English · 简体中文 · 日本語 · 한국어 · Español · Português (Brasil)
🌐 Explore the website · 📜 Changelog · 🧠 Jev-like models · ➕ Submit a project
Awesome Jev is an independent, community-maintained catalog of 896 open-source projects built with Jev, TypeSafe AI's System One model for typed decisions inside software. It is not affiliated with or endorsed by TypeSafe AI.
What makes this catalog useful?
Every entry identifies the concrete decision Jev makes and links to the strongest public evidence available—so you can evaluate real implementations, not just project claims.
- ✅ Official — 6
- 📦 SDKs & clients — 55
- 🧠 Jev-like models — 60
- 🧩 Frameworks & integrations — 75
- 🤖 Agent tooling — 220
- 🖥️ Browser & computer use — 73
- 🪟 Applications — 123
- 🎮 Games & simulations — 70
- 🧪 Demos & playgrounds — 62
- 📊 Benchmarks & research — 113
- 📚 Other lists — 39
This README is a dated snapshot of 896 unique public GitHub repositories. Stars were captured on 2026-09-18–24 for discovery, not ranking; verify current behavior, activity, and licensing upstream.
62 projects added on September 24, 2026
- SDKs & clients (2): go-jev, swift-jev
- Jev-like models (17): SemIf-OpenJev, CLM, JevK5, TypeLLM, solar-mini4-jev, laya-server, OpenJev-Vision, Valen, jev-forge, MoJev, OpenJev, sys1, stuntd, snap, tev1, blink, jevper
- Frameworks & integrations (8): learn-agent-architecture, milvus-model, system-one, jev-tree, laya-jev-GraphRAG, algal, jevsearch, jev-switch
- Agent tooling (10): supercov, jev-judge-mcp, agent-chaperone, jev-agent-design-with-topk-logits-choices, pi-advisor, claude-jev, lintus, liteagents, codex-jev-router, jev-retrieval
- Browser & computer use (3): reticle, jev-browser, jev-cua
- Applications (12): jev-chat-windows, AIStock, warrenduffer, james_library, JevIntent, jev-poly-crypto-demo, jev-suite, jev-guard, yanwai, wechat-jev-assistant, ad-radar, jevpdf
- Games & simulations (3): Jev_Star, jev-reflex-autonomy-lab, JevTown
- Demos & playgrounds (3): typesafe-playground, pix-golpe, jevbot
- Benchmarks & research (3): dejevu, jev-does-not-play-dice, jev-skillbench
- Other lists (1): awesome-jev (Amal-David)
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| TypeSafe agent skills | ★ 765 | — | 2026-09-19 | Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations. |
| System One adapter (Python) | ★ 171 | Python | 2026-09-19 | Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models. |
| TypeSafe JavaScript SDK | ★ 168 | TypeScript | 2026-09-19 | Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk. |
| TypeSafe Python SDK | ★ 128 | Python | 2026-09-19 | Official sync and async Python client. pip install typesafe-sdk. |
| TypeSafe Daggerverse | ★ 12 | Python | 2026-09-20 | Official collection of reusable Dagger modules for TypeSafe AI and System One workflows. |
| TypeSafe Overwatch | ★ 4 | Python | 2026-09-20 | Official tooling for observing and evaluating System One workflows. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| openai-scala-client | ★ 249 | Scala | 2026-09-23 | Scala client module for TypeSafe System One that submits Jev Noul, Choice, and Score questions and returns typed answers. |
| advocaat | ★ 85 | TypeScript | 2026-09-19 | A small, type-safe client for asking AI questions about your data, powered by TypeSafe Jev. |
| ruby_decision_model | ★ 49 | Ruby | 2026-09-22 | Ruby client for decision models such as Typesafe Jev |
| spring-ai-typesafe | ★ 31 | Java | 2026-09-23 | A Java SDK for the TypeSafe AI JEV API, & Spring AI TypeSafe integrations. |
| pijev | ★ 27 | Python | 2026-09-23 | Permutation Invariant Jev. |
| pi-typesafe | ★ 26 | TypeScript | 2026-09-21 | Pi extension with a batched Jev evaluation tool, terminal playground, and typed API for other extensions. |
| TypeSafe Swift SDK | ★ 24 | Swift | 2026-09-21 | SwiftPM client for the TypeSafe System One API with typed Noul, Choice, and Score questions. |
| jev (dannote) | ★ 17 | Elixir | 2026-09-19 | TypeSafe Jev for OTP: reply to Jev from a GenServer and pattern match on its answer. |
| go-jev | ★ 13 | Go | 2026-09-24 | Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions. |
| swift-jev | ★ 11 | Swift | 2026-09-24 | Swift client for TypeSafe Jev typed judgments instead of generated text. |
| typesafe-ai | ★ 10 | Rust | 2026-09-19 | Typed TypeSafe AI clients for Rust, with async and blocking backends and observable retries. |
| typesafe-sdk-go (Tangerg) | ★ 8 | Go | 2026-09-19 | Go SDK for the TypeSafe AI API — typed questions in, probability distributions out. |
| zod-jev | ★ 7 | TypeScript | 2026-09-19 | Zod validates the shape, Jev validates the meaning: semantic checks on request bodies become calibrated probabilities you threshold in code. |
| jev-dsl | ★ 6 | Haskell | 2026-09-19 | Agent-first Haskell DSL for TypeSafe's Jev judgment model: typed packets, inferred types, answers under the same labels. |
| scala-jev-sdk | ★ 6 | Scala | 2026-09-22 | Scala SDK for Jev. No effect system bundled. |
| super-jev | ★ 5 | Python | 2026-09-19 | A small, extensible decision-to-action harness for TypeSafe Jev. |
| typesafe-dotnet-sdk | ★ 5 | C# | 2026-09-19 | 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. |
| typesafe-sdk-swift (alterhq) | ★ 4 | Swift | 2026-09-19 | Dependency-free Swift 6 client for Jev Choice, Score, and Noul questions, with strict concurrency, retries, and offline transport tests. |
| typesafe-sdk (joshmn) | ★ 4 | Ruby | 2026-09-19 | Ruby client for typesafe.ai. |
| jev-go (Gaurav-Gosain) | ★ 3 | Go | 2026-09-19 | Go client for TypeSafe's System One API and its model Jev: typed judgments and calibrated probabilities instead of generated text. |
| typesafe-ai-rs | ★ 3 | Rust | 2026-09-19 | Independent async and blocking Rust SDK for the TypeSafe AI System One API. |
| typesafe-sdk-swift | ★ 3 | Swift | 2026-09-19 | Swift SDK for TypeSafe AI. |
| zio-typesafe-ai | ★ 3 | Scala | 2026-09-19 | Scala 3 / ZIO client for the System One API: typed end-to-end, several questions per round-trip via NamedTuple. |
| jod | ★ 3 | TypeScript | 2026-09-19 | Semantic schemas over TypeSafe's Jev — validate the state locally, then project typed answers. |
| typesafe_sdk | ★ 3 | Elixir | 2026-09-19 | 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. |
| jev-java | ★ 3 | Java | 2026-09-19 | Idiomatic Java SDK for TypeSafe AI Jev System One decision engine. |
| typesafe-ai-go | ★ 3 | Go | 2026-09-21 | Community Go client for the TypeSafe System One API with typed question builders, retries, examples, and jev-latest as the default model. |
| typesafe-sdk-rust | ★ 2 | Rust | 2026-09-19 | Rust SDK for the TypeSafe AI API. |
