No evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks. MCP server, Python SDK, CI route tests. · Python
**kira-ai-plugin-jev** - Jev-powered reply trigger for KiraAI 3.x with persona-aware decisions and message history context · Python
**jev-charactor** - Jev-Character: a TypeScript core for role-playing agents, autonomous game NPCs and AI towns. Agent memory, natural-language behavior authoring and programmatic dialogue, with a playable 2D multi-agent simulation. · TypeScript
**dsh-plugin-jev-router** - Per-turn model and reasoning-effort routing for DeepSeek Harness, decided by one Jev choice question. Jev picks the candidate, a confidence gate falls back, and every turn appends a receipt that can be replayed at zero cost. · TypeScript
**pi-jev-helm** - TypeSafe / Jev community project: Z761293629/pi-jev-helm. · TypeScript
**jev-plays-pokemon** - Like Claude Plays Pokemon, but with Jev · Python
**jev-switchboard** - A JEV-gated semantic communication layer for parallel coding agents. · JavaScript
**jev-in-jev** - JEV in JEV: an AI task router that uses Jev to decide whether a task needs Jev. · Python
**doorman** - Bot and pitch detection for risky forms with one typed question to Jev. Zero dependencies, mock mode without a key, recorded live run included. · JavaScript
**jev-craft** - 让 Agent 长出「操作杆」：用 System One 模型（Jev）承担高频判断、多模态模型当眼睛。给思路 + 可跑的参考实现（75 条离线断言，零依赖零 key） · JavaScript
**jev-advisor-gateway** - Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor $GPT or Claude$. · TypeScript
**pi-ask-jeff** - An advisor called Jeff for pi: calibrated decisions via ask\_jeff, backed by the Jev-compatible System One API $OpenRouter / TypeSafe / jev-agent$ · TypeScript
**jev-prism** - Jev Pipeline: a locally-run, multi-stage decision pipeline on TypeSafe Jev. Live API calls, bring your own key. · CSS
**zcode-router** - Jev driven auto-router for Zcode, with MoA, swarm, and adversarial solution capability · TypeScript
**jev-decision-skill** - 让 AI Agent 直接调用 TypeSafe AI「Jev」决策模型的 Skill —— 免 API key，纯标准库 CLI。Agent Skill for TypeSafe AI Jev $System One$. · Python
**jeviatus** - A repository for jeviatus · TypeScript
**jev-guard** - Guardián en tiempo real para agentes internos de 30X, construido sobre JEV $TypeSafe AI$. Reto 30X. · Python
**bright-sight** - macOS 命令行工具：把一句中文指令变成受控的应用操作，每一步执行完都由代码回读验证 · TypeScript
**jev-claude** - jev-claude: TypeSafe Jev ecosystem repository. · Rust
**jev-decision** - jev-decision: TypeSafe Jev ecosystem repository. · TypeScript
**hookgate** - Calibrated, sub-second decisions in Claude Code's hooks, answered by TypeSafe's Jev · HTML
**jev-inbox-triage** - Jev $TypeSafe$ typed prefilter skill: two-phase inbox triage with confidence gating + pre-send guard · JavaScript
**jev-mcp** - Jev agent workstation. · TypeScript
**jev-multiagent-retail** - A retail multi-agent system where TypeSafe's Jev acts as the System One decision layer inside a LangGraph orchestrator it will multiple agents using A2A Servers, Google ADK, Langgraph, Claude Agent sdk and Microsoft agent sdk · Python
**enhance-cx-with-jev** - A Jev decision layer for Customer Success — 22 typed decisions per inbound message, 14 per account, 10 per outbound draft. Zero dependencies, 38 tests, runs offline. · JavaScript
**Sentinel** - Sentinel: TypeSafe Jev ecosystem repository. · JavaScript
**jev-dev-flow** - jev-dev-flow: TypeSafe Jev ecosystem repository. · TypeScript
**jev-docs** - jev-docs: TypeSafe Jev ecosystem repository. · JavaScript
**jev-semantic-cost-map** - jev-semantic-cost-map: TypeSafe Jev ecosystem repository. · Python
**jev-playground** - A playground for TypeSafe AI's Jev $System One model$, built around five real production workflows: support triage, RAG relevance gating, agent action firewall, inline moderation, and CI eval judging. · JavaScript
**jev-brotato** - Let TypeSafe Jev play Brotato: local game bridge, autonomous menus, and recorded runs with probabilities, latency, tokens and cost. · Python
**rocky** - Say it, and your computer does it. Voice-controlled computer agent on TypeSafe Jev for macOS and Windows. · Python
**agent-doc-search** - Point AI coding agents at the right docs in large codebases: local BM25 and a Jev search propose, a Jev check confirms. · JavaScript
**jev-healthcare-support-router** - TypeScript demo using Jev as a decision layer for healthcare customer-support routing, urgency detection, and human escalation. · TypeScript
**JudgeJev** - DeepThink meets llm as judge. Use heavy prefill caching to run the same request in parallel and let Jev give you the best result. · TypeScript
**n8n-nodes-typesafe** - Typesafe AI Node for N8N · TypeScript
**jev-lcm-hermes-compaction** - Calibrated Jev ranking before lossless context condensation · Python
**fhir\_jev** - fhir\_jev: TypeSafe Jev ecosystem repository. · Python
**jev-cascade** - Jev answers first; only the uncertain band goes to a stronger model, with a check that stage two really is stronger. · Python
**JEV-Studio** - Editor visual de flujos de IA con Jev $TypeSafe$ como motor de decisión · React Flow + FastAPI + SQLite · TypeScript
**jev-un-squadron** - A TypeSafe Jev decision model flying U.N. Squadron $SNES, 1991$ from raw WRAM via BizHawk + Lua + Python · Python
**synthetic\_colony** - synthetic\_colony: TypeSafe Jev ecosystem repository. · Python
**laya-computer-use** - 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. · Python
**jev-terrarium-dinosaurs** - Autonomous dinosaur ecosystem where code runs the physics and TypeSafe's Jev decides each creature's intent from prose laws. Pixel-art web UI with a live Jev monitor $JSON in/out per tick$, interchangeable brains $hybrid / full Jev / offline$. Experimental Jev integration. · Python
**pi-jev** - Jev-powered semantic process conditions and skill suggestions for Pi · TypeScript
**JevRAG** - Option-ready retrieval for decision models on the CloudBTL landing layer · Python
**jev-tools** - TypeScript tools built on TypeSafe AI's Jev: an agent tool-call guardrail, a GitHub issue-triage Action, and a bulk classification CLI $npm workspaces monorepo$. · TypeScript
**jev-skill-router** - Route each task to the one tool an agent should call, with Jev — with confidence. Single-file, no build. Use free: jevtypesafeai.com/tools/jev-skill-router · HTML
**Jevris** - Local decision control plane $using the TypeSafe's System One Jev Model$ for AI-assisted development: routing advice, permissions and verification for Claude Code, Codex, Kilo, OpenCode and Antigravity · JavaScript
**client-issue-followup** - Match client requests to GitHub issues with confidence-based review and approval-required follow-up drafts. · Python
**pi-jev-router** - Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway · JavaScript
**dsh-jev-router** - DSH 插件 · 用 Jev（TypeSafe System One）判定推理强度：默认只切思考强度（零缓存代价），自动模型路由出厂关闭 + 硬门禁 + 成本闸。作者 chenshi.ai · JavaScript
**jevvie** - Jevvie: a small website companion. A page's actions as WebMCP tools, a visitor's request as one Jev Choice, a voxel character that does it. · TypeScript
**jev-gates** - Three gates for any coding agent: a deterministic approval gate before irreversible actions, a completion gate that demands evidence instead of «done», and a rubric regression gate. Powered by TypeSafe Jev $System One$. Works with Claude Code, Codex, DeepSeek Harness, Cursor, opencode, Hermes, plain shell and CI. · JavaScript
**jev-agent-routing** - DIY Jev fast decision layer for Agent - 10x faster, 10x cheaper · HTML
**typesafe-mcp** - TypeSafe System One dispatch pipeline as a ZCode plugin: typed subagent routing $Battery #1$, deterministic thresholds, destructive-op guard, usage ledger · JavaScript
**jev-claude-orchestrator** - Jev-supervised madmax conductor for Claude Code: tiny slices, parallel subagent workers in worktrees, TypeSafe Jev makes routing/review/QA/supervision decisions. · Python
**jev-pi-model-router** - pi extension: TypeSafe Jev picks the model for each turn, only from models pi can use · JavaScript
**jev-skill** - Agent skill: route subagent tasks to the cheapest capable model via TypeSafe Jev · Python
**LTPPXT** - LTPPXT: TypeSafe Jev ecosystem repository. · Python
**jev-model-router** - jev-model-router: TypeSafe Jev ecosystem repository. · TypeScript
**jev-router** - Claude Code mod: routes each turn to Haiku, Opus or Fable via Jev, and sends image work to OpenAI through Codex · TypeScript
**JevOps** - JevOps: TypeSafe Jev ecosystem repository. · TypeScript
**jev-state-engine** - jev-state-engine: TypeSafe Jev ecosystem repository. · Python
**Mario-And-Jev** - Mario-And-Jev: TypeSafe Jev ecosystem repository. · C++
**jev-subagent-router** - Use TypeSafe Jev to select subagent models and reasoning effort in Codex and Claude Code. · Python
**openclaw-typesafe-catalog-router** - typesafe jev openclaw plugins · TypeScript
**Jev-Agentic** - Jev-Agentic: TypeSafe Jev ecosystem repository. · Python
**typesafe-jev-salesforce** - A typed decision layer for Salesforce: TypeSafe Jev $System One$ in Apex for Service Cloud case triage and an Agentforce guardrail. Built live for Deep Dives by Sangam. · Apex
**dsh-jev-gate** - dsh-jev-gate: TypeSafe Jev ecosystem repository. · JavaScript
**intelligent-model-router** - Intelligent model router: pluggable top-K model recommendation $rules + System One/Jev judgments, with reasons$ · Rust
**Cascade-Agent** - Cascade-Agent: TypeSafe Jev ecosystem repository. · Python
**zocomputer-jev** - A Zo skill for situational script writing and execution using Vercel AI Gateway and TypeSafe AI Jev.
**smart-home-assistant** - Demo app to showcase the System One models functionality. Say what you want in natural language, System decides what to do on the home.. · TypeScript
**jev-fabric** - Native process orchestration with typed, explicit Jev decisions. One Bend executable owns your processes, keeps bounded logs, and asks Jev only when told. Agent skill + curl install. · TypeScript
**Jev-plugin-for-hermes** - Jev-plugin-for-hermes: TypeSafe Jev ecosystem repository. · Python
**dsh-agent-dispatch** - Jev-guided dispatch advice for DeepSeek Harness: before each turn, Jev judges whether to delegate and to which registered agent. Advice only — jev-optional, fail-open, keychain-first. · JavaScript
**gut** - gut: TypeSafe Jev ecosystem repository. · TypeScript
**jev-playground** - jev-playground: TypeSafe Jev ecosystem repository. · Swift
**reflex-state** - Jev-powered execution state for Pi coding agents. Track changes, checks, and blockers outside the main LLM, with evidence-backed updates and replay. Inspired by SKILL.state. · TypeScript
**toolbox** - One MCP endpoint in front of all your MCP servers: Jev routes each prompt to the right server and tool, and a risk gate decides run, ask or block. · Python
**model-router** - Claude Code mod: routes model and effort per task with TypeSafe's Jev · TypeScript
**jev-france-services-router** - Oriente une demande administrative vers les partenaires et structures France Services pertinents. · JavaScript
**jev-mistral-reflex** - Route bounded decisions through Jev and hand open-ended work to Mistral. · JavaScript
**jev-workflow** - Decision contracts, adversarial testing, tracing, stability, and privacy controls for TypeSafe Jev · TypeScript
**wiring-jev-into-a-local-agent** - Companion code for Old Nain episode 001: wiring Jev, TypeSafe's System One model, into a local email agent. For educational use only. · Python
**jev-watchdog** - Event-driven trajectory watchdog for coding agents: per-event LLM judgments $Jev, Claude, GPT$ accumulated into quarantine decisions · Python
**jev-spire-strategist** - Slay the Spire 2 agent: TypeSafe Jev picks each move, a Claude Code session plans the run as strategist · JavaScript
**jev-demo** - jev-demo: TypeSafe Jev ecosystem repository. · JavaScript
**System-One-plus-Two-Ops-Agent** - System-One-plus-Two-Ops-Agent: TypeSafe Jev ecosystem repository. · Python
**typesafe-pi** - TypeSafe System One for Pi: a consent-gated judgment tool and workflow design skill · TypeScript
**rx-interaction-jev** - rx-interaction-jev is an intelligent, high-performance prescription safety and policy review engine. It combines Retrieval-Augmented Generation $RAG$ with Jev $TypeSafe AI’s non-generative, probabilistic System-1 decision model$ and openFDA clinical label data to deliver real-time, deterministic drug interaction and policy compliance checks. · Python
**mindrails-supervisor** - Pick the right AI model and effort before an agent starts: Jev plugins for Claude Code and Codex, a local chat app for both, and an MCP completion gate. · JavaScript
**jev-decision-maker** - omp plugin: JEV $TypeSafe System One$ picks the next coding step from agent-supplied candidates · TypeScript
**jev-telegram-channel-router** - Jev as a channel message router \| Jev频道消息路由 · Python
**jev-governor** - A calibrated System One decision layer for existing LLM agents - Jev decides, the LLM writes, and the decision is enforced. Adapters for Hermes, Pydantic AI and OpenClaw. · Python
**skill-library-skill** - skill-library-skill: TypeSafe Jev ecosystem repository. · TypeScript
**choola** - Python framework for building automations with AI coding agents — single-file nodes, JSON payloads, built-in LLM cost guardrails. · Python
**jev-latam-lead-triage** - Triage de leads de WhatsApp/CRM con Jev $TypeSafe AI$: ruteo por confianza, plantilla n8n y benchmark en español. Sin dependencias. No afiliado. · Python
**Pi-Jev** - Pi-Jev: TypeSafe Jev ecosystem repository. · TypeScript
**jev-social** - Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence. · JavaScript
**codex-jev** - Route each Codex prompt to the right effort with TypeSafe's Jev · Python
**opencode-langsearch** - Unofficial OpenCode v2 plugin: LangSearch web search provider, optionally gated by Jev $TypeSafe AI$ to cut tokens and filter noisy/injected results before they reach the model. · TypeScript
**prime-typesafe-jev** - System-1 decision model integration, safety governance, and host bridge for Prime Agent · TypeScript
**hangar-computer-control** - MCP que opera um desktop Windows pela árvore de acessibilidade a partir de um objetivo em português · Rust
**l4-jev-workflows** - Loopfour workflow steps rebuilt with Jev $TypeSafe$ instead of an LLM · TypeScript
**LogiPulseAI\_JEV** - Real-time last-mile delivery exception triage: Jev $TypeSafe AI System One$ evaluates each event, deterministic guardrails decide. FastAPI + Streamlit. · Python
**claude-jev** - claude-jev: TypeSafe Jev ecosystem repository. · JavaScript
**mmmgc\_modelrouter** - mmmgc\_modelrouter: TypeSafe Jev ecosystem repository. · TypeScript
**RFQ\_Routing** - RFQ\_Routing: TypeSafe Jev ecosystem repository. · Python
**pi-smart-router** - A Pi coding-agent extension that routes each prompt to the best backend model — cheap, fast, balanced, or powerful — using local heuristics, with optional TypeSafe Jev classification. · TypeScript
**jev-mcp-server** - jev-mcp-server: TypeSafe Jev ecosystem repository. · TypeScript
**jev-demo** - a demo of Typesafe's Jev a System One Model for structured decsion making · TypeScript
**tracecore-reflex** - Verifiable hybrid agents that use fast Jev decisions for routine actions and strong LLM fallbacks for uncertainty, with confidence gating, telemetry, replayable traces, and auditable TraceCore compliance bundles. · Python
**dsh-jev-loop** - Jev $TypeSafe System One$ judgments at the DeepSeek Harness agent-loop gates. No UI dependency. · TypeScript
**jev-ui-map** - Map your app's UI so Jev can drive it. Demo: order food by voice. Built with AdaL. · JavaScript
**jev-control-plane** - JEV powered model and reasoning routing for delegated Codex work · Python
**jev-docs-agent** - Goal-driven AI agent that records walkthrough videos of any web app and writes the user guide. Powered by Jev $TypeSafe AI$ + Playwright, driven from Claude Desktop via MCP. Open-source alternative to Supademo/Scribe and manual testing. · Python
**GitHub-Issue-Classification-Using-Jev** - This repository contains a GitHub issue classifier built on Jev, TypeSafe AI's System One model. It labels every new issue with typed values and calibrated confidence in milliseconds, labelling what it is sure about and escalating what it is not. Three guardrail layers guard every write, and a frozen eval suite gates each deploy. · Python
**jev-social** - Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence. · JavaScript
**58\_JEV\_AI** - 58\_JEV\_AI: TypeSafe Jev ecosystem repository. · Python
**support-ticket-router** - Sorts customer support tickets automatically and sends the uncertain ones to a person. · Python
**jev-router-pi** - Jev-powered automatic model routing for the pi coding agent across z.ai GLM models · TypeScript
**dsh-skill-auto-load-typesafe** - dsh-skill-auto-load-typesafe: TypeSafe Jev ecosystem repository. · TypeScript
**system-one-skill** - System One decision pattern for OpenClaw: choose from candidates instead of generating $Jev-style$. embed + matrix scoring CLI, escalation thresholds, agent checklist · Python
**decision-ghc-router** - Cost-aware JEV model routing for GitHub Copilot CLI, VS Code, and VS Code Insiders · JavaScript
**opencode-jev-plugin** - opencode-jev-plugin: TypeSafe Jev ecosystem repository. · TypeScript
**jev-decision-gateway** - A provider-agnostic AI decision gateway using TypeSafe AI's Jev $System One$ model to gate, route, and verify expensive LLM workflows · TypeScript
**Jev\_job\_hunter** - Jev\_job\_hunter: TypeSafe Jev ecosystem repository. · Python
**hypr-jev** - 基于 jev 的快速轻量 Hyprland 桌面助手 · Python
**jev-one-system** - jev-one-system: TypeSafe Jev ecosystem repository. · TypeScript
**jev-triage-router** - jev-triage-router: TypeSafe Jev ecosystem repository. · TypeScript
**astrbot\_plugin\_intentiontrigger** - astrbot\_plugin\_intentiontrigger: TypeSafe Jev ecosystem repository. · Python
**jevons** - A bounded Pi execution supervisor powered by TypeSafe Jev: decisions, recovery, review and verification. · TypeScript
**jev-agent-router** - Code when exact. Jev when useful. Agent when uncertain. A lightweight routing layer for computer-use agents, with real workflow benchmarks. · Python
**tano\_hackathon** - tano\_hackathon · Python
**use-jev** - use-jev: TypeSafe Jev ecosystem repository. · TypeScript
**maestro-jev** - Goal-driven UI verification on iOS/Android/Chromium: Jev $TypeSafe$ decides each step, Maestro executes. Installs as a pi / Claude Code / Codex skill. · JavaScript
**jev-model-router** - Claude Code hook: TypeSafe Jev scores each prompt and picks the model and effort it deserves · Python
**jev-apps** - Pipeline failure triage and a customer support router built on TypeSafe AI's Jev model · Python
**jev-social** - Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cited browser evidence. · JavaScript
**JEV** - Exploración de control por voz en macOS: TypeSafe Jev, planificación con Anthropic y sesiones continuas. · Swift
**frost** - A flexible and configurable CLI model router using TypeSafe Jev. · Go
**jev-accelerator** - A skill using jev to speed up LLM use. · JavaScript
**ha-jev-conversation** - Czech Home Assistant Assist agent on TypeSafe Jev: typed decisions in ~300 ms, confirmations for locks and garage · Python
**guardian** - A real-time safety layer for AI agents: every tool call is checked by Jev $TypeSafe$, escalated to a human when unsure, explained from Entire sessions and traced to NeatLogs. · Python
**jermes** - Jev decision layer for Hermes Agent · Python
**astrbot\_plugin\_smart\_wake** - AstrBot 智能主动唤醒插件：关键词抽签 + Jev 模型判定两级漏斗，让 bot 主动参与群聊 · Python
**jev-orchestrator** - Workflow orchestration for System One models. Batch, gate, trace, and calibrate thousands of typed Jev decisions. · Python
**droidjev** - A fast, screenshot-free Android emulator clicker powered by TypeSafe's jev · JavaScript
**flowaid** - Open-source, backend-first AI agent and workflow platform with typed decision intelligence. · TypeScript
**messenger-human-firewall** - messenger-human-firewall: TypeSafe Jev ecosystem repository. · TypeScript
**Jev-CustomerService-Demo** - Ticket-Routing im Kundenservice mit dem Entscheidungsmodell Jev von typesafe.ai · Python
**jev-model-router** - A lightweight Codex skill that uses TypeSafe Jev to route execution subagents by model and reasoning effort. · Python
**hermes-plugin-jev** - Jev $TypeSafe AI$ System One decision engine plugin for Hermes Agent, backed by Agnes AI Flash. · Python
**model-router** - Picks the Claude model and reasoning effort for each task with Jev, TypeSafe's System One decision model · TypeScript
**jev2mcp** - A small intelligence layer for context-aware MCP, plugin, and tool selection. Built with Jev. · JavaScript
**NanoJev** - NanoJev bot for pvp mainly sword · TypeScript
**harnessjudge** - Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev · TypeScript
**mcpmatch** - Match user goals to MCP catalog $two-stage$ via TypeSafe Jev · TypeScript
**spendbrake** - Agent budget brake — continue / downgrade\_model / stop via TypeSafe Jev · TypeScript
**swarmrouter** - Route tasks to research/code/browser/support/writer agents via TypeSafe Jev · TypeScript
**model-proxy** - model-proxy: TypeSafe Jev ecosystem repository. · Go
**agent-battle-royale** - Interactive agent-routing demo. The API key and Sites project id stay in local env files. · TypeScript
**jev-issuePilot** - jev-issuePilot: TypeSafe Jev ecosystem repository. · TypeScript
**jev** - jev: TypeSafe Jev ecosystem repository. · PowerShell
**jev-verifier-skill** - Fast 'System One' reflex for reasoning LLMs: typed probabilistic second opinions from Jev via OpenCode Zen, with PII-minimizing state redaction.
**agentp-macos** - Fast computer-use agent for macOS: Gemini plans once, Jev acts at every step via the Accessibility API · Python
**ps2-ai-agent** - Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One · Python
**approval-judge-bridge** - OpenAI-compatible judge endpoint for agent approval gates: typed judgements $Jev$, any OpenAI-compatible model, or a rule file — fail-closed, calibrated, with a replay battery · Python
**exemplo-hev-roteamento** - Roteamento automático de incidentes para o time certo usando o modelo Jev $TypeSafe AI$ via OpenRouter, com benchmark de 1000 requisições. · HTML
**jev-hermes** - jev-hermes: TypeSafe Jev ecosystem repository. · Python
**jev-effort** - Per-turn reasoning effort for coding agents, classified by TypeSafe's Jev via AI SDK $Vercel AI Gateway / OpenRouter / TypeSafe$. Claude Code plugin; Codex, Cursor, Amp next. · JavaScript
**pi-jev-reasoning-router-lite** - pi-jev-reasoning-router-lite: TypeSafe Jev ecosystem repository. · TypeScript
**jev-inbox-triage** - A decision model $TypeSafe Jev$ sorts a store's inbox: 19/20 emails to the right lane, 0 risky emails automated, ~2.5 US cents a month. · HTML
**jev-orchestrator** - An mini node orchestrator that uses Jev to handle routing to different LLMs based on difficulty. · TypeScript
**4genthub-client** - 4genthub-client: TypeSafe Jev ecosystem repository. · Go
**jev-context-compaction** - Jev-guided transcript compaction for Claude Code. Rust rewrite of tamaratran/fast-jev-compaction. · Rust
**jev-plugins** - Cursor and Hermes marketplace for the four published JEV Labs routers.
