84 projects · updated 2 November 2026
Decision models in developer tooling
Code review gates, CI checks, agent harnesses and editor plugins. The densest cluster in the ecosystem, because a coding agent makes hundreds of small decisions per session and each one costs something.
72 of these 84 call the hosted API rather than running open weights.
jevgrep3.1k ★dzhngFind code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.skills2.9k ★typesafe-aiAgent skills for building with TypeSafe's System One APIhermes-jev-skills1.3k ★kerpopuleJev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)jev-browser-use1.2k ★wy-coliney5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.momo-code1.1k ★momozi1996MOMO CODE — RSI *JEV*Pi --AI coding agent that evolves with youforeman804 ★thruwireAn agent supervisor and software factory foreman powered by decision modelshippo-memory790 ★kitfunsoStop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.distill774 ★samuelfajGet FAR MORE done with FAR FEWER tokens 🔥jev-seo750 ★AgriciDanielLive SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports.jev-review695 ★devagrawal09A staged code-review workflow and local dashboard built with TypeSafe Jev.jev-skill662 ★wuyoscarAn awesome collection of Jev use cases, workflows, and agent skills.jev-router650 ★gargpratyushRoute to the cheapest model in claude code for your task using jev-routerJev-cu631 ★Sac-Y把 Computer Use 的「下一步点哪里」交给 Jev（TypeSafe System One）：Jev 从界面文字候选中选元素、动作、完成度与风险，Codex Computer Use 负责读取界面与执行，本地策略门槛拦截敏感操作。只传文字，不传截图。mu571 ★qybaihemu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.JevHarness554 ★TianyuCodingsLLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.JevRouter467 ★BillionsBobbyA lightweight Jev-powered router for models, tools, and subagentsvexjoy-agent444 ★notqueVexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.perch358 ★lakeday-orgSemantic code and security scannertypesafe-mcp357 ★itsmostafaSystem One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Layasystem-one-connector357 ★itsmostafaSystem One MCP connector to evaluate anything fast and cheap. Give your AI agent direct access to models like: Jev, D1, CLM and Layakeel355 ★codejunkie99Local-first macOS coding workspace with local Laya and optional Jev decision selectionjev-gateway323 ★vinilanaAn easy way to use jev with your coding agent for tool calling reasoningAstra-Ares314 ★miuuyyAdaptive reasoning effort for GPT-6 during Codex tasks, powered by Jev to reduce token usage.skillbox277 ★kitzeSelf-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.jev-dsh-decision268 ★Devin-AXISJev 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。jev-review248 ★NiazMorshed2007Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.compact-adviser228 ★kunchenguid"Work appears completed or recorded. Run /compact to save tokens."aiwg227 ★jmaglyReusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and MCP tools for Claude Code, Codex, Copilot, Cursor and more, plus SDLC workflows, session memory, and Jev decision support that offloads bounded LLM decisions to save tokens.dsh-jev-plugin201 ★luobosibing2Native 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.Jevmind186 ★dealerdefiOne brain, nine hands. An agent's decisions pulled out of its prose and put in one place, as typed answers with a confidence, behijev-gui-delegate166 ★YUTA-fywooAI-assisted Windows and Chrome GUI delegation for Codex: task contracts, local execution, Jev semantic decisions, recovery and outcome verification.supercov159 ★supercorp-aiCoverage, security and code quality for coding agentsjev-semgrep150 ★uehajgrep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できるjev-guard144 ★leepokaiAuto 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.quicksilver142 ★UditAkhouriiClaude 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.skillranker137 ★DicklesworthstoneRust 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.jevmem136 ★Avinash-jetwanijevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session.Canny132 ★qkalStops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.skills126 ★fabricioctellesA collection of skills for AI agents (Kiro, Cursor, Windsurf, Claude Code, and others). Each skill is a reusable module that teaches the agent to perform complex tasks with context, structure, and best practices.agent-router120 ★nidhi-singh02CLI that picks Cursor, Claude Code, Codex, or OpenCode + model/effort for a task, then launches it. Powered by Jev and Herdrjev-shell-history119 ★mrnuggetFish-style zsh history autosuggestions ranked by Jev (TypeSafe)stanley-code119 ★devagrawal09Bounded TypeSafe Jev workflows for coding agents.jevcore104 ★PerryLinkTypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.Intent-Router92 ★angel291592Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Layajev-kit91 ★jonathanavis96Everything 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.claude-x-jev85 ★charlesdove977Fast, cheap, typed decisions for Claude Code. Jev (TypeSafe's decision model on