| typesafe-go (cole-gillespie) | ★ 2 | Go | 2026-09-19 | Unofficial go SDK for typesafe AI, with typed answers, retries, and context support. |
| jevgo | ★ 2 | Go | 2026-09-19 | Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation. |
| TypeSafeAI.Net | ★ 2 | C# | 2026-09-19 | .NET SDK for the TypeSafe AI platform. |
| typesafe-sdk-java | ★ 2 | Java | 2026-09-19 | Community Java client for the TypeSafe System One API (unofficial). |
| jevclient | ★ 1 | Python | 2026-09-19 | Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse. |
| jev | ★ 1 | Go | 2026-09-19 | Unofficial Go client for TypeSafe's System One API and its model, Jev. |
| typesafe-sdk (binnash) | ★ 1 | PHP | 2026-09-19 | PHP & Laravel SDK for TypeSafe AI's JEV Model series. |
| typesafeai-go | ★ 1 | Go | 2026-09-19 | Go SDK for TypeSafe AI API https://docs.typesafe.ai/api. |
| jev-go (guillemus) | ★ 1 | Go | 2026-09-19 | Unofficial Go SDK for TypeSafe AI's Jev API. |
| typesafe-client | ★ 1 | Rust | 2026-09-19 | Unofficial typed async Rust client for the TypeSafe System One API. |
| typesafe_sdk_ex | ★ 1 | Elixir | 2026-09-19 | Typesafe AI SDK in Elixir using Req. |
| decido | ★ 1 | Python | 2026-09-19 | Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright. |
| typesafe-go (zhirschtritt) | ★ 1 | Go | 2026-09-19 | Idiomatic Go SDK for the TypeSafe AI API. |
| typesafe-sdk-php (Butochnikov) | ★ 1 | PHP | 2026-09-22 | Unofficial PHP client for TypeSafe System One with typed Choice, Score, and Noul requests and synchronous or concurrent transport. |
| jev-sdk-java | ★ 1 | Java | 2026-09-22 | Type-safe Java 21 client for the TypeSafe AI Jev (System One) decision API |
| s1-rs | ★ 0 | Rust | 2026-09-19 | Typed System One layer for Rust (Choice/Score/Noul). |
| typesafe-rs | ★ 0 | Rust | 2026-09-19 | Latency-first Rust SDK for TypeSafe System One. |
| typesafe_ai (hfiguera) | ★ 0 | Elixir | 2026-09-19 | A supervised Mint client for the TypeSafe AI System One API. |
| kunobi-jev | ★ 0 | Rust | 2026-09-19 | Rust client for the TypeSafe System One API (Jev). |
| jev-cli (lhotwll217) | ★ 0 | TypeScript | 2026-09-20 | JSON-in, typed-decisions-out CLI for the TypeSafe System One API. |
| typesafe | ★ 0 | Elixir | 2026-09-19 | An idiomatic Elixir client for the TypeSafe AI API. |
| typesafe.zig | ★ 0 | Zig | 2026-09-19 | An idiomatic Zig client for the TypeSafe AI API. |
| tinyjevclient | ★ 0 | Rust | 2026-09-19 | An integration with jev by typesafe.ai in Rust. |
| typesafe_ai (typesend) | ★ 0 | Elixir | 2026-09-19 | Unofficial Elixir SDK for the TypeSafe AI API. |
| typesafe-sdk-go | ★ 0 | Go | 2026-09-19 | Unofficial Go SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI. |
| typesafe-sdk-php | ★ 0 | PHP | 2026-09-19 | Unofficial PHP SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI. |
| typesafe-go | ★ 0 | Go | 2026-09-22 | Unofficial Go SDK for TypeSafe AI's System One API (Jev). |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| laya | ★ 17,709 | Python | 2026-09-23 | Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request. |
| SemIf-OpenJev | ★ 4,121 | Python | 2026-09-24 | Open-model semantic-if engine for local Jev-style decisions. |
| SemIf | ★ 2,023 | Python | 2026-09-19 | Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe. |
| kev | ★ 1,558 | Python | 2026-09-21 | Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference. |
| LocalJev | ★ 662 | TypeScript | 2026-09-21 | Local Jev-compatible System One API that converts typed questions into DiffusionGemma classification prompts and probabilities. |
| von | ★ 507 | Python | 2026-09-23 | The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev. |
| Simple Jev | ★ 429 | Python | 2026-09-21 | Open-model Jev-style server that reads next-token logits to return typed choices, rubric scores, and truth judgments. |
| deepopen | ★ 383 | Python | 2026-09-23 | 非自回归System 1决策引擎，专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine. |
| laya | ★ 302 | TypeScript | 2026-09-23 | Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime. |
| openjev-sglang | ★ 245 | Python | 2026-09-21 | Jev-compatible API server built on open models and SGLang, with prefill-only inference and typed decision endpoints. |
| agent-jev | ★ 235 | Python | 2026-09-23 | AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding. |
| Open-Jev | ★ 231 | Python | 2026-09-23 | Open probability decisions with Qwen3.5-2B, Qwen3.5-9B and Qwen3.8-27B. |
| rizzo-flow | ★ 230 | Python | 2026-09-22 | The open, local take on Jev: typed decisions from an LLM, without generating a single token |
| jeff | ★ 189 | Python | 2026-09-21 | Self-hosted Jev-compatible System One server backed by GLiNER-family models, with batching and typed question support. |
| djev-spark | ★ 168 | HTML | 2026-09-22 | DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe No repository-level license file was found during review. |
| openjev | ★ 142 | Python | 2026-09-19 | Open, Jev-compatible System One decision server on DiffusionGemma. |
| AnyJev | ★ 142 | Python | 2026-09-23 | Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating). |
| laya-ultrafast | ★ 116 | Python | 2026-09-23 | Same as jev-ultrafast but using Laya. |
| LLM2Jev | ★ 114 | Python | 2026-09-21 | Adapter that turns local language models into Jev-style Choice, Score, and Noul decision engines with typed probabilities. |
| CLM | ★ 103 | Python | 2026-09-24 | Contrastive language model for one-pass typed decisions and option probabilities. |
| OpenJev | ★ 102 | TypeScript | 2026-09-23 | OpenSource Jev. |
| jimothy | ★ 68 | TypeScript | 2026-09-23 | Train small, insanely fast local classifiers from Jev-compatible examples. Run locally in your browser or Node.js. |
| JevK5 | ★ 51 | Python | 2026-09-24 | Open-weight Jev alternative that returns typed decisions with probabilities in one forward pass. |
| OpenDecision | ★ 45 | Python | 2026-09-21 | Open semantic decision engine implementing Choice, Noul, and Score primitives with a TypeSafe comparison harness. |
| open-jev-typed-decision-engine | ★ 40 | Python | 2026-09-23 | Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min. |
| TypeLLM | ★ 40 | Python | 2026-09-24 | Type-safe language-model generation and structured decisions. |
| solar-mini4-jev | ★ 39 | Python | 2026-09-24 | Solar Mini–based local model for Jev-style typed decisions. |
| laya-server | ★ 38 | TypeScript | 2026-09-24 | Self-hosted API and web interface for Laya decision models with a Jev-compatible API shape. |
| OpenJev-Vision | ★ 36 | Python | 2026-09-24 | Open visual decision model that encodes an image once and answers multiple structured questions. |