**conduit** - Loopback gateway for Claude Code or OpenCode: automatic Anthropic → GLM → DeepSeek failover, breaker-driven, plus optional per-call model routing by Jev $TypeSafe System One$ — capability-first across all three providers — with manual pinning, control UI and CLI · Go
**Jev-Defense** - A Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode. · Python
**Jev-Integrate** - Jev decides; Claude, Grok, or any LLM only writes. TypeSafe Jev integration for routing, compaction, and cheaper agent turns. · Python
**hass-hunch** - hass-hunch: TypeSafe Jev ecosystem repository. · Python
**tiny-bouncer** - A Classifier for AI Agent Shell Commands, Powered by Decision Models or LLMs · Go
**insurance-claims** - Jev + Claude prototype: FNOL claim triage and cost-aware Claude model routing · Python
**fastgate-jev** - Jev $TypeSafe AI$ as a System One decision layer for a multilingual EN/UZ/RU RAG helpdesk, with an independent benchmark · Python
**jev-support-agents** - Multi-agent customer support API where the LLMs write the text and a typed decision model makes the decisions. Jev $TypeSafe System One$ handles routing, response evaluation and retry/escalation; FastAPI + Ollama. Includes a 60-ticket benchmark against LLM free-text and structured-JSON baselines. · Python
**the-llm-dispatcher** - An LLM router that uses Jev $TypeSafe System One$ to dispatch each request to the cheapest model and lowest reasoning effort that will do the job. OpenAI-compatible proxy, Claude Code and Codex wrappers, TypeScript and C#. · C#
**jev-editor-skill** - Editorial gate skill for Claude Code and other agents. Scores a draft on AI tells, your own voice, editorial quality, and SEO using TypeSafe's Jev. · Python
**arbitype** - Typed decision tools for AI agents, powered by TypeSafe Jev · Python
**loom-skill-selector** - Proactive Jev-powered skill selection for Loom, running as a jailed extension · Gleam
**memory-router** - Routing + write-lease service for multi-agent memory systems $Jev-backed, MCP$ · Python
**TrashCompact** - Deterministic transcript cleanup and compaction support using TypeSafe's Jev. · JavaScript
**JevArena** - Two Jev agents duel at Snake via Vercel AI Gateway. · TypeScript
**gcp-typesafe-jev-hybrid-gateway** - Hybrid AI Architecture on Google Cloud: Sub-100ms Gateway with TypeSafe Jev $System 1$ and Vertex AI Gemini $System 2$ on Cloud Run · HTML
**fast-jev-opencode** - OpenCode v1 + v2 plugin: prune stale tool calls and truncate bulky tool results from the outgoing request using TypeSafe Jev decisions $verbatim compaction, no summarization$. · JavaScript
**Hearth** - Hearth: TypeSafe Jev ecosystem repository. · Python
**jev-fast-judgements** - Agent Skill that offloads bulk yes/no, pick-one-option and rating judgments to TypeSafe's Jev so Claude spends fewer tokens during investigations. · Python
**agent-reflex** - A ~400ms System-One safety reflex for AI coding agents: auto-approves routine tool calls, escalates risky ones, blocks exfiltration & prompt injection. Powered by TypeSafe's Jev. · TypeScript
**juna** - A lean Pi coding agent profile that keeps context small, with TypeSafe Jev pruning tool output · TypeScript
**relay-macos-assistant** - Experimental local-first macOS voice automation using whisper.cpp, TypeSafe Jev routing, typed actions, and optional Ollama generation. · Python
**zork\_by\_jev** - Autonomous Zork I agent: a local or hosted language model reads the game and proposes commands, and Jev $a decision model$ picks one. Python harness with map memory, lessons across games, and replay. · Python
**ci-triage** - Reads failed CI runs, re-runs flaky and infrastructure failures once, and explains real ones in one PR comment $Jev$ · Python
**depgate** - Merges safe Dependabot and Renovate updates itself, holds risky ones: 0 wrong merges on 199 real updates $Jev$ · Python
**n8n-nodes-jev** - n8n node that routes items only when the AI is confident and sends the rest to a person $Jev, 97.5% accurate$ · JavaScript
**agent-decision-lab** - 100 Java agent recipes, typed decision guardrails, Jev adapter, tested fixtures and architecture guides by Sandeep Belgavi · Java
**typesafe-triage-guard** - Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate. · Python
**jev-godfather** - jev-godfather: TypeSafe Jev ecosystem repository. · JavaScript
**sunvai** - AI triage layer for MP CM Helpline 181: Jev typed decisions + Claude, built at Claude Code Build Day Bhopal · TypeScript
**jevlet** - Jev-powered System One operator for Kubernetes: observable, typed, policy-gated cluster decisions and automated remediation. · Go
**chrome\_jev\_agent** - chrome\_jev\_agent: TypeSafe Jev ecosystem repository. · JavaScript
**astrbot\_plugin\_jev\_gate** - AstrBot 主动回复门控插件：用 TypeSafe Jev 模型给群聊消息打分，只在真值得接话时才触发一次主动回复 · Python
**jev-router** - Route each message to the smallest Claude model that can do it, sized by Jev $TypeSafe$ · Python
**HACKU-windows-mousebuddy-** - HACKU-windows-mousebuddy-: TypeSafe Jev ecosystem repository. · TypeScript
**pi-jev-route** - Route mid-run Pi prompts with TypeSafe Jev · TypeScript
**reflex** - Lab project: route Alertmanager alerts to urgent or informational Discord channels using TypeSafe's Jev model, with label-based fallback · Go
**omp-jevens-classifier** - Jev-powered model-judged permission gate for OMP $TypeSafe System One$ · TypeScript
**jev-corrective-rag** - Corrective RAG where every decision gate is a typed System One model call instead of an LLM judge. 7x fewer LLM calls, 4x lower p50 latency. · Python
**typesafe-minesweeper** - Autonomous Minesweeper powered by TypeSafe System One and local constraint inference · TypeScript
**claude-jev-router** - Claude Code plugin: route each prompt to the cheapest Claude model and thinking effort that fits, decided by TypeSafe Jev · TypeScript
**sizeup** - Jev-powered model router for AI coding agents $omp + Claude Code$: small jobs go to smaller, cheaper models. · TypeScript
**t-shiratori-ai-model-evaluation-router** - t-shiratori-ai-model-evaluation-router: TypeSafe Jev ecosystem repository. · TypeScript
**n8n-nodes-typesafe** - TypeSafe for n8n: ask yes/no, pick-one and rate-it questions about any item and route on calibrated answers $Pass / Fail / Review$ · TypeScript
**pi-jev-continue** - Goal-scoped continuous development for Pi, judged by Jev. · TypeScript
**cursor-jev** - Jev for Cursor. Jev decides. The agent writes. The router is off until you turn it on. · Python
**jev-starter** - jev-starter: TypeSafe Jev ecosystem repository. · TypeScript
**ChoiceMyModel** - Use Jev to choice the cheapest llm model to have the better quality · TypeScript
**subagent-dispatcher** - experimental subagent dispatcher · JavaScript
**tierwise** - Cache-aware, TypeSafe-driven model tier router for Claude Code · TypeScript
**Jev-decision-plugin** - A Codex plugin that turns noisy input into small, typed, calibrated decisions using TypeSafe Jev. · Python
**effort-router** - Picks the reasoning effort for each turn of Claude Code with a System One classifier · TypeScript
**jev-ops** - JevOps is a control plane for AI agent decisions. TypeSafe AI's Jev model judges each proposed action, then deterministic policy rules return ALLOW, RETRY, HUMAN\_REVIEW or BLOCK. Built with FastAPI, Celery $drift detection, replay runs$ and a Next.js operations console. · Python
**pikachu** - Curated Pi coding agent configuration with Jev compaction, LSP, subagents, plan mode, safety tools, and automatic updates. · TypeScript
**doc** - Doc, Scott's sidekick: Jev $TypeSafe$ wired into every coding agent $Claude Code, Codex, Grok, Hermes$ — checks comments before they're published, keeps effort estimates and secret requests out of replies, points each turn at the right skill, and routes easy work to a cheaper model. · Python
**jev-agent** - agent for jev · Python
**typesafe-agent-framework** - typesafe-agent-framework: TypeSafe Jev ecosystem repository. · C#
**uefn-plugin-typesafe** - TypeSafe Jev judge for UEFN Ducky Automations and Pipelines. Not a chat model. · Python
**jev-on-air** - JevOnAir monitors livestreams in real time, transcribes speech, detects market-moving statements with Jev, and turns them into structured simulated trade signals. · TypeScript
**jev-plays-super-mario-bros** - AI agent that plays Super Mario Bros with TypeSafe Jev - a typed decision model reading NES RAM instead of pixels, verified by emulator rollback search. Clears 1-1 to 1-4 and 2-1 for ~$0.02. · Python
**jev-mcp-middleware** - Semantic MCP middleware that intercepts AI-agent tool calls and combines deterministic policy with TypeSafe Jev risk judgments before actions reach upstream MCP servers. · TypeScript
**jev-claude-demo** - This is a small Spring Boot service built around one idea: Jev decides, Claude writes · Java
**gmail-triage** - Gmail トリアージ自動化 - Claude Code CLI でメールを分類し、不要メール削除・重要メール Discord 通知 · Python
**demo-video-javascript-jev-starter** - This application is intended to showcase to developers a possible use case of Vonage Video API and TypeSafe AI to create an AI support agent that quickly detects if a user is getting frustrated and start a video call with a Human agent. · JavaScript
**jevymarket-direct** - jevymarket-direct: TypeSafe Jev ecosystem repository. · Python
**firstread** - firstread: TypeSafe Jev ecosystem repository. · TypeScript
**ilmari-plugin-jev** - ilmari plugin: the jev step, a quick decision on TypeSafe Jev via OpenRouter · JavaScript
**agent-guardrail-jev** - AI agent tool-call guardrail for Xano: Jev $TypeSafe AI$ judges each call; Xano allows, blocks, or holds it for human review. · XS
**jevdevice** - MCP server that lets an LLM agent control a real Android phone, using TypeSafe's Jev to pick real, runtime-discovered targets instead of hardcoded automation. · Python
**sekizui** - sekizui: TypeSafe Jev ecosystem repository. · TypeScript
**astrbot\_plugin\_typesafe\_autoreply** - 使用 TypeSafe AI 判断聊天消息是否需要 AI 主动参与，并调用 AstrBot 已配置的大语言模型生成自然回复。 · Python
**model-preflight** - model-preflight: TypeSafe Jev ecosystem repository. · Python
**deslop** - Score web pages for ads, slop, SEO and second-hand content. An agent skill built on TypeSafe Jev: four probabilities per page, no verdict, the caller sets the thresholds. · Python
**n8n-ai-brief-workflow** - Weekday AI news briefs in Slack with n8n, You.com, and TypeSafe Jev. Workflow, evaluation, and write-up. · Python
**jev-agent-skill** - Free typed judgments for AI agents: offload classify/screen/score/verify to Jev $TypeSafe System One$ via OpenCode Zen. Claude Code / ZCode skill. 给AI代理省token的免费决策分流技能 · Python
**zcode-jev** - Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic. · TypeScript
**JevGreenfield** - JevGreenfield: TypeSafe Jev ecosystem repository. · TypeScript
**jev-dsh** - System One $TypeSafe Jev$ decision tool for DeepSeek Harness — bounded choice / noul / score judgments as an agent tool + skill. · JavaScript
**jev-tetris** - jev-tetris: TypeSafe Jev ecosystem repository. · JavaScript
**codex-jev-imagegen** - Jev-powered decision workflows for Codex image generation. Explicit constraints, bounded repairs, and honest evaluation. · Python
**antigravity-approval** - Fail-closed Antigravity PreToolUse guardrail using deterministic rules and TypeSafe Jev to screen tool calls, block risky commands, and escalate ambiguous actions to manual approval. · Python
**agent-handoff-gate** - An experimental protocol for evidence-aware agent handoffs, bounded worker continuation, and TypeSafe/Jev-assisted review, with reproducible evaluation. · Python
**JevPlane** - An audited decision control plane for Gemini agents. Use Jev to route models, preflight prompts and tool evaluate agent runs with Google ADC, structured reports, and hash-chained traces.calls, select bounded context, and · Python
**astrbot\_plugin\_jev\_radar** - Jev 意图雷达 — 用 TypeSafe SystemOne$Jev$ 读懂消息背后的意图、情绪与风险 · Python