OpenRouter) sorts, checks, scores, gates and verifies at 0.3s and a fraction of a cent per item. Claude keeps the reading, writing and judgment.semdecide83 ★sharzikiTyped semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.jevcache78 ★hyperspaceaiA decision cache for TypeSafe Jev-class models — memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary.pi-jev72 ★TheoOliveiraSemantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jevjeview66 ★andududuAn unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI.jev-mcp66 ★burnigtmMCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP clientjev-use65 ★shitianfangClaude 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 LLMjev-ui-test64 ★buer2233Jev 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）jgrep62 ★kyu1204grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev.grev61 ★aurorainfraThinking coreutilspi-advisor60 ★philipbrembeckFully customizable Advisor and Executor flow plugin for the Pi Coding Agentjev-code55 ★FrancoisChastelJev, 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.optim-jev51 ★Oqura-aiJev based decision tools for claude code and codexjevreel51 ★DeepAlephA zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent.jev-judge-mcp49 ★PyModelTyped 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.jevify47 ★altryneAn agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.jev-axi46 ★shiftynickAgent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shellask-jev-skill40 ★shantanugoelSkill for Hermes, and other agents, to ask typesafe's jevis-malicious39 ★luantakA codebase scanner that helps you not run malicous codejeff38 ★AlurithCatch code issues before they catch you.jev-skill-suggester34 ★win4r用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.pi-jev-auto-mode33 ★jomatsuJev (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.yoshi31 ★compozyContext-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozyjev-agent-skill-router31 ★GodsBoyTyped, confidence-aware agent skill routing with TypeSafe Jev.loki28 ★wundercorpThe agent that evolves with you 𖤍unified-brain27 ★DevLoops-aiSystem One Coding Agents: code-level answers at the same score as Claude Fable 5.1 on the same 74-point xz benchmark (69 / 74, 93.2 % each), at 1/20 of the cost and 3.5× faster. No Context Loss and Memory Limits on sessions since every answer starts from the same, updatable, SQLite index.jev-macos-loop25 ★jcpsimmonsOpen-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own OpenRouter, Vercel AI Gateway, or TypesafeAI token.jevwire25 ★BrainwiresJev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)typesafe-mcp23 ★PyModelevaluate is a stdio MCP server for TypeSafe Jev. Coding agents send observed state plus typed questions and get back probabilitiesBrighTO_Router22 ★thusinh1969BrighTO LLM Router: free open-source, ultra-fast Rust LLM gateway/router and LiteLLM/Bifrost alternative with OpenAI + Anthropic APIs, Claude CLI bridge for OpenAI-compatible models, Qwen3.8 dual protocol, model load balancing, fallback routing, team API keys, token budgets, SystemOne decisions for Ollaya/Laya, JEV/DJEV and Quyết.jev-code22 ★rhighsInteractive TypeScript coding CLI powered by Jev typed decisions and constrained AST generation.patdown16 ★tyler-dot-earthBlock, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, claude extension, and more. Built with Effect + TypeScript.parallelConstraintDecoding15 ★stephanjParallel Constraint Decoding using Java and Llama.cpp compared to Python 🔥jev-mode15 ★tiffygkClaude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One model. All materials pull directly from their canonical cookbooks and documentation.guardrails-md12 ★berget-aiopencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policydsh-jev12 ★zhangxaochenJev (System One decision model) plugin suite for DeepSeek Harness (dsh)openjev12 ★darwintechlabOpenJev: An Opencode plugin that replaces text-generation decisions with Jev (TypeSafe System One).hermes-jev-plugin11 ★ajensenwaudTypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluatejev-harness10 ★PromtEngineerA Pi agent harness built around TypeSafe's Jev (System One model): router, context picker, gate, verifier. Tested on Neon Postgres branches.
Other things people build
Open reimplementations 80
People rebuilding the category from open weights: one-pass scorers, constrained decoding over local models, and small models trained to return a calibrated distribution. The fastest-moving cluster here.
Agents 30
Tool selection, routing and step gating. An agent choosing its next action is the purest version of the problem this class of model exists for.
Language integrations 30
Libraries that make a typed decision feel native to a language: pattern matching on an answer in Elixir, a probabilistic if in Ruby, a typed method via BAML.
Browser 22
Extensions and automation that judge pages: what to hide, what to click, what is worth reading. Latency matters here in a way it does not on a server.
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.