| djev | ★ 35 | Python | 2026-09-23 | Jev-style structured decisions on DiffusionGemma: the example server from vLLM PR 57250. |
| Valen | ★ 33 | Python | 2026-09-24 | Training stack for a multimodal Jev-like System One model with vision. |
| jevify | ★ 32 | Python | 2026-09-23 | Supersimple way to serve LLMs as a Jev-like endpoint. |
| jev-forge | ★ 32 | Python | 2026-09-24 | Training and inference stack for calibrated Jev-style choice models with dynamic candidate sets. |
| OpenSourceJev | ★ 31 | Python | 2026-09-23 | Turning an LLM model into a Jev like System. |
| typed-decision-bert | ★ 30 | Python | 2026-09-23 | Unofficial PoC: a BERT-style encoder decision engine behind a typed-decision (noul / choice / score) HTTP API. Not affiliated with TypeSafe. |
| open-jev | ★ 30 | TypeScript | 2026-09-23 | open-jev is a browser-focused TypeScript library for typed decisions: one piece of text (the state) plus any number of typed questions go in, and one forward pass returns a calibrated probability distribution per question. Nothing is generated, so an answer is always one of the options you provided. |
| OpenThai-SystemOne | ★ 29 | Python | 2026-09-21 | Open Thai-English System One model with Choice inference, calibration, evaluation scripts, and a Jev comparison suite. |
| MoJev | ★ 28 | Python | 2026-09-24 | Open model for typed, calibrated decisions in one forward pass. |
| OpenJev | ★ 25 | HTML | 2026-09-24 | Open probabilistic Choice, Noul, and Score API powered by constrained open-model log probabilities. |
| sys1 | ★ 22 | Rust | 2026-09-24 | Rust System One–compatible API for open decision models such as Laya. |
| arbiter | ★ 21 | HTML | 2026-09-23 | Serve typed-decision (System 1) models — Laya or your own — on NVIDIA GPUs or Apple Silicon, with a Jev-compatible API and coding-agent integrations. |
| stuntd | ★ 19 | Python | 2026-09-24 | Local Jev-compatible proxy that learns an application’s typed decisions and serves them with a Laya head. |
| notjev | ★ 18 | JavaScript | 2026-09-23 | Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint. |
| open-jev (JoshuaSP) | ★ 17 | Python | 2026-09-19 | Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results. |
| JEV-CPU | ★ 17 | Python | 2026-09-23 | Run SemIf (Jev-style semantic-if decisions) on a CPU — no GPU. Reads typed option probabilities straight from an open model in one forward pass, plus a web UI. |
| snap | ★ 17 | Rust | 2026-09-24 | Local Jev-compatible typed decisions from unstructured state in one forward pass. |
| tev1 | ★ 15 | Python | 2026-09-24 | Open-weight Jev-inspired decision model fine-tuned from Qwen3.5 4B. |
| laya-mps | ★ 13 | Python | 2026-09-23 | Run Jev-style typed decisions locally on your Mac with low RAM usage and fast responses. |
| blink | ★ 13 | C | 2026-09-24 | High-performance System One model with an embeddable C runtime and WebAssembly support. |
| Nemotron_Jev | ★ 12 | Python | 2026-09-23 | Ask typed questions about text or JSON and inspect model-derived probability distributions in a browser. One container runs the model, the original Decision Lab explorer, and a TypeSafe-shaped API. |
| open-jev | ★ 11 | Python | 2026-09-23 | an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch. |
| snapjudge | ★ 11 | Python | 2026-09-23 | Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text generation. TypeSafe-compatible HTTP API, runs on MLX. |
| jevper | ★ 11 | Python | 2026-09-24 | Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence. |
| open-spark-jev | ★ 5 | Python | 2026-09-21 | Open local System One implementation for NVIDIA DGX Spark, with a Qwen3-based model, Jev-compatible API, architecture notes, and evaluation tooling. |
| poorjev | ★ 5 | Python | 2026-09-22 | Local Jev-like System One decision layer that returns typed choices and calibrated confidence without a hosted API. |
| OpenJev (xingwudao) | ★ 5 | Python | 2026-09-22 | OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI. No repository-level license file was found during review. |
| edgejev | ★ 5 | Python | 2026-09-22 | Local Jev-like typed-decision runtime using ONNX and quantized models for offline CPU inference. |
| jev-local | ★ 3 | Python | 2026-09-22 | Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist No repository-level license file was found during review. |
| TinyJev | ★ 3 | Python | 2026-09-23 | Local 596M typed-decision model with its own weights, Choice, Score, and Noul support, and a Jev-compatible System One endpoint. |
| Diffusion Jev | ★ 1 | Python | 2026-09-23 | Independent DiffusionGemma and SGLang typed-decision server for text and images, with a drawing playground and public evaluation artifacts. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| litellm | ★ 59,363 | Python | 2026-09-22 | AI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing. |
| oh-my-pi | ★ 32,394 | TypeScript | 2026-09-22 | Coding agent with a TypeSafe judgment provider that uses Jev for typed checks, routing, and workflow decisions. |
| json-render | ★ 17,982 | TypeScript | 2026-09-22 | Generative UI framework with an experimental evaluator that lets Jev choose among application-supplied composition criteria. |
| eve | ★ 5,274 | TypeScript | 2026-09-19 | Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path. |
| ai | ★ 1,183 | PHP | 2026-09-22 | Laravel AI SDK with a TypeSafe provider for Jev Choice, Score, and Noul classification requests. |
| learn-agent-architecture | ★ 980 | Python | 2026-09-24 | Agent architecture examples that use Jev for fast typed control decisions. |
| ai-cli | ★ 807 | TypeScript | 2026-09-19 | Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command. |
| hippo-memory | ★ 752 | TypeScript | 2026-09-22 | Agent memory library with an optional Jev reranker that judges which retrieved memories are relevant. |
| ai-sdk-provider | ★ 686 | TypeScript | 2026-09-23 | The OpenRouter provider for the Vercel AI SDK contains support for hundreds of models through the OpenRouter chat and completion APIs. |
| aiavatarkit | ★ 678 | Python | 2026-09-22 | Conversational-avatar framework with a Jev gate that judges whether a speaker has finished a turn. |
| smithers | ★ 417 | TypeScript | 2026-09-19 | Agentic TypeScript workflow framework with a Jev session checker wired into its workflows. |
| pg-jev | ★ 224 | Python | 2026-09-19 | Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev. |
| skillbox | ★ 200 | TypeScript | 2026-09-19 | Self-hosted, versioned skills library for AI agents with optional Jev recommendations through TypeSafe or an AI gateway. |
| ai-backends | ★ 146 | HTML | 2026-09-23 | API server runtime for common AI use cases — supports multiple models and providers. Run locally with Ollama or LM Studio, or in the cloud via OpenRouter, OpenAI, Anthropic, or Google. |