Browser & computer use

**jev-ultrafast** - Browser Use × Jev Ultrafast — high-speed browser automation powered by TypeSafe Jev. i. am. speed. · Python
**typesafe-computer-use** - Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click $macOS$. · Python
**jev-browser-use** - 5–10x faster browser operations: Jev clicks, Codex thinks and verifies. · JavaScript
**jev-voice-browser** - Control a real browser by voice. Jev $TypeSafe System One$ decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence. · JavaScript
**unclutter** - WXT browser extension: Jev-powered page clutter removal with reusable template rules. · TypeScript
**jev-browser** - Browser use using TypeSafe's Jev model. · JavaScript
**jev-use** - Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model · Swift
**jev-browser** - Browser automation where an LLM plans and Jev $Typesafe System One$ decides. Library, CLI and MCP server. · JavaScript
**fastbrowse** - A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page. · Python
**typesafe-adblock** - 🧹 Fun project: a Chrome extension that asks a tiny AI decision model $TypeSafe Jev$ "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker. · JavaScript
**jev-ui-test** - Jev 决策模型驱动的 UI 自动化测试框架：不生成「下一步做什么」的文字，而是在候选元素里直接打分；一句话写用例，pytest 执行，Allure 出报告，每个操作决策中位 458 ms（UI test automation driven by the Jev decision model — scored decisions, not generated prose; ~458 ms per decision） · Python
**jev-for-chrome** - Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe. · TypeScript
**flick-computer-use** - Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes. · TypeScript
**ego-decision-layer** - Pluggable decision layer for the ego lite browser: one System One $Jev$ call per step replaces the per-step LLM turn, and the backend can be swapped for a local OpenAI-compatible model. Fail-closed execution guards. The measured one — raw bench data, 16 suites, changelog with corrections. · JavaScript
**jev-ultrafast-mcp** - Hand the browser work off: an MCP server where a decision model drives the page for your agent, so a flow costs one tool call instead of a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay. Speaks CDP to your Chrome. · Python
**playjev** - Fast, typed browser automation powered by Jev and Playwright · TypeScript
**jev-ego** - Fast browser agent for ego lite. One TypeSafe request per step; an agent or Jev picks the move. · TypeScript
**jev-browser** - One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions. · JavaScript
**jev-browse** - Fast, cheap browser sub-tasks for Claude and other agents: TypeSafe Jev decisions on top of browser-harness · Python
**aside-jev** - Aside agents decide with TypeSafe Jev $System One: Choice/Score/Noul$. Not a Cua binding — Jev is the model, Aside is the browser runtime. · Python
**AskJev** - AskJev — Jev autopilot for any website + guard on irreversible clicks $TypeSafe System One, not Claude$ · TypeScript
**jev-skip** - Browser extension that uses captions and TypeSafe Jev to decide when to skip YouTube sponsor segments, with a seek-bar probability heatmap. · TypeScript
**computer\_use** - macOS computer use driven by Jev $TypeSafe System One$ as the decision maker · Go
**JevOnly** - Pure Jev that can "type" and drive towards task completion. · Python
**jev-mcp** - MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV $TypeSafe System One$: ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace. · TypeScript
**jev-browser-control** - Let Claude code, chatgpt codex or control your own Chrome. Chrome extension + MCP server: Jev, TypeSafe's decision model, picks each click in ~0.5 s for a fraction of a cent. MIT, bring your own OpenRouter key. · JavaScript
**jev-browse** - Browser automation with Jev $TypeSafe$ as decision model · JavaScript
**system-one-browser-agent** - High-speed dual-process browser agent combining sub-150ms Jev reflex decisions with Stagehand stealth automation and Gemini/Claude System 2 fallback. · TypeScript
**CloakBrowser-Agent** - Jev-powered stealth browser agent. TypeSafe Jev decides each step in ~0.3 s, CloakBrowser carries it out like a human. MCP server, CLI and Python API. · Python
**otto** - Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning. · TypeScript
**jev-browser-use** - Jev-powered browser automation for Codex and Claude: native reasoning, continuous action loops, CLI, MCP and Chrome extension. · TypeScript
**jev-browser-skill** - Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP · JavaScript
**jev-demofast** - One sentence in, a product demo video out. Jev drives your real product in a browser; an index built from your source code guides it. · Python
**jev-browser-local** - Run jev-browser on a fully local JEV-style decision engine $no cloud API$. Warm-browser fork, VRAM guard, measured benchmarks, run traces. · Python
**jev-max** - The Jev browser agent that handles the real web: shadow DOM and iframe piercing, canvas fallback, uploads, multi-tab, MCP for any agent host. · Python
**ego-jev-ultrafast** - Jev drives your Ego Lite browser: one typed-choice request per step. Single-file, zero-dependency port of browser-use/jev-ultrafast with multi-model benchmarks and extra guardrails. Unofficial. · JavaScript
**turbo** - Jev-powered semantic browser use · Go
**jev-automation** - Trying automation on web browser via jev from typesafe · TypeScript
**jev-browser-pilot** - A bounded decision layer for browser and desktop automation: a decision-only model picks one next step; the code owns perception, content, actuation and verification. $TypeSafe Jev / System One$. · Python
**playwright-jev** - 基于 Jev + playwright-cli 的自然语言 Web E2E 测试工具：Jev 负责决策，Playwright 负责执行，代码负责断言与安全边界。Goal-driven web E2E testing with Jev + playwright-cli: bounded AI decisions, real browser execution, and deterministic assertions. · JavaScript
**jevnav** - Page truth for browser agents — and decisions that replay, test and audit. Jev picks the element, risky actions are gated, every run replays offline in CI. · Python
**jev-play-ping-pong** - Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence. · JavaScript
**gits** - Gits is a browser extension powered by Jev to search the leads data on the Google Maps · TypeScript
**ajevt-browser** - A bounded Jev System-1 browser tool for Pi, OpenCode V2, Amp, and MCP, powered by agent-browser · TypeScript
**jev-browser-skill** - Let Jev, TypeSafe's ~100ms decision model, drive your browser. A plug-and-play skill for Claude Code and Codex. · JavaScript
**qc-use** - Test the most important path in your app. Describe it in plain words. Powered by TypeSafe Jev. · Python
**jev-ultrafast** - ⚡ Ultrafast browser agent with dynamic, indexed action spaces. Zurich → London on Google Flights in 7.1s. · Python
**jev-voice-browser-zh** - jev-voice-browser-zh: TypeSafe Jev ecosystem repository. · JavaScript
**jev-browser** - A fast browser agent. It picks an action from a numbered table of the page's real controls instead of writing a selector, so one step is a single small-model call. · TypeScript
**jev-voice** - Talk to your browser: Claude plans the command, Jev carries it out in your own Chromium profile. A side-panel extension with no chrome.debugger and no remote-debugging port. · Python
**jev-chrome-extension** - Highlight text, right-click, Ask Jev — TypeSafe Jev answers in a Chrome side panel · JavaScript
**hunch** - ⚡ Browser agent that acts on a hunch: Jev $TypeSafe System One$ picks every click in ~150 ms, an LLM is only needed when confidence drops. Zero-dependency Python on top of agent-browser. · Python
**psearch** - Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration. · Python
**pi-Jev-browser** - Browser and macOS desktop agent for pi: Jev $TypeSafe System One$ chooses each action from a structured observation in a bounded, surface-agnostic loop. Isolated Playwright tools, an allow-listed accessibility-tree tool, deterministic selectors, four-tier benchmarks. · TypeScript
**jevitate** - Autonomous browser testing that turns discovered bugs into deterministic regression tests. A model may choose what to try; only browser evidence decides pass or fail. CLI + MCP server. · TypeScript
**voice-browser-extension** - Control Chrome by voice with a Manifest V3 extension powered by Jev. · JavaScript
**jev-terminal-browser-driver** - Hermes plugin: drive and read a visible terminal-browser tab with Jev typed decisions. No screenshots, fractions of a cent per step. · Python
**jev-reach** - chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, your agent makes one devtools call there. · TypeScript
**ultrafast** - ultrafast: TypeSafe Jev ecosystem repository. · Python
**jev-browser** - jev-browser: TypeSafe Jev ecosystem repository. · TypeScript
**jev-voice-browser** - Voice-controlled browser via Jev, native CDP $port 9229$, Doubao Voice Bridge and Web Audio streaming · JavaScript
**jev-voice-browser** - 音声でブラウザを操作する Chrome 拡張機能$発話の解釈は TypeSafe の Jev$ · JavaScript
**avid-autofill** - avid-autofill: TypeSafe Jev ecosystem repository. · JavaScript
**codex-jev-turbo** - Super-optimized TypeSafe Jev + Brave Browser MCP plugin and skill for OpenAI Codex · TypeScript
**jev-orb** - Siri-style push-to-talk voice orb for autonomous browser control with Jev and Metal Whisper · Makefile
**jev-in-safari** - Experimental Safari WebDriver adapter for Jev Ultrafast. Native Safari validation pending; macOS testers welcome. · Python
**JevTest** - Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence. · TypeScript
**jev-browser-tests** - Prompt-driven browser tests: Jev executes, deterministic code verifies. · Python
**jev-voice** - Control Chrome by voice: open sites, search, click links and fill in forms. Chrome extension powered by Jev. · JavaScript
**browser-jev** - Adversarial browser testing: personas explore your web app while Jev judges every page state · TypeScript
**wrangle** - Hand one Safari window to a program, and no more than that. · Ruby
**browser-use-olympics** - Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent $Chrome DevTools + TypeSafe Jev$. · HTML
**JEV\_voice\_browser** - JEV\_voice\_browser: TypeSafe Jev ecosystem repository. · JavaScript
**jevBrowser** - jevBrowser: TypeSafe Jev ecosystem repository. · TypeScript
**plain** - End-to-end browser tests in plain English: Playwright acts, the Jev model decides. CLI, MCP server, Claude Code and Codex plugin. · TypeScript
**jev-pilot** - jev-pilot: TypeSafe Jev ecosystem repository. · JavaScript
**jev-browser** - Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values. · Python
**jev-browser-chrome** - Fast Jev browser agent for existing signed-in Chrome tabs via a local extension bridge and MCP · Python
**Jev-browser-remote** - beta project di use-computer su google chrome mediante l'uso di Jerv, riducendo notevolmente la latenza e i costi per token · TypeScript
**jev-browser** - Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included. · JavaScript
**jev-browser-standalone** - Fork of jkudish/jev-browser with cookie seeding $--cookie-file$ for authenticated pages · TypeScript
**duit** - duit: TypeSafe Jev ecosystem repository. · TypeScript
**jev-ultrafast** - A browser agent with a dynamic, indexed action space. · Python
**automation-jev** - automation-jev: TypeSafe Jev ecosystem repository. · TypeScript
**jev-browser** - Browser automation where an LLM plans and Jev $Typesafe System One$ decides. Library, CLI and MCP server. · JavaScript
**JevLens** - Using Jev for better web browsing · TypeScript
**jev-browser-relay** - A high-speed browser runtime for AI coding agents: Jev drives the browser loop, the host model intervenes only when it must. Rust control plane + MCP. · Rust
**jev-mcp** - MCP server that lets Claude Code and Claude Desktop drive the jev-ultrafast browser agent in your real Chrome, with a domain-bound safeguard · Python
**playwright-jev-testing** - Playwright TypeScript automation testing with TypeSafe Jev as the intelligence layer: semantic assertions, element selection, goal-driven flows, and failure classification $flake vs genuine, fix vs ticket$. Includes Petstore API example. · TypeScript
**laya-voice-browser** - laya-voice-browser: TypeSafe Jev ecosystem repository. · JavaScript
**jev-voice-browser-chrome-extension** - Control your own Chrome by voice. Jev $TypeSafe System One$ decides intent + target from typed probabilities in ~300 ms per spoken word; the extension acts before you finish the sentence. MV3 port of moritzkremb/jev-voice-browser. · JavaScript
**jev-computer-use** - Safe computer-use automation guided by typed Jev decisions · JavaScript

