Awesome JEV

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

Contents

• 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

• 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
• cua - Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation. · Rust
• 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
• 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
• 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
• jev-social - Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports. · JavaScript
• 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
• system1-agents - System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics · Python
• 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
• 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-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
• 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
• jevify - An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments. · Python
• 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
• 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
• 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
• 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
• jev-agent-skill-router - Typed, confidence-aware agent skill routing with TypeSafe Jev. · Python
• 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
• lev - Jolt implementation of Laya non-autoregressive System 1 decision engine · Clojure
• omo-jev-plugin - Jev-powered decision support for OmO and senpi agents · TypeScript
• 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
• 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
• 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
• jevvy - Jev-powered plugins for coding agents · TypeScript
• 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
• jev-usecases - Production TypeSafe Jev (System One) use-case harnesses with confidence-gated decision logic · 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
• 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
• 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
• 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
• 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
• jev-me - jev-me is grill-me with jev
• 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
• 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-apply - Memory-backed job-application skill: Jev selects, an LLM writes only new text, Playwright fills. Greenhouse + Ashby. · JavaScript
• 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
• 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
• jev-ai-sdk-form-router - Route form submissions to the right people with Jev and AI SDK. · 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
• jev-mobile - Fast structured Android control loops with TypeSafe Jev and Mobile MCP · Python
• 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
• 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
• JevGPT - JevGPT: Thinking Fast and Slow in Autonomous Research · 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
• 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
• 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
• 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
• 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
• jev-mobile - One TypeSafe Jev decision per step over the A11Y tree, executed via ADB. No screenshots and ultra fast! · Python
• 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
• 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
• 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
• 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
• 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
• 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
• 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
• typesafe-computer-use-windows - Windows port of typesafe-computer-use with Jev decisions, local OCR/UIA, and MCP host integration · Python
• jevcraft - Jev-powered Minecraft bot · JavaScript
• 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
• 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-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
• ha-gutcheck - Home Assistant integration that makes small judgment calls about your install · Python
• skill-router-mod - The skill-router mod: Jev picks and loads the skills each prompt needs. · 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-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
• 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
• 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
• 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](https://github.com/clownware