| NeuroLink | ★ 134 | TypeScript | 2026-09-21 | Unified AI SDK whose TypeSafe decide API supplies typed judgments for model routing, compaction, tools, and retrieval planning. |
| pg_typesafe | ★ 79 | C | 2026-09-19 | Pre-alpha PostgreSQL extension for TypeSafe AI (Jev) categorical classification. |
| jev-shell-history | ★ 67 | TypeScript | 2026-09-19 | Fish-style zsh history autosuggestions ranked by Jev (TypeSafe). |
| milvus-model | ★ 60 | Python | 2026-09-24 | Milvus model library with a TypeSafe Jev reranker provider for semantic search. |
| beam_weaver | ★ 56 | Elixir | 2026-09-23 | BeamWeaver exposes Jev Choice, Score, and Noul evaluations as provider-neutral decision-model calls in Elixir workflows. |
| system-one | ★ 47 | TypeScript | 2026-09-24 | Provider-neutral System One runtime for TypeScript and the Pi coding agent. |
| neo4jev | ★ 38 | Jupyter Notebook | 2026-09-19 | Typesafe.ai System One Model Jev navigating a Neo4j graph by using a classifier over neighbouring relationships. |
| tocket | ★ 38 | TypeScript | 2026-09-23 | Jev chooses the next step from bounded options and records that choice in Tocket’s shared project notebook. |
| jev-tree | ★ 36 | Python | 2026-09-24 | Probability-tree and graph runtime for verifiable multi-step Jev decisions. |
| Jevbridge | ★ 35 | TypeScript | 2026-09-21 | ACP and MCP adapter that exposes Jev typed decisions and computer-use actions to Codex, Claude, OpenCode, and other agents. |
| Astra | ★ 32 | Rust | 2026-09-23 | Astra uses native Jev judgments to inspect agent context and choose evidence-backed runtime actions. |
| Loki | ★ 26 | Python | 2026-09-19 | Self-improving agent harness with an optional TypeSafe Jev companion for typed Choice, Score, and Noul judgments. |
| HA-Jev | ★ 24 | Python | 2026-09-19 | Home Assistant integration for TypeSafe Jev. Ask a question about your house and get a probability, a choice or a score as an entity. |
| ST-jeved | ★ 22 | JavaScript | 2026-09-22 | SillyTavern extension where Jev scores replies against configured narration rules before adding guidance. |
| laya-jev-GraphRAG | ★ 22 | Python | 2026-09-24 | Agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models. |
| duckdb-jev (colliber) | ★ 20 | C++ | 2026-09-22 | DuckDB extension: typed Jev answers as real SQL types |
| ruby_llm-typesafe | ★ 15 | Ruby | 2026-09-19 | TypeSafe structured-output provider for RubyLLM 2. |
| invalidate | ★ 15 | Python | 2026-09-22 | The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on TypeSafe Jev. |
| jev-reranker | ★ 15 | Python | 2026-09-23 | Jev-powered relevance filtering and reranking for RAG in Python. |
| hunch | ★ 14 | Ruby | 2026-09-23 | Probabilistic control flow for Ruby and Rails - powered by TypeSafe's Jev. |
| jev-edge | ★ 13 | Lua | 2026-09-23 | Typed-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev. Fail-open, cached, hot-reloadable. |
| discern | ★ 12 | TypeScript | 2026-09-23 | Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev. |
| Turn | ★ 11 | Rust | 2026-09-23 | Turn programs call Jev for Choice, Score, and Noul decisions and route execution from the typed answers. |
| JevLint | ★ 11 | TypeScript | 2026-09-23 | Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin. |
| jevalyn | ★ 10 | Ruby | 2026-09-21 | Rails-native Jev wrapper that turns typed, calibrated decisions into application control flow. |
| jevframe | ★ 10 | Python | 2026-09-22 | Semantic AI for pandas and Polars: classify text, analyze sentiment, and score DataFrame rows with natural-language questions and full probabilities using TypeSafe Jev. |
| jev-foundation-models | ★ 10 | Swift | 2026-09-22 | A lightweight, native Swift 6 bridge integrating TypeSafe AI's Jev System One decision model into Apple's Foundation Models framework. |
| algal | ★ 10 | TypeScript | 2026-09-24 | Language and runtime for agent-graph evolution with Jev-backed decisions. |
| J++ | ★ 8 | Python | 2026-09-21 | Experimental language and Rust runtime where semantic questions and decision methods are composable program values, with Jev as a supported provider. |
| jev-feels | ★ 8 | Ruby | 2026-09-22 | Semantic decisions as ordinary Ruby — feels?, decide, score, Rails validations and pattern matching powered by Jev |
| jevql | ★ 7 | Go | 2026-09-20 | Adds jev(), jev_prob, jev_choice, and jev_score to vanilla PostgreSQL queries through a psql-shaped CLI and Go, TypeScript, and Python SDKs. |
| a0-typesafe-ai | ★ 5 | Python | 2026-09-19 | TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards. |
| typesafe-jev-workflow | ★ 5 | Python | 2026-09-19 | Async LangGraph workflow that gets a typed Jev Choice (invoice or general) and routes each inbound email to the matching handler. |
| jevsearch | ★ 5 | TypeScript | 2026-09-24 | Site search that recalls candidates locally, then uses Jev to score and rerank them. |
| typesafe-on-neon | ★ 4 | TypeScript | 2026-09-19 | Neon Function proxy for the Neon AI Gateway with TypeSafe Jev routing. |
| mysql-ailike | ★ 4 | C++ | 2026-09-22 | Natural-language row filtering for MySQL, powered by TypeSafe Jev. |
| llama-index-jev | ★ 3 | Python | 2026-09-19 | LlamaIndex reranker + router powered by TypeSafe Jev — typed scores/choices, cheaper than LLM-as-judge. |
| jevals | ★ 3 | Python | 2026-09-21 | Framework-agnostic agent evals and guardrails that batch a trace's checks into one request to Jev, Kev, Laya, or a chat-model fallback. |
| duckdb-jev (prasanthj) | ★ 3 | C++ | 2026-09-22 | High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from SQL. |
| vgi-typesafe | ★ 3 | Python | 2026-09-22 | A VGI worker exposing TypeSafe System One questions (choice, noul, score) to DuckDB/SQL as LATERAL-joinable table functions |
| typesafe-ui | ★ 2 | TypeScript | 2026-09-19 | Shadcn-style reusable components and blocks for using TypeSafe AI. |
| laravel-typesafe-jev | ★ 2 | PHP | 2026-09-19 | Unofficial Laravel integration for TypeSafe Jev AI with typed responses, async requests, scoped dependency injection, and testing fakes. |
| new-api-plugin-typesafe | ★ 2 | JavaScript | 2026-09-19 | TypeSafe AI System One task plugin for New API with a native /v1/systemone endpoint, routing, and token billing. |
| typesafe-ai-rails | ★ 2 | Ruby | 2026-09-19 | Community Rails integration on the typesafe-sdk gem: configuration, persisted usage and cost telemetry, and opt-in confidence policies. |
| jev-ui | ★ 2 | TypeScript | 2026-09-22 | 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. No repository-level license file was found during review. |