SDKs & integrations

**fastmcp** - 🚀 The fast, Pythonic way to build MCP servers and clients. · Python
**langchainjs** - The agent engineering platform · TypeScript
**effect** - Build production-ready applications in TypeScript · TypeScript
**pg-jev** - Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev. · Shell
**jev-mcp** - Proof of concept MCP for TypeSafe's Jev AI model. · JavaScript
**docjev** - Classifies and splits PDFs, DOCX, and PPTX with TypeSafe Jev. Provides a Python library, CLI, and local app with LiteParse extraction and optional LlamaParse OCR. · Python
**system-one-adapter-python** - Drop-in TypeSafeClient replacement backed by LLM APIs — run System One / Jev-style calls against open models. · Python
**system-one-connector** - MCP connector giving AI agents direct access to TypeSafe AI's Jev model. · Go
**typesafe-sdk-python** - Official Python library for the TypeSafe API $System One / Jev$. · Python
**typesafe-sdk-js** - Official TypeScript/JavaScript SDK for the TypeSafe API $System One / Jev$. · TypeScript
**openai-scala-client** - Scala client for OpenAI API and other major LLM providers · Scala
**system-one-foundation-models** - A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework. · Swift
**laya-php** - Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative. · PHP
**jevcore** - TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default. · TypeScript
**advocaat** - A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev. · TypeScript
**micdrop** - Micdrop is a set packages for node and browser that simplify voice conversations with AI systems. · MDX
**pg\_typesafe** - Pre-alpha PostgreSQL extension for TypeSafe AI $Jev$ categorical classification · C
**jevmlx** - Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass. · Python
**system-one** - Provider-neutral System One runtime for TypeScript and Pi · TypeScript
**Jevstiller** - Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware. · Python
**typesafe.pro** - typesafe.pro: TypeSafe Jev ecosystem repository. · Python
**jev-mcp** - MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client · TypeScript
**ruby\_decision\_model** - Ruby client for decision models such as Typesafe Jev · Ruby
**spring-ai-typesafe** - A Java SDK for the TypeSafe AI JEV API, & Spring AI TypeSafe integrations. · Java
**jev-code** - Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup. · TypeScript
**hono-jev-router** - Route HTTP requests by meaning. A semantic router for Hono powered by Jev. · TypeScript
**pi-typesafe** - TypeSafe decisions for Pi: batched evaluation tool, terminal playground, and typed API for extension authors · TypeScript
**jev-judge-mcp** - Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate. · Python
**Jevbridge** - ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode. · TypeScript
**go-jev** - Go SDK and CLI for TypeSafe Jev: typed decisions $yes/no, choice, score$ from a model · Go
**jevreel** - A zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent. · Python
**vibecheck** - ✨✅ The easiest decisions your code will ever make. · Python
**jev-spring-boot-starter** - A simple Spring Boot 4 starter for TypeSafe Jev using Spring MVC and RestClient · Java
**system-one** - Batched single-token choice inference for open language models, compatible with TypeSafe · Python
**jev** - TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer · Elixir
**motion-engine** - Expressive face and body for TalkingHead avatars, decided by a classifier that reads the transcript. · JavaScript
**pijev** - Permutation Invariant Jev · Python
**llm-typesafe** - LLM plugin for accessing Jev and other TypeSafe AI models · Python
**TypeSafe** - TypeSafe SDK in Swift · Swift
**jevonian** - Local OpenAI/Anthropic/Responses-compatible proxy that uses TypeSafe Jev to route model and thinking level after protocol, context, and quota filtering; records each turn. · Go
**jev-mcp** - MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer · Python
**OpenJev** - Jev-compatible System 开源Jev · Python
**AnyDecisionModel** - A Swift package for typed decisions from language models $probabilities, choices, and scores$, with support for local MLX models and the TypeSafe Jev API. · Swift
**fastjev** - SDK-first, independently maintained SemIf fork for fast, self-hosted semantic decisions. · Python
**jev-feels** - Semantic decisions as ordinary Ruby #feels?, #decide, #score, Rails validations and pattern matching powered by Jev · Ruby
**hunch** - Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev · Ruby
**jevalyn** - The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow. · Ruby
**Jevflake** - Ask TypeSafe's Jev decision model questions about your data from inside Snowflake. dbt package plus a Terraform module. · Python
**jev-rerank** - Use Jev $TypeSafe's System One model$ as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0. · Python
**ruby\_llm-typesafe** - TypeSafe structured-output provider for RubyLLM 2 · Ruby
**jev-call-router** - Library that uses Jev by TypeSafe AI as the decision layer for phone calls · HTML
**jev-rs** - System One judgments $noul/choice/score$ from any LLM in one prefill — a Rust, Jev-compatible /v1/systemone engine · Rust
**swift-jev** - A Swift client for TypeSafe AI's Jev — typed judgements, not text · Swift
**jev-studio** - if you're experimenting with jev it will be easier from here · Python
**jev** - An unofficial, provider-neutral Unix client for Jev from TypeSafe AI. Written in Go. · Go
**typesafe-ai** - Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries. · Rust
**jevql** - psql-shaped CLI and Go/TypeScript/Python SDKs that add jev, jev\_prob, jev\_choice, and jev\_score to queries against vanilla Postgres with no extension: plain SQL runs on the server, surviving rows are judged by Jev in batches, and the client applies the filter, sort, or group. · Go
**typesafe-sdk-go** - unofficial go sdk for typesafe ai. not affiliated with or endorsed by typesafe ai. a side project built to fill the missing go sdk gap, for the community to use. · Go
**JEV\_sees** - Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras. · Python
**jev-ultralightspeed** - BRRRRRRRRRRRRRRRRRRRRRR · Python
**midscene-jev-runner** - Community-maintained JEV runner integration for Midscene Test · TypeScript
**jev4k** - A Kotlin DSL and client for TypeSafe's Jev model · Kotlin
**jev-datafusion** - DataFusion SQL functions for typed judgments. TypeSafe is one server. · Rust
**typesafe-sdk-java** - Community Java client for the TypeSafe System One API $unofficial$ · Java
**typesafe-dotnet-sdk** - Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers. Not affiliated with TypeSafe AI. · C#
**Jev** - PowerShell decisions with TypeSafe AI's Jev model: https://typesafe.ai/blog/introducing-system-one-models-and-jev · PowerShell
**duckdb-jev** - High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL. · C++
**scala-jev-sdk** - Scala SDK for Jev. No effect system bundled. · Scala
**typesafe-ai-php** - Jev for PHP, TypeSafe AI PHP SDK · PHP
**SwiftJev** - Swift framework to access Jev System One model by TypeSafe.ai · Swift
**jev-android** - A Kotlin Android SDK for UI automation powered by TypeSafe Jev, with an accessibility runtime and sample app. · Kotlin
**kojev** - Kotlin Multiplatform client for Jev that returns your own enum/sealed types instead of string keys. · Kotlin
**dsh-jev-plugin** - DeepSeek Harness plugin for TypeSafe Jev: typed decisions, configurable guardrails, and Web UI result cards. · TypeScript
**TypeSafeJevPlayground** - TypeSafe Jev Playground - idiomatic .NET port of typesafe-ai/typesafe-sdk-js v0.6.0 · C#
**one-system** - Use local and hosted classifiers aka decision models aka Jev-like models, all through a single TypeSafe API · TypeScript
**jev.nu** - Nushell module for the TypeSafe System One API: typed decisions with calibrated probabilities · Nushell
**typesafe-sdk-go** - Community TypeSafe SDK in Golang · Go
**jevgo** - Unofficial Go client for the TypeSafe AI System One API $Jev$ — typed questions in, calibrated answers out. · Go
**typesafe-client** - Unofficial Go and Rust clients for the TypeSafe AI System One API $Jev$ · Rust
**jev-dsl** - Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels · Haskell
**zod-jev** - zod-jev: TypeSafe Jev ecosystem repository. · TypeScript
**JevSwiftSDK** - An independent, type-safe Swift SDK for TypeSafe Jev, with async/await, batching, retries, and SPM support. · Swift
**system\_one\_client** - Elixir client for System One decision models: TypeSafe Jev, Cloudflare Clef, OpenRouter, self-hosted $CLM$. Full probability distributions, behaviour + stub, retries, telemetry. · Elixir
**llama-index-jev** - LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge. · Python
**daf-jev** - daf-jev: composable Python toolkit for TypeSafe's Jev $System One$ decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill · Python
**typesafe-ai-rs** - Independent async and blocking Rust SDK for the TypeSafe AI System One API · Rust
**typesafe-sdk** - Ruby client for typesafe.ai · Ruby
**n8n-nodes-jev-classification** - n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching. · TypeScript
**gut** - 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. · Python
**jev-mcp** - MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin. · TypeScript
**hunch** - Ask Jev over columns of data: closed-set questions, cached and joined back. · Python
**jev-java** - Unofficial Java SDK for TypeSafe Jev and Vercel AI Gateway, with Spring Boot and WebClient support · Java
**TypeSafeAI.Net** - .NET SDK for the TypeSafe AI platform · C#
**hiep-paseo-plugin** - Local Paseo plugin exposing Jev evaluations through MCP · TypeScript
**jev-sdk-java** - Type-safe Java 21 client for the TypeSafe AI Jev $System One$ decision API · Java
**jev-java** - Idiomatic Java SDK for TypeSafe AI Jev System One decision engine · Java
**jevbrief** - Clean, traceable state briefings for TypeSafe's Jev model · Python
**jev-go** - Community Go SDK for TypeSafe AI Jev / System One · Go
**sael** - Go client for the TypeSafe System One API $Jev$ — the first piece of sael, a content-safety classifier for an AI request relay · Go
**jev-ui** - React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev. · TypeScript
**jev-php** - A PHP library to connect to TypeSafe JEV APIs · PHP
**jev-go** - Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text · Go
**jev** - A Go client for the TypeSafe AI's System One API and its model, Jev. · Go
**jevshield** - Sub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev $System-1$ decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready. · Python
**ex-regex** - Match meaning in Python. Find, replace, extract, and compose semantic patterns with typed decisions, explicit uncertainty, and exact replay. · Python
**typesafe\_sdk** - An idiomatic, type-safe Elixir port of the official TypeScript AI SDK $ai / ai-sdk$ providing unified LLM integrations, streaming text and structured outputs, tool calling, and agentic workflows. Jev is their current flagship model and is the first System One model. · Elixir
**duckdb-dual-cognition** - Native DuckDB extension composing fast System One judgments with selective System Two reasoning, provenance, batching, and caching. · C++
**typesafe-jev-bridge** - Use the TypeSafe Jev decision model $System One$ anywhere: zero-dependency OpenAI-compatible bridge for 9Router, Claude Code, Cursor, Cline & any OpenAI SDK. Typed yes/no, choice & score judgments via CLI or HTTP. · JavaScript
**typesafe-dotnet** - Unofficial .NET client for the TypeSafe AI System One API · C#
**ai-provider-for-jev** - Connect WordPress to TypeSafe's Jev System One model for structured decisions $choice, score, noul$. · PHP
**jev** - Ruby client for the typesafe AI Jev model · Ruby
**dsh-jev-adapter** - Use the Jev $System One$ decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. A jev\_decide tool for DeepSeek Harness $dsh$. · JavaScript
**protoc-gen-jev** - Experimental plugin to convert protobuf into Jev code · Go
**openjev** - Open, local, zero-cost reimplementation of the Jev decision layer for job postings · Python
**ElBruno.AI.Decisions** - Community .NET 10 SDK for official TypeSafe AI Jev typed decisions and Microsoft.Extensions.AI integrations. · C#
**question-kit** - Tool kits for building with System-One models · TypeScript
**typesafe4s** - A type safe Typesafe Scala 3 SDK · Scala
**henriquekieckbusch-module-jev** - AI-powered decisions for Magento 2: Jev analyzes orders, customers, products, reviews and abandoned carts and writes the answer right in your admin. · PHP
**typesafe-sdk-swift** - Swift SDK for TypeSafe AI · Swift
**SystemOneDotNet** - .NET client for TypeSafe System One $Jev$ — typed questions in, typed answers with probabilities and confidence out. No prompt engineering, no output parsing. · C#
**typesafe-ai-java** - Community-maintained Java SDK for the TypeSafe AI System One $Jev$ API. Not an official TypeSafe product. · Java
**rlcd-gateway** - 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. · Go
**connector-for-typesafe-jev** - WordPress connector for TypeSafe Jev: typed, confidence-scored answers your code can branch on. · PHP
**typesafe-ai-go** - Community-maintained Go SDK for the TypeSafe AI System One evaluation API, with typed questions, fluent builders, retries, and examples. · Go
**jevtok** - Exact token counting and request-cost prediction for TypeSafe's Jev $tiktoken-style$ · Python
**dsh-jev-decide** - DSH plugin: register TypeSafe Jev $System One decision model$ as an agent tool — jev\_decide returns calibrated probabilities $noul/choice/score$ for routing/triage/guardrail judgments, no text generation. 把 TypeSafe Jev 决策模型注册为 DSH agent 工具 · JavaScript
**tenbin** - MCP server and agent skill for the TypeSafe AI System One API $Jev$: decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code · TypeScript
**verdict4s** - A Scala 3 client for TypeSafe AI's Jev, a decision model that answers typed questions about your program state with choices, scores and calibrated probabilities instead of text. · Scala
**typesafe-go** - Idiomatic Go SDK for the TypeSafe AI API · Go
**jevegis** - Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT. · TypeScript
**jev-go-sdk** - Dependency-free Go client for TypeSafe AI's System One API and the Jev model · Go
**typesafe-jev-mcp** - MCP server exposing TypeSafe's Jev model as a typed evaluate tool. · Rust
**jev-accounts-hub** - A multi-account manager and API gateway for Jev. 一个用于 Jev 的多账户管理器和 API 网关。交流群：1102910606 · Go
**typesafe-ai-rust-sdk** - typesafe-ai-rust-sdk: TypeSafe Jev ecosystem repository. · Rust
**jev-net** - A lightweight .NET client for the TypeSafe AI API $System One / Jev$. One dependency; a faithful port of the official Python SDK. · C#
**laravel-typesafe-jev** - Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes. · PHP
**jev-shield** - 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. · JavaScript
**jev-mcp** - MCP server for Jev $TypeSafe AI's System One model$ — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com · JavaScript
**jev-mcp** - MCP local que expone Jev $TypeSafe$ como herramienta para Claude Code, Codex, Hermes y cualquier agente: ask\_jev y list\_jev\_models, sin dependencias · Python
**typesafe-sdk-rust** - Rust SDK for the TypeSafe AI API · Rust
**openrouter-jev-mcp** - High-speed System One Jev AI decision gateway and MCP server powered by OpenRouter · Python
**jevgo** - Go client for TypeSafe AI's System One API $Jev$, with optional Langfuse instrumentation · Go
**jev-mcp** - MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe · Go
**typesafe-sdk-dotnet** - Unofficial .NET port of the TypeSafe AI client SDK $typed questions & answers$ · C#
**hfjev** - Classify Hugging Face datasets across typed semantic dimensions with TypeSafe Jev System One. · TypeScript
**jev-ios-bridge** - Bridge that lets Claude Code verify an iOS app on a simulator, with TypeSafe's Jev choosing each step $planning stage$ · TypeScript
**taurus-jev-sdk-go** - Unofficial, dependency-free Go client for the TypeSafe AI System One API and the Jev model. Validated responses, masked credentials, bounded retries. · Go
**Mechanical-Jev** - The asking side of Jev $TypeSafe System One: noul, choice, score$ in Rust: client library, mjev CLI, evaluation harness, and Jev reverse engineered from its docs. Talks to Intel-Phi-Jev. · Rust
**pi-typesafe-jev** - A pi extension that exposes TypeSafe $Jev, System One$ judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions. · TypeScript
**JEV-MCP-REST** - JEV-MCP-REST: TypeSafe Jev ecosystem repository. · C#
**jod** - Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers. · TypeScript
**nf-jev** - TypeSafe Jev plugin for example · Groovy
**dsh-jev** - DSH bundle that registers jev\_ask for TypeSafe Jev noul, choice, and score answers. · TypeScript
**typesafe-sdk-cpp** - An unofficial CPP 20 SDK for the TypeSafe API · C++
**SystemOneSharp** - A .NET client for the System One API used by Jev and compatible Laya servers · C#
**llm-schema-lite** - “LLM-ify” your JSON schemas · Python
**jev-relevance** - Drop-in relevance filter for LangChain RAG retrievers powered by TypeSafe Jev. · Python
**vellum** - Markdown to Sanity documents, with a classifier instead of an LLM. Jev decides, code copies. Experimental. · TypeScript
**dbt\_jev** - use jev in dbt · Python
**jev-mcp** - Local MCP server exposing TypeSafe Jev $System One decision model$ as native Claude Code / Codex tools · Python
**Jev4Mellea** - Jev adapter to Mellea · Python
**jev-mcp-server** - MCP server for Jev $TypeSafe System One$: the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call. · Python
**jevclient** - Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse. · Python
**playwright-jev** - Structured JEV decisions for Playwright: failure triage, smart retries, healer gating, snapshot pruning, locator healing, semantic assertions, and test impact ordering. · TypeScript
**Memworthy** - Decide what an AI system should remember: policy-driven memory gating with typed judgments. · Python
**godot-jev** - Godot 4.7+ addon that wraps TypeSafe AI's Jev System One HTTP API to evaluate game state. · GDScript
**typesafe-sdk** - PHP & Laravel SDK for TypeSafe AI's JEV Model series · PHP
**typesafe-sdk-php** - typesafe-sdk-php: TypeSafe Jev ecosystem repository. · PHP
**systemone** - One CLI and Jev-compatible API for local and hosted typed-decision backends $planning$ · HTML
**adk-go-typesafe** - TypeSafe AI System One integration and utilities for adk-go · Go
**claude-jev** - Jev System One for Claude Code — typed Choice/Noul/Score via live TypeSafe API $mirror of opencode-openjev, live-only MCP$ · JavaScript
**anofox-decide** - DuckDB extension: evaluate natural-language predicates and answer sets with TypeSafe Jev or local open decision models $Julia-1, Laya$ · C++
**fuzzy-jev** - 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 $native and wasm32$. · Rust
**nu\_plugin\_jev** - Nushell plugin for TypeSafe Jev structured decisions · Rust
**jev-go** - jev-go: TypeSafe Jev ecosystem repository. · Go
**typesafe-claude-kit** - Claude Code kit for TypeSafe $Jev$: agents, skill, client, calibration tools · Python
**codex-jev** - Evidence selection and quota-aware recovery for Codex. Optional Jev reranking, local privacy controls, exact source reads. Keep your coding model. · JavaScript
**s1\_ruby** - Makes S1-model 'measurement' $and the collapse that follows it$ a Ruby primitive. · Ruby
**jevfilter** - Turn a user's search sentence into filters your API already accepts, powered by Jev · TypeScript
**jev-playwright-mcp** - Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent. · TypeScript
**deep-jev-seek** - Use DeepSeek/llamacpp like Jev · TypeScript
**mcp-server-jev** - Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool. · JavaScript
**typesafe** - An idiomatic Elixir client for the TypeSafe AI API · Elixir
**jev-php-sdk** - PHP SDK for TypeSafe's Jev: send text and typed questions, get typed answers with calibrated confidence. PHP 8.1+, works with any PSR-18 client, Laravel 8–13. · PHP
**laya-server** - Run the Laya System One decision model locally behind TypeSafe's Jev wire API, with a demo page · Python
**guideme-rust** - 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. · Rust
**qualm** - Typed decisions from a System One model, where uncertainty is something you have to handle. · TypeScript
**jev-mcp** - MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents · Python
**promptrejectormcp** - Open-source MCP and HTTPS screening for prompts, skills, and tool descriptions using TypeSafe AI Jev, deterministic checks, and configurable reasoning. · TypeScript
**gosys1** - Client for TypeSafe's SystemOne API for Jev · Go
**jev-dotnet** - An opinionated and convention-based .NET implementation of the Jev Classification AI by TypeSafeAI · C#
**jevguard-mcp** - Official Model Context Protocol $MCP$ server for JevGuard and TypeSafe AI · Python
**jev-driver** - Typed Rust driver for TypeSafe AI's Jev $System One$ decision model · Rust
**jev\_dart** - Typesafe Jev Api · Dart
**hunch-js** - Jev judgments as TypeScript functions over arrays: classify, score, check, where, extract, pick, rank, verify. LLMs propose, Jev decides. · TypeScript
**tinystruct-typesafe-sdk** - A tinystruct-based TypeSafe SDK with JEV model. · Java
**jev-bridge** - Jev-style /v1/systemone API in front of any OpenAI-compatible LLM server $one-token logprob scoring, MIT$ · Python
**jev-harness** - harness for jev · Python
**typesafe-sdk** - GitHub project related to TypeSafe AI / Jev: typesafe-sdk-csharp/typesafe-sdk · C#
**decision-gate** - Rate and spend limits for code that calls Jev and other decision models · JavaScript
**s1-rs** - Typed System One layer for Rust $Choice/Score/Noul$. · Rust
**typesafe-rs** - Latency-first Rust SDK for TypeSafe System One. · Rust
**s1-core** - S1-Core — a zero-dependency Python harness for System 1 decision models $Jev & friends$: choice/score/noul specs, fail-closed calibration gates, wave-parallel fan-out, replayable audit ledger. · Python
**jev-mcp** - TypeSafe AI Jev MCP server for bounded probabilistic decisions: four read-only stdio tools for choices, routing, risk signals, and yes/no gates. Conservative second opinions with installers for Codex, Claude Code, Cursor, Kimi, Gemini CLI, and other MCP clients. · TypeScript
**typesafe-sdk-ruby** - Unofficial Ruby SDK for the TypeSafe AI API $Jev model$ - typed questions, retries, and typed errors. Community port of typesafe-sdk-js. · Ruby
**clickhouse-jev** - Natural-language predicates, probabilities, and classification for ClickHouse, powered by Jev. · Python
**s1gate** - Native System One inference gateway for HTTP and MCP. · Rust
**jev-decision-mcp** - Local MCP server for TypeSafe Jev typed decisions, with Codex integration · TypeScript
**system\_one\_dart** - jev: TypeSafe Jev ecosystem repository. · Dart
**jev** - Unofficial Go client for TypeSafe's System One API and its model, Jev. · Go
**switchboard** - Guardrail + model router for LLM gateways on TypeSafe's Jev $System One model$, with an independent accuracy/calibration/latency evaluation. Stdlib Python. · Python
**clojev** - Unofficial portable Clojure SDK for TypeSafe System One · Clojure
**jev-mcp-open-source** - Self-hosted Jev MCP on Cloudflare Workers with intent routing, retrieval reranking and batch judgments · TypeScript
**jev-lcm-dsh-compaction** - Calibrated Jev ranking before lossless context condensation · TypeScript
**hunch-ts** - Probabilistic control flow for TypeScript - powered by TypeSafe's Jev · TypeScript
**jev-mcp** - Lightweight MCP server exposing TypeSafe Jev decision tools via OpenRouter for Hermes Agent · Python
**typesafeai-go** - Go SDK for TypeSafe AI API https://docs.typesafe.ai/api · Go
**jev-dotnet** - Unofficial .NET SDK for TypeSafe AI's Jev System One model. Typed Choice/Score/Noul judgments with calibrated confidence, zero dependencies. · C#
**jev-guard** - Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty. · TypeScript
**jev-decision** - Zero-dependency System 1 decision engine, calibrated guardrails, and token optimization client for Jev $TypeSafe AI$ · Python
**typesafe-go** - unofficial go SDK for typesafe AI, with typed answers, retries, and context support · Go
**jevlin** - Zig SDK for TypeSafe AI's Jev decision API. Typed classification, scoring and yes/no probabilities with bounded buffers, retries and deadlines. · Zig
**typesafe-sdk-java** - This is an unofficial community port and is not supported by TypeSafe. · Java
**typesafe-ai-go** - typesafe-ai-go: TypeSafe Jev ecosystem repository. · Go
**jev-client** - Shared Typesafe judgement client used by zillow-agent and coin-launch-agent · Python
**go-jev** - Go client for the TypeSafe System One $Jev$ API · Go
**typesafe-jev-ruby** - Ruby client for Jev, TypeSafe's System One model: typed questions, probabilistic answers. Zero runtime dependencies. · Ruby
**typesafe-sdk-go** - Go SDK for TypeSafe AI. · Go
**jev-kol-mcp** - TypeScript MCP server that finds TikTok and YouTube micro-KOLs, tags their niche, scores campaign fit with Jev, and drafts outreach emails. Results are cached locally in SQLite. · TypeScript
**jev-acp** - Use Jev typed decisions from any ACP $Agent Client Protocol$ client or IDE · TypeScript
**composable-jev** - A library to chain Jev calls, for the deranged and enlightened · PHP
**node-decision-model** - Node client for decision models such as Typesafe Jev · TypeScript
**abap-jev-client** - An ABAP client for the TypeSafe's Jev decision model API. · ABAP
**typesafe-mcp** - 🧠 MCP server for TypeSafe's Jev model · JavaScript
**nifi-jev** - Apache NiFi processor for TypeSafe Jev semantic routing with uncertainty lane · Java
**decide** - One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback · Python
**typesafe-sdk-go** - Go SDK for TypeSafe AI — classification and rating primitives over text and JSON · Go
**jev-go** - Unofficial Go SDK for TypeSafe AI's Jev API · Go
**sub2api** - sub2api: TypeSafe Jev ecosystem repository. · Go
**jev-readability** - jev-readability: TypeSafe Jev ecosystem repository. · JavaScript
**typesafe-ai-ruby** - Ruby client for the TypeSafe AI$Jev$ System One API · Ruby
**typesafe-sdk-godot** - TypeSafe SDK for Godot 4.7, at parity with the Python SDK and the HTTP API reference. · GDScript
**jev-mcp** - A Rust MCP server for TypeSafe AI Jev structured decisions · Rust
**jev.zig** - An unofficial Zig client for the TypeSafe System One API $Jev$ · Zig
**libtypesafe** - Unofficial C++17 client for the TypeSafe AI API · C++
**semantic-operators** - An abstraction for System One models, currently supporting TypeSafe's Jev and Laya. Typed questions, probabilities, and "don't know" instead of a guess, from Python, the command line, or MCP · Python
**JevApi** - JevApi — .NET tooling for the TypeSafe AI Jev model, which evaluates typed questions $noul/choice/score$ against a state and returns structured answers with probabilities and confidence. · C#
**jev-toolkit** - MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server $jev mcp$ serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana. · TypeScript
**typesafe-client** - Unofficial typed async Rust client for the TypeSafe System One API · Rust
**typesafe-sdk-go** - Unofficial Golang library for the TypeSafe API · Go
**dsh-plugin-jev** - TypeSafe Jev $System One decision model$ as a native jev\_decide tool plugin for DeepSeek Harness · JavaScript
**jev-kit** - Jev toolkit for building fast, testable AI decision points for agent permissions, routing, semantic change detection, and evidence checks. · TypeScript
**typesafe-sdk-rust** - GitHub project related to TypeSafe AI / Jev: Ketankhunti/typesafe-sdk-rust · Rust
**kunobi-decision** - Rust client for the TypeSafe System One API $Jev$ · Rust
**jev-go** - TypeSafe.ai Jev Go SDK · Go
**jev-kit** - A growing kit of Jev-powered tools for Claude, ChatGPT, your browser and your terminal, starting with Laugh Track. · JavaScript
**jev-bridge** - A zero-dependency MCP server for TypeSafe's Jev — calibrated, typed judgments for Claude Code, with a local answer cache and cost tracking. · JavaScript
**jevcore** - JEV core — the judgement primitive and harness for TypeSafe System One $Jev$. Closed-set, fail-open, stdlib-only. · Python
**typesafe-ai-dart** - typesafe-ai-dart: TypeSafe Jev ecosystem repository. · Dart
**Minos.NET** - Unofficial .NET client for TypeSafe's Jev System One API — source-generated, Native AOT, allocation-conscious · C#
**typesafe-mcp** - Research and scaffolding for a TypeSafe Jev MCP server · TypeScript
**typesafe.zig** - An idiomatic Zig client for the TypeSafe AI API · Zig
**jev-typesafe-dotnet** - .Net SDK for the TypeSafe Jev API · C#
**typesafeai-systemone-jev-go** - Typed Go client for the TypeSafe System One API $Jev$: structured questions and answers your code can act on. Community SDK, MIT. · Go
**jev-hooks** - Compose typed Jev judgments as reactive semantic state in React and backend programs · TypeScript
**go-discern** - 🧭 Typed Go decision layer for the TypeSafe Jev and Cloudflare Clef System One APIs · Go
**generation-sdk** - generation-sdk: TypeSafe Jev ecosystem repository. · TypeScript
**agent-workflow-typesafe-ai** - Standalone TypeSafe