| tripwire | ★ 2 | TypeScript | 2026-09-22 | Judge every LLM response before the user sees it. AI SDK middleware and OpenAI-compatible proxy. |
| jev-layer | ★ 2 | JavaScript | 2026-09-22 | Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations. |
| pydantic-jev-examples | ★ 1 | Python | 2026-09-19 | Pydantic AI capabilities made stronger with Jev: small runnable demos, one file each. |
| judging-with-typesafe | ★ 1 | Python | 2026-09-19 | Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev). |
| typesafe-assist | ★ 1 | Python | 2026-09-19 | Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model. |
| hunch | ★ 1 | Python | 2026-09-23 | Python library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and DataFrame workflows. |
| hunch-js | ★ 1 | TypeScript | 2026-09-23 | TypeScript library that maps Jev Choice, Score, and Noul questions onto classification, ranking, extraction, verification, and array workflows. |
| chat2jev | ★ 1 | TypeScript | 2026-09-23 | Workbench that converts Chat Completions requests into editable Jev State and Questions, compares text generation with typed judgments, and exposes reusable proxy routes. |
| jev-connector | ★ 0 | JavaScript | 2026-09-20 | Connector for integrating TypeSafe Jev decisions into application workflows. |
| n8n-nodes-typesafe-ai | ★ 0 | TypeScript | 2026-09-19 | N8n community node for the TypeSafe AI System One API — typed yes/no, choice and score questions with calibrated probabilities. |
| hiep-paseo-plugin | ★ 0 | TypeScript | 2026-09-20 | Local Paseo plugin that exposes Jev evaluations through MCP. |
| Jev4Mellea | ★ 0 | Python | 2026-09-19 | Jev adapter to Mellea. |
| ground-zero | ★ 0 | Python | 2026-09-20 | Evaluation framework for detecting AI hallucinations and instruction-following failures with Jev. |
| pytest-jev | ★ 0 | Python | 2026-09-22 | Semantic assertions for pytest: test what your LLM app's output means, judged by TypeSafe's Jev. |
| openclaw-typesafe-ai | ★ 0 | TypeScript | 2026-09-22 | Optional typed TypeSafe AI Jev decisions for OpenClaw, with SecretRef credentials and strict API validation. |
| jev-switch | ★ 0 | Rust | 2026-09-24 | Local multi-upstream router for the Jev protocol with a Rust backend and React interface. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| claude-code-templates | ★ 30,897 | Python | 2026-09-22 | Claude Code configuration toolkit shipping Jev-based model routing, skill suggestion, and tool guardrail modules. |
| openwork | ★ 23,654 | TypeScript | 2026-09-19 | Open-source Claude Cowork alternative whose eval testkit can use Jev as a typed verification judge for agent-produced work. |
| fast-jev-compaction | ★ 4,427 | TypeScript | 2026-09-19 | Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim. |
| vexjoy-agent | ★ 423 | Python | 2026-09-23 | VexJoy 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. |
| foreman | ★ 406 | Python | 2026-09-19 | Software Factory Foreman: an agent supervisor that uses Jev decisions to keep coding agents on task. |
| jev-review (devagrawal09) | ★ 366 | TypeScript | 2026-09-19 | A staged code-review workflow and local dashboard built with TypeSafe Jev. |
| hermes-jev-skills | ★ 345 | Python | 2026-09-21 | Hermes plugin and skill suite using Jev for model routing, skill selection, memory filtering, compaction, and GUI actions. |
| jev-search | ★ 244 | TypeScript | 2026-09-19 | Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API. |
| decapod | ★ 233 | Rust | 2026-09-23 | During assurance evaluation, Jev estimates how likely a proposed agent trajectory is to satisfy its bounded objective. |
| Albatross | ★ 232 | Rust | 2026-09-23 | Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud, your keys, one TUI. No black box. |
| jev-router (gargpratyush) | ★ 214 | JavaScript | 2026-09-19 | Route to the cheapest model in claude code for your task using jev-router. |
| jev-gateway | ★ 181 | TypeScript | 2026-09-23 | An easy way to use jev with your coding agent for tool calling reasoning. |
| Astra-Ares | ★ 178 | JavaScript | 2026-09-23 | Adaptive reasoning effort for GPT-6 Astra during Codex tasks, powered by Jev to reduce token usage. |
| compact-adviser | ★ 173 | TypeScript | 2026-09-22 | Agent plugin that uses Jev to judge when a coding session should compact its context. |
| jev-review (NiazMorshed2007) | ★ 171 | TypeScript | 2026-09-19 | Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev. |
| abide | ★ 169 | TypeScript | 2026-09-19 | Supervises coding-agent edits and uses Jev to flag violations of project rules. |
| glowbom-oss | ★ 163 | Go | 2026-09-23 | Coding agents can ask Jev to judge small workflow decisions, such as whether build results look healthy. |
| Anna-Agent | ★ 149 | TypeScript | 2026-09-23 | Anna uses Jev as a fast judgment layer for bounded enterprise-agent recommendations and abstentions. |
| jev-pruner | ★ 130 | TypeScript | 2026-09-21 | Claude Code and Codex hooks that ask Jev which parts of long shell output remain relevant before sending them into model context. |
| jev-semgrep | ★ 125 | JavaScript | 2026-09-22 | grep 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-mcp (jkudish) | ★ 121 | TypeScript | 2026-09-19 | Proof of concept MCP for Typesafe's new Jev AI model. |
| building-with-jev-skill | ★ 118 | — | 2026-09-19 | A skill for writing and improving programs that call Jev, TypeSafe's System One model. |
| typesafe-mcp | ★ 117 | Go | 2026-09-19 | Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex. |
| stanley-code | ★ 113 | TypeScript | 2026-09-23 | Bounded TypeSafe Jev workflows for coding agents. |
| supercov | ★ 109 | Rust | 2026-09-24 | Code-quality and coverage reviewer that uses Jev to judge coding-agent changes. |
| pi-warden | ★ 96 | TypeScript | 2026-09-19 | 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. |
| pi-jev (y0usaf) | ★ 92 | TypeScript | 2026-09-19 | TypeSafe Jev as a decision layer for the Pi coding agent: a measured tool-call gate plus jev_ask for typed, calibrated answers. |
| JevRouter | ★ 90 | TypeScript | 2026-09-19 | A lightweight Jev-powered router for models, tools, and subagents. |
| skills | ★ 90 | Python | 2026-09-23 | Four agent skills use Jev Score and Noul judgments to assess subjective criteria with calibrated probabilities. |
| jev-codex-router | ★ 75 | Python | 2026-09-19 | Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn. |
| jev-code | ★ 75 | TypeScript | 2026-09-19 | Bounded TypeSafe Jev workflows for coding agents. |
| captaincore | ★ 71 | Go | 2026-09-23 | Jev triages malware-scan findings and supplies typed Noul, Choice, and Score decisions for WordPress maintenance. |