AI/Jev semantic-evidence adapter for bounded Agent-Workflow decisions, explicit uncertainty, compatibility evaluation, and host-owned policy. · Python
**typesafe-go** - Zero-dependency Go SDK for TypeSafe's System One API $Jev$. Typed questions in, calibrated probabilities out with static analyzers that catch bad question design at build time, a decision layer, batching and caching. Not affiliated with TypeSafe AI. · Go
**measuretwice** - Readable AI checks, measured decision policies, and inspectable reports. · TypeScript
**Jev.Sdk** - A .NET client library for the \[TypeSafe AI\]$https://typesafe.ai$ System One API $\https://api.typesafe.ai\$. · C#
**jev-excel** - jev-excel: TypeSafe Jev ecosystem repository. · JavaScript
**guideme-python** - Type-safe inline judgments from TypeSafe Jev, for Python · Python
**guideme-typescript** - TypeScript guideme SDK: a TypeSafe Jev judgment as control flow · TypeScript
**typesafe-sdk-go** - A type-safe Go SDK for building reliable integrations with strongly typed APIs. Designed to provide an idiomatic developer experience, compile-time safety, and convenient abstractions while reducing boilerplate and preventing common runtime errors. · Go
**vllm2jev** - Jev-compatible adapter for vLLM: use any vLLM-served LLM for Choice, Score, and Noul decisions via logprobs—without modifying the model or vLLM service. · Python
**TypeSafe.Jev** - Typed AI decisions for .NET: ask Jev $TypeSafe AI System One$ yes/no, choice and score questions and get a C# enum with calibrated probabilities back. · C#
**jevface** - Typed judgments for Java: declare questions as an interface and let Jev answer them. · Java
**typesafeai-go** - An unofficial, dependency-free Go $Golang$ SDK for the TypeSafe System One API · Go
**jev-mcp** - MCP server that gives coding agents a judge: twelve jev\_\* tools for typed decisions and probabilities, plus a tray app and a Claude Desktop bundle. · TypeScript
**use-jev** - MCP server + CLI exposing TypeSafe's Jev judgment model as typed noul/choice/score tools — with a typed escalation contract, an action gate, and TypeSafe/OpenRouter/Vercel/mock backends · JavaScript
**jev-compare** - jev-compare: TypeSafe Jev ecosystem repository. · TypeScript
**gojev** - Go harness for Jev/Kev decision models: TypeSafe, Vercel AI Gateway, and in-process Kev via llama.cpp · Go
**honeytongue** - Characters players can actually argue with: a persuasion mechanic for JavaScript games where players type or speak to NPCs. Powered by Jev. · JavaScript
**jev-mcp** - MCP server exposing TypeSafe's Jev typed-decision model over the TypeSafe API or OpenRouter · Go
**jev-symfony-bundle** - Unofficial Symfony bundle for TypeSafe AI's Jev: typed client, validator constraints, Messenger, Workflow guards and profiler panel · PHP
**typesafe\_sdk\_ex** - Typesafe AI SDK in Elixir using Req · Elixir
**jev-typesafeai** - jev-typesafeai: TypeSafe Jev ecosystem repository. · TypeScript
**gram-render** - Near-instant generative UI for Telegram bots, powered by JEV. · TypeScript
**decido** - Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright. · Python
**typesafe-go** - A general-purpose Go SDK for TypeSafe AI, including Jev models and the System One API. · Go
**metajev** - Cache the decision, compute the policy. Record typed decisions from Jev-class System One models under a key built from state, question, and model, then change thresholds, review bands, routing, and budgets without re-running anything. · Python
**decision-model-sdk-rust** - Unofficial async Rust SDK for the TypeSafe AI System One API: typed questions via #\[derive$QuestionSet$\], a port of typesafe-sdk-python. · Rust
**pi-taskmesh** - Pi Jev System One integration with TypeSafe Direct and Vercel AI Gateway transports · TypeScript
**jev-api-adapter** - Jev decision bridge for OpenAI Chat Completions and Responses on Cloudflare Workers and Vercel · TypeScript
**typesafe-jev-sdk** - TypeSafe AI Jev API Wrapper SDK · Rust
**nest-decisions** - nest-decisions: TypeSafe Jev ecosystem repository. · TypeScript
**typesafe-sdk-swift** - The unofficial Swift library for the TypeSafe API
**typesafe-laravel** - Laravel integration for typesafe-php — config, facade, and Http::fake-friendly transport. Unofficial; not affiliated with TypeSafe. · PHP
**typesafe-php** - Unofficial PHP client for TypeSafe's System One API $Jev$ — typed noul, choice and score judgements. Not affiliated with TypeSafe. · PHP
**jev-native-mcp** - Review public code and documents with Jev in Codex and Claude Code: ranking, batch screening, claim checks, spend limits, and evaluation tools. · Python
**ak-jev** - Node.js bindings for TypeSafe's Jev — the System One model. Typed decisions, probabilities and confidence, with no text generation and no parsing. · JavaScript
**judgevet** - Typed client, CLI and MCP server for TypeSafe's Jev $System One$ judgment model · Python
**Jev.DotNet** - Jev.DotNet: TypeSafe Jev ecosystem repository. · C#
**pi-jev** - Single-file pi extension for batched TypeSafe Jev judgments · TypeScript
**ripwire-broker** - Task-oriented, budgeted MCP code context over Ripwire: three tools, hooks for Claude Code and Codex, optional relevance scoring and per-workspace memory via TypeSafe Jev, optional local-model notes · Rust
**askif** - Let Jev decide. Typed decisions for your code: ask.if, ask.switch, ask.score. · TypeScript
**typesafe-sdk-go** - Unofficial Go port of the TypeSafe AI SDK · Go
**fast-opencode-compaction** - opencode V2 adapter for fast-jev-compaction: prunes stale tool calls and results from the outgoing request using a typed-decision endpoint · TypeScript
**node-red-contrib-jev** - Typesafe.AI Jev integration · HTML
**jev-claude-skill** - Claude Code skill for TypeSafe's Jev decision model — typed decisions via TypeSafe, Vercel AI Gateway or OpenRouter · Python
**Jev.TypeSafe.AI** - Unofficial dotnet port of https://github.com/typesafe-ai/typesafe-sdk-js · C#
**hunch** - CLI for asking TypeSafe's Jev model yes/no, multiple-choice and scoring questions · Rust
**laya-api** - laya-api: TypeSafe Jev ecosystem repository. · Python
**typesafe-demo-mcp** - MCP server exposing TypeSafe System One judgments $noul, choice, score$ as agent tools · TypeScript
**local-laya** - local-laya: TypeSafe Jev ecosystem repository. · TypeScript
**typesafe-sdk-go** - Community SDK for Typesafe.ai in Go · Go
**jevwrapper** - English in. Typed JEV decisions out. Inspectable LLM-to-JEV middleware, a browser sandbox, and reusable examples. MIT licensed. · JavaScript
**jev-rag-gate** - Semantic gating for RAG retrieval candidates $relevance, premise contradiction, prompt injection$ using the TypeSafe Jev System One model · Python
**criteria-adapter-decision** - Decision adapter $System One decision models: TypeSafe Jev, Ollama /v1/systemone$ for the criteria workflow engine · Go
**jevcore** - TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default. · TypeScript
**AskJev-MCP** - MCP server for TypeSafe's System One API $Jev$: typed choice/noul/score judgments with calibrated probabilities and confidence · JavaScript
**vai2jev** - vercel ai-gateway 转换为标准TypeSafe-AI接口 · JavaScript
**jev** - jev: TypeSafe Jev ecosystem repository. · Python
**csharp-typesafe-sdk** - SKD on C# for Model Jef · C#
**jev-java** - Unofficial Java SDK for TypeSafe AI's Jev System One model. Typed Choice/Score/Noul judgments with calibrated confidence, zero dependencies $JDK 21+$. · Java
**jev-rerank** - Jev-powered relevance filtering and reranking for RAG. Score, sort, and filter retrieved passages with one batched call. Drop-in reranker at a fraction of hosted-rerank cost. · Python
**dsh-jev-guardrails** - dsh-jev-guardrails: TypeSafe Jev ecosystem repository. · TypeScript
**jev-mcp** - MCP server exposing one tool: ask Jev a typed question and get a short answer back. · TypeScript
**system-one-adapter-rust** - Rust port of TypeSafe system-one-adapter $LLM-backed system\_one evaluations$ · Rust
**typesafeai-sdk-rust-community** - Community-built Rust SDK for the TypeSafe AI API $System One / Jev$. A port of typesafe-sdk-python · Rust
**ZCode-Jev** - 把 TypeSafe Jev 轻量决策模型接入 ZCode 的决策外脑工具包：零依赖 MCP server（route/grill/review/risk/complete 五个决策工具）+ skills + 治理文档，在任务生命周期关键关口做廉价判断 · Python
**JevWrapper** - JevWrapper: TypeSafe Jev ecosystem repository. · C#
**decide-mcp** - Configurable decision MCP server with AI SDK, Jev, percentage scores, and bias profile routing · TypeScript
**jevfilter** - Filter anything with plain-English rules, powered by TypeSafe's Jev. · Python
**jev-mcp** - MCP server for TypeSafe Jev $System One$: one typed evaluate tool over streamable HTTP · Python
**localjev-mcp** - localjev-mcp: TypeSafe Jev ecosystem repository. · JavaScript
**jev** - Result-based TypeSafe System One client library and jev command-line interface. · TypeScript
**nightwatch** - Decides what to do with a failed BullMQ job. Rules answer the errors they know, TypeSafe Jev answers the rest, and the queue moves only when the answer is sure enough. · TypeScript
**typesafe-java** - Java client and CLI for the TypeSafe AI API. Support local models like CLEF and LAYA via ONNX Runtime · Java
**n8n-nodes-typesafe-ai** - n8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities · TypeScript
**rjif** - jif: calibrated if-statements in R via TypeSafe Jev — judgment-based control flow with reliability curves for biostatistics · R
**jev-mcp** - MCP server for decision models with TypeSafe Jev, Cloudflare Clef, OpenRouter, and local providers. · TypeScript
**JevSysUno** - TypeSafe / Jev community project: Dujaydis/JevSysUno. · TypeScript
**jevmcp** - TypeSafe AI JEV MCP Server - Tooling, Code Audit, CI/CD chain analysis, other SDLC related tools · Python
**jev-mcp** - jev-mcp: TypeSafe Jev ecosystem repository. · Python
**typesafe-sdk-csharp** - typesafe-sdk-csharp: TypeSafe Jev ecosystem repository. · C#
**jev-mcp** - A repository for jev-mcp · Python
**Jev-Csharp** - Jev-Csharp: TypeSafe Jev ecosystem repository. · C#
**JevKit** - JevKit is an open-source decision infrastructure that helps developers integrate Jev into their applications, define structured decision tasks, evaluate model performance, and build reliable fallback policies. · Python
**dsh-jev-core** - Shared TypeSafe Jev decision-model client for the dsh ecosystem: strict response validation, keychain-first key resolution, typed fail-open errors. Jev-optional by design. · JavaScript
**jev-mcp** - jev-mcp: TypeSafe Jev ecosystem repository. · Go
**jev-kit** - Typed client and benchmark harness for Jev, TypeSafe AI's System One decision model, through the Vercel AI Gateway. Measure accuracy, calibration and cost on your own data before you trust a threshold. · TypeScript
**ext-typesafe-ai** - Flow Steward extension for Jev is TypeSafe’s flagship model and the first System One model · Python
**jev-secrets** - Pseudonymisation wrapper for Jev queries · PHP
**typesafe-sdk-php** - Unofficial PHP library for the TypeSafe API · PHP
**jev-gateway** - TypeSafe Jev API gateway with official SDK compatibility and a simple ask endpoint, built for Vercel. · TypeScript
**ai** - ai: TypeSafe Jev ecosystem repository. · Rust
**ooda** - Rust client + type system for typed, calibrated decision models $Jev/Laya-compatible System One APIs$. Bounded Choice/Score/Noul questions in, typed confidence-scored answers out. · Rust
**decisionpacks** - Versioned Jev decision contracts with typed validation, deterministic policies and historical replay. · JavaScript
**flink-jev** - Flink SQL ML\_PREDICT provider for TypeSafe Jev semantic decisions · Java
**jev-acceslibre-needs** - Compare les besoins d’accessibilité d’une personne aux caractéristiques déclarées d’un établissement. · JavaScript
**jev-agribalyse-claim-check** - Vérifie si une allégation environnementale alimentaire est soutenue par la référence AGRIBALYSE citée. · JavaScript
**jev-air-episode-context** - Explique un épisode de pollution atmosphérique à partir de mesures réglementaires sans recalculer les seuils officiels. · JavaScript
**jev-alimconfiance-followup** - Compare des contrôles sanitaires successifs et prépare une conclusion de suivi sourcée et révisable. · JavaScript
**jev-anr-overlap** - Repère les recouvrements thématiques possibles entre projets de recherche financés. · JavaScript
**jev-association-dossier-proof** - Évalue la cohérence entre l’objet déclaré d’une association, ses activités et une demande de financement. · JavaScript
**jev-avant-boamp** - Détecte dans les délibérations locales des signaux d’achat public avant la publication d’un avis BOAMP. · JavaScript
**jev-baac-scene-pattern** - Regroupe des accidents corporels en configurations descriptives sans attribuer de causalité individuelle. · JavaScript
**jev-balo-material-event** - Transforme une annonce BALO en événement d’entreprise structuré et signale les changements potentiellement significatifs. · JavaScript
**jev-bnf-authority-match** - Résout une mention ambiguë vers des autorités BnF candidates et conserve les rapprochements incertains en revue. · JavaScript
**jev-bocc-impact** - Relie les évolutions des conventions collectives à leurs impacts paie et RH, après filtrage exact par IDCC. · JavaScript
**jev-cada-desk** - Prépare le triage des demandes de documents publics à partir de précédents CADA sourcés. · JavaScript
**jev-carbone-factor-fit** - Classe les facteurs d’émission ADEME candidats pour un libellé d’activité ou de dépense. · JavaScript
**jev-certfr-inventory-fit** - Rapproche un inventaire logiciel des avis CERT-FR et rend les correspondances incertaines révisables. · JavaScript
**jev-climat-batiment-scenarios** - Relie un projet de bâtiment aux vulnérabilités décrites par les scénarios climatiques prospectifs français. · JavaScript
**jev-cnccfp-expense-review** - Prépare la revue de libellés de dépenses électorales et rend visibles les rattachements ambigus. · JavaScript
**jev-concurrence-precedent-map** - Classe les précédents de l’Autorité de la concurrence pertinents pour une pratique économique décrite. · JavaScript
**jev-dataes-practice-fit** - Rapproche un besoin de pratique sportive des caractéristiques documentées des équipements français. · JavaScript
**jev-datagouv-join** - Resolve ambiguous joins between French public datasets with auditable candidates. · JavaScript
**jev-datagouv-schema-drift** - Qualifie les évolutions de schéma et de ressources d’un jeu de données référencé sur data.gouv.fr. · JavaScript
**jev-datatourisme-intent-fit** - Rapproche une intention de sortie de lieux touristiques documentés et justifie les propositions en français. · JavaScript
**jev-debat-trace** - Suit la manière dont les arguments d’un débat pu