| grok-bot-jev | ★ 70 | Python | 2026-09-21 | Grok Bot integration where Jev applies usage gates and routes requests before the generative model runs. |
| skillranker | ★ 69 | Rust | 2026-09-19 | 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. |
| total-agent-memory | ★ 69 | Python | 2026-09-23 | Jev checks retrieved memories for contradictions before an agent uses them in an answer. |
| save-token-jev-clean | ★ 67 | TypeScript | 2026-09-23 | Portable, Jev-guided context compaction for coding agents. |
| jmeter-ai | ★ 60 | Java | 2026-09-23 | Jev classifies JMeter agent intent and selects a focused tool pack, with a full-tool fallback when routing is uncertain. |
| weflow-cli | ★ 59 | Python | 2026-09-23 | When enabled, Jev classifies article topics and relevance for WeChat daily digests. |
| agent-router | ★ 58 | TypeScript | 2026-09-21 | CLI that uses Jev task classification to choose and launch Cursor, Claude Code, Codex, or OpenCode with an appropriate model and effort level. |
| oxlint-plugin-jev | ★ 58 | TypeScript | 2026-09-23 | > This package is experimental. Use at your own risk. |
| jegrep | ★ 57 | Rust | 2026-09-21 | Semantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query. |
| jev-lint | ★ 55 | TypeScript | 2026-09-21 | Text linter that uses Jev Score judgments to evaluate strings embedded in source code against configurable writing rules. |
| Canny | ★ 52 | TypeScript | 2026-09-23 | Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies. |
| jev-recruiter | ★ 46 | Python | 2026-09-23 | A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief. |
| jev-rules | ★ 45 | JavaScript | 2026-09-21 | Claude Code plugin where Jev decides which project rules apply to each prompt and edited file. |
| jev-sift | ★ 45 | JavaScript | 2026-09-22 | Agent plugin and MCP tool where Jev classifies batches of text so agents can read only the relevant items. No repository-level license file was found during review. |
| duet-agent | ★ 43 | TypeScript | 2026-09-19 | Full-stack agent harness with memories, long-running tasks, multi-agent relay, and a Jev-backed model-routing table. |
| hono-jev-router | ★ 39 | TypeScript | 2026-09-19 | Route HTTP requests by meaning. A semantic router for Hono powered by Jev. |
| JevRev | ★ 39 | TypeScript | 2026-09-23 | An LLM + Jev workflow. Boost your vertebrate brain with a spine inside. |
| skilled-agent-harness_spec-driven-loops | ★ 36 | TypeScript | 2026-09-23 | The cli-jev transport routes typed-judgment requests from the skill harness to the Jev CLI and MCP interfaces. |
| jev-dsh-decision | ★ 35 | JavaScript | 2026-09-21 | Decision plugin for DeepSeek Harness and iPolloWork that lets OpenCode, Codex, and other agents use Jev to select tools, skills, and task owners and evaluate outputs. |
| ask-jev-skill | ★ 34 | Python | 2026-09-19 | Skill for Hermes, and other agents, to ask typesafe's jev. |
| Jev-Mem | ★ 34 | Python | 2026-09-23 | Jev-Mem: System-One Controlled Agentic Memory. |
| obsidian-llm-hub | ★ 34 | TypeScript | 2026-09-23 | Obsidian plugin for AI chat, workflow automation, and semantic search — supports Gemini, OpenAI, OpenRouter, Grok, Ollama, and CLI backends. |
| jev-skill-suggester | ★ 32 | Python | 2026-09-23 | 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-skill-picker | ★ 29 | TypeScript | 2026-09-23 | Rank Pi Agent Skills for the current task with TypeSafe Jev. |
| jevgrep | ★ 28 | TypeScript | 2026-09-21 | Semantic code search CLI and MCP server: Jev scores authorized repository excerpts and returns exact file paths and line numbers to coding agents. |
| ai-news-aggregator | ★ 27 | Python | 2026-09-23 | Multi-agent AI news pipeline powered by GLM-5.3-Flash and Jev. |
| winnow | ★ 26 | Python | 2026-09-19 | A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context. |
| jev-judge-mcp | ★ 24 | Python | 2026-09-24 | MCP tools that expose Jev for verification, screening, classification, reranking, review, gating, and scoring. |
| snifftest | ★ 22 | TypeScript | 2026-09-19 | A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model. |
| jev-use | ★ 20 | JavaScript | 2026-09-23 | 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. |
| agent-chaperone | ★ 20 | TypeScript | 2026-09-24 | MCP proxy that uses Jev to screen agent tool calls and tool results. |
| jev-agent-design-with-topk-logits-choices | ★ 20 | Python | 2026-09-24 | Jev-native agent design with top-k proposals, fallback decisions, memory, and replanning. |
| pi-advisor | ★ 20 | TypeScript | 2026-09-24 | Customizable Advisor and Executor workflow for Pi with Jev decision support. |
| jev-mcp (burnigtm) | ★ 19 | TypeScript | 2026-09-19 | MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client. |
| ErisLint | ★ 19 | Rust | 2026-09-23 | Rust linter powered by configurable Jev rules, with a VS Code extension. |
| Multi-Agent | ★ 19 | TypeScript | 2026-09-23 | Multi-agent orchestration engine with warm sessions, a durable mailbox, and per-task token accounting. |
| yoshi | ★ 18 | TypeScript | 2026-09-19 | Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into Compozy. |
| pi-jev (TheoOliveira) | ★ 18 | TypeScript | 2026-09-19 | Semantic tool routing and typed System One decisions for the Pi coding agent using TypeSafe Jev. |
| cnki-skills | ★ 18 | Python | 2026-09-23 | The optional cnki-jev package uses Jev for first-pass literature screening and escalates complex cases for model or human review. |
| pi-jev-auto-mode | ★ 17 | TypeScript | 2026-09-19 | 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. |
| jev-axi | ★ 17 | TypeScript | 2026-09-19 | Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell. |
| oh-my-harness | ★ 17 | TypeScript | 2026-09-23 | Tame your AI coding agents with natural language. Generate enforced guardrails (CLAUDE.md, hooks, settings) from a single command. |
| zero-api-key-web-search | ★ 17 | Python | 2026-09-23 | Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification. |
| dsh-jev | ★ 16 | TypeScript | 2026-09-23 | Jev-powered decision layer for DeepSeek Harness. |
| a3m-router | ★ 16 | TypeScript | 2026-09-23 | ⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel ensemble merge. npm: adaptive-memory-multi-model-router. |
| jgrep | ★ 16 | TypeScript | 2026-09-23 | grep for what code does, not what it's called. Semantic code search powered by TypeSafe Jev. |
| jev-cli | ★ 16 | Rust | 2026-09-23 | Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents. |
| JevLoop | ★ 16 | TypeScript | 2026-09-23 | The agent loop where decisions don't cost a large language model call. Zero deps, runs offline, no API key needed. |
| deepreseach-learing | ★ 15 | Python | 2026-09-23 | Jev runs in shadow mode to append structured quality evaluations to generated deep-research reports. |