Frequently asked questions

What is Awesome JEV?

Search Jev / System One projects and read their recorded inclusion evidence.

How do I install Awesome JEV?

It runs as a remote server. In Claude Code: claude mcp add --transport http awesome-jev 'https://awesomejev.cc/api/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Awesome JEV need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Awesome JEV open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains Awesome JEV?

It is published by daftAI2026. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.

Server details

Listed in: Official MCP Registry
Publisher: daftAI2026
Category: Search and web
Runs: Remote
GitHub stars: ★ 14
Language: TypeScript
Last commit: Oct 24, 2026
Open issues: 0
Version: 1.0.0
Published: Oct 20, 2026

io.github.daftAI2026/awesome-jev

Similar servers

OwnSearch Quality-ranked SearXNG search over MCP with local fleet state, scoring, and merged resu...
haiku.rag Local-first agentic RAG with citations - hybrid search, reranking, multimodal document ...
Plumb Registry Search and verify fire protection contractor licenses (TX SFMO, CA CSLB C-16) from stat...
AiAkiv Memory Shared long-term memory for AI agents: save and recall context as a searchable knowledg...
Fold Laboratories Original art from galleries and artists: search, details, delivered prices and checkout...
Memento Agent memory MCP server with 4-type cognitive memory, hybrid search, and TTL-based forg...
SearXNG Search MCP server for SearXNG — privacy-respecting web search with pagination, URL reading
OpenGit Search agent-ready open source repos by task, interface, ecosystem and OG score.

Search and web