| jev-test-filter | ★ 15 | TypeScript | 2026-09-23 | Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understand. |
| jevvy | ★ 15 | TypeScript | 2026-09-23 | Jev-powered plugins for coding agents. |
| pi-review | ★ 15 | TypeScript | 2026-09-23 | Jev screens likely defects, arbitrates ambiguous findings, classifies scope, and supports cross-round review memory. |
| is-malicious | ★ 14 | TypeScript | 2026-09-19 | Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it. |
| pi-jev-router (philippdubach) | ★ 14 | TypeScript | 2026-09-21 | Pi model router that uses Jev task classification and a measured Pareto frontier over quality, cost, and latency to select an OpenRouter model. |
| patdown | ★ 14 | TypeScript | 2026-09-22 | Block, steer, and "fuzzy lint" with Jev to make agents follow your rules and conventions. CLI, github action, pi package, and more. Built with Effect. |
| MetaCog | ★ 14 | Python | 2026-09-23 | MetaCoginition powered by Reflex 4B. |
| Tiermem | ★ 13 | Python | 2026-09-23 | The Jev integration routes agent memory queries between compact Markdown notes and searchable raw history. |
| azdaja | ★ 13 | Python | 2026-09-23 | Azdaja exposes optional Jev semantic judgments inside a bounded local evaluation surface. |
| jevyoumean | ★ 13 | Go | 2026-09-23 | Semantic "Did you mean?" for any CLI — wraps commands and uses TypeSafe's Jev to match subcommand typos by intent, not edit distance. |
| jgrep | ★ 12 | Python | 2026-09-19 | Grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line. |
| jev-code | ★ 12 | TypeScript | 2026-09-23 | 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. |
| jevcore | ★ 12 | TypeScript | 2026-09-23 | TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default. |
| claude-jev | ★ 12 | Python | 2026-09-24 | Claude Code plugin that uses Jev for rule checks, verbatim compaction, and prompt routing. |
| lintus | ★ 12 | Rust | 2026-09-24 | Natural-language linter that uses Jev to evaluate code against plain-language rules. |
| jev-seo | ★ 11 | Rust | 2026-09-19 | Agent-first SEO and GEO CLI suite and MCP server using DuckDuckGo evidence and Jev scoring. |
| jev-mcp (blakestone-x) | ★ 11 | Python | 2026-09-19 | MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer. |
| jev-cli (Nasrallah-AL) | ★ 11 | TypeScript | 2026-09-19 | Command-line tool for TypeSafe's Jev AI model. |
| slop-grader | ★ 11 | TypeScript | 2026-09-22 | Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines. |
| cmd-mod-jev-nudge | ★ 11 | TypeScript | 2026-09-23 | Command Code mod: nudges the agent to keep going when it stops with work left, judged by Jev. |
| eutrya | ★ 11 | JavaScript | 2026-09-23 | Jev-native AI security harness for autonomous research, multi-agent swarms, persistent hunt boards, and long-running agent workflows. CLI-first, open source, and built for authorized security research. |
| pi-jev | ★ 11 | TypeScript | 2026-09-23 | Jev-assisted file retrieval and request caching for faster Pi workflows. |
| zevals | ★ 11 | TypeScript | 2026-09-23 | Jev judges yes-or-no assertions about an agent transcript, and the test passes when its probability reaches the configured threshold. |
| pi-jev-router | ★ 11 | TypeScript | 2026-09-23 | Task-boundary model routing for Pi Coding Agent, powered by TypeSafe Jev. Conservative policies, exact caching, and observable failover. |
| jev (BorisLeMeec) | ★ 10 | Go | 2026-09-19 | A claude code plugin for jev. |
| jevwire | ★ 10 | TypeScript | 2026-09-19 | Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev). |
| JevLint | ★ 10 | TypeScript | 2026-09-19 | Configurable semantic linting powered by Jev, with file-level NOUL judgments and a magic-strings plugin. |
| jev-guard | ★ 10 | JavaScript | 2026-09-19 | Prompt-injection and dangerous-action guard for coding agents (Claude Code, Codex, pi, ACP), powered by Jev. |
| jcr | ★ 10 | JavaScript | 2026-09-21 | Jev Capability Resolver: agents query a nested capability tree and receive only the deterministic commands and context relevant to the task. |
| evoke | ★ 10 | Rust | 2026-09-22 | 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. |
| liteagents | ★ 10 | Python | 2026-09-24 | Provider-independent agent SDK that uses typed routing to select a model for each turn. |
| jev-belay | ★ 9 | JavaScript | 2026-09-20 | Claude Code Stop hook that asks four Jev questions when files changed without a passing check, blocking unverified completion claims while failing open on errors. |
| hermes-jev-approvals | ★ 8 | Python | 2026-09-19 | PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only. |
| typesafe-skill-router | ★ 8 | Python | 2026-09-19 | 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. |
| jev-agent-skill-router | ★ 8 | Python | 2026-09-19 | Typed, confidence-aware agent skill routing with TypeSafe Jev. |
| pi-quiet-ask | ★ 8 | TypeScript | 2026-09-19 | TypeSafe Jev as the pi coding agent's quiet decision layer. |
| hermes-jev | ★ 8 | Python | 2026-09-19 | Typed System One decisions, ranking, verification, and an opt-in Hermes tool gate using TypeSafe Jev. |
| jev-router | ★ 8 | TypeScript | 2026-09-22 | LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call. |
| omp-jev-compaction | ★ 7 | TypeScript | 2026-09-19 | Verbatim Jev-scored context reduction for omp, over TypeSafe or OpenRouter. |
| pi-jev-router | ★ 7 | JavaScript | 2026-09-19 | Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway. |
| clean-code-review | ★ 6 | TypeScript | 2026-09-19 | Every code file in a pull request, judged against Uncle Bob's Clean Code by TypeSafe's Jev, then reviewed by Luna. Built on eve and Next.js. |
| opencompany | ★ 6 | TypeScript | 2026-09-19 | AI workspace whose approval review uses Jev to gate workspace actions with typed decisions. |
| jev-architect | ★ 6 | HTML | 2026-09-21 | Agent skill for finding, designing, and validating useful Jev decision loops before committing them to an application. |
| pi-jev-context | ★ 6 | TypeScript | 2026-09-22 | Model performance first. Token savings second. A Pi extension with freshness-aware read dedupe, Jev log filtering, and searchable verbatim recall. Keeps existing message history intact. |
| jev-mcp (arunav25) | ★ 5 | JavaScript | 2026-09-19 | Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy. |
| pi-fast-jev-compaction | ★ 5 | TypeScript | 2026-09-19 | Pi extension: verbatim context compaction with TypeSafe Jev decisions. |
| riff | ★ 5 | Python | 2026-09-19 | A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model. |
| jev-commit | ★ 5 | Python | 2026-09-20 | Pre-commit hook where Jev checks the message against the staged diff and flags debug leftovers, unmentioned work, and added credentials. |
| bicameral | ★ 4 | TypeScript | 2026-09-19 | Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes. |
| jev-superpowers | ★ 4 | Shell | 2026-09-19 | Cross-agent software-development skills that add Jev decisions to planning, execution, debugging, and completion gates. |
| slidepilot | ★ 4 | TypeScript | 2026-09-19 | Voice-driven semantic auto-advance for Slidev, powered by Cloudflare Agents and TypeSafe AI Jev. |
| diffjury | ★ 4 | TypeScript | 2026-09-19 | DiffJury — TypeSafe Jev PR risk router + code review coach. |
| tenet | ★ 4 | Go | 2026-09-20 | Commit-time review gate where Jev judges plain-language rules against agent-written code. |
| jev-spec | ★ 4 | TypeScript | 2026-09-21 | Specification-driven semantic verification engine that uses Jev to check AI-generated code and specs against explicit requirements. |
| jev-tool-router | ★ 4 | JavaScript | 2026-09-21 | MCP router for Codex that uses Jev to select an external tool on demand instead of exposing the agent to every tool schema. |
| jev-pref | ★ 4 | JavaScript | 2026-09-22 | Turn your AGENTS.md preferences into a fast, Jev-powered AI linter. |
| jev-oas-sentinel | ★ 4 | Python | 2026-09-22 | Catch breaking API behavior hidden in OpenAPI prose with deterministic checks and TypeSafe JEV System One semantic review. |
| Augustus | ★ 3 | Python | 2026-09-19 | Agent skill for designing Jev-assisted systems with decision theory, composition patterns, question diagnostics, and validation gates. |
| typesafe-cli (geilt) | ★ 3 | Python | 2026-09-19 | CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments. |
| jev-judgment | ★ 3 | Python | 2026-09-19 | Agent Skill: send closed coding-agent judgments to TypeSafe Jev. |
| jevex | ★ 3 | Python | 2026-09-19 | Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response. |
| fast-dev-compaction | ★ 3 | TypeScript | 2026-09-19 | Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks. |
| pi-heed | ★ 3 | TypeScript | 2026-09-19 | Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev. |
| jev-router (prismhq) | ★ 3 | Python | 2026-09-19 | Open-source LLM router that uses TypeSafe's Jev to pick a model, on top of LiteLLM. |
| jev-mcp (rashedInt32) | ★ 3 | TypeScript | 2026-09-19 | MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin. |
| open-jev-approvals | ★ 3 | Go | 2026-09-21 | Approval gate for Claude Code and Codex: intercepts tool calls, gets a Jev risk judgment, then applies a versioned local allow/deny policy. |
| dsh-jev | ★ 3 | TypeScript | 2026-09-22 | DSH bundle that registers jev_ask for TypeSafe Jev noul, choice, and score answers. |
| prompt2jev | ★ 3 | Python | 2026-09-22 | Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script |
| jev-mcp-dispatcher | ★ 3 | Python | 2026-09-22 | Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence. No repository-level license file was found during review. |
| hermes-jev-plugin | ★ 3 | Python | 2026-09-22 | TypeSafe Jev (System One) decision tools for Hermes Agent: jev_check / jev_route / jev_score / jev_evaluate |
| langchain-skill-router | ★ 3 | Python | 2026-09-23 | LangChain and deepagents skill router where Jev ranks installed SKILL.md files and decides whether and which skills to load for each turn. |
| jcm-router | ★ 2 | TypeScript | 2026-09-19 | Local proxy that picks the Claude model and effort per message using TypeSafe Jev. Routes subagents, leaves your cached main chat alone. |
| typesafe-mod | ★ 2 | TypeScript | 2026-09-19 | 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. |
| jev-shield | ★ 2 | JavaScript | 2026-09-19 | 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. |
| mastra-jev-moderation | ★ 2 | TypeScript | 2026-09-19 | Mastra input processor that uses Jev for a typed block decision and moderation category. |
| tiershift | ★ 2 | TypeScript | 2026-09-19 | 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. |
| skill-router | ★ 2 | Python | 2026-09-19 | Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery. |
| todo-jev | ★ 2 | Python | 2026-09-19 | ⚡ Ultra-fast, low-cost intelligent task classifier and 3-tier routing engine powered by TypeSafe Jev (System One). |
| jev-workbench | ★ 2 | TypeScript | 2026-09-19 | Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine. |
| typesafe-migration-guard | ★ 2 | TypeScript | 2026-09-19 | Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model). |
| pi-fast-jev-compaction (QuentinDanblon) | ★ 2 | TypeScript | 2026-09-20 | Pi context pruning that uses Jev to drop or truncate stale tool calls while preserving retained content verbatim. |
| jev-system-architect | ★ 2 | — | 2026-09-19 | System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives. |
| jev-skill-gate | ★ 2 | JavaScript | 2026-09-19 | Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session. |
| ailerix | ★ 2 | TypeScript | 2026-09-19 | Type-safe model router. Jev (System One) banks each request to a typed catalog route. |
| typesafe-ai-firewall | ★ 2 | Python | 2026-09-22 | Shadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md. No repository-level license file was found during review. |
| jev-mcp (freepik-company) | ★ 2 | Go | 2026-09-22 | MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe |
| decision-first | ★ 2 | Python | 2026-09-22 | Agent skill that spots bounded-judgment steps, tries a typed decision model (TypeSafe's Jev) first, and documents every attempt |
| jear | ★ 2 | Rust | 2026-09-22 | Jev-routed client for NEAR AI Cloud inference and IronClaw agents. |
| jev-git | ★ 1 | Rust | 2026-09-19 | Sub-second pre-commit and pre-push semantic gate that screens staged diffs with Jev. |
| jev-scout | ★ 1 | Rust | 2026-09-19 | Grounded GitHub and crates.io discovery CLI and MCP server that uses Jev to score architectural fit, licensing, and maintenance. |
| jev-skillful | ★ 1 | TypeScript | 2026-09-19 | 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. |
| jev-triage | ★ 1 | TypeScript | 2026-09-19 | Uses typeful jev, zero sync to pull and sync large repositories for issue triage. |
| jev-predict-skill | ★ 1 | HTML | 2026-09-19 | Predict another skill's next closed decision with TypeSafe Jev — without running that skill. |
| stepwarden | ★ 1 | TypeScript | 2026-09-20 | Claude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it. |
| Antigravity-mcp-semantic-search-with-TypeSafeAi | ★ 1 | Python | 2026-09-19 | Fast semantic code search & diff sanity auditor for AI coding assistants (Antigravity, Cursor, Claude Code) powered by TypeSafe System One. |
| pi-jev | ★ 1 | TypeScript | 2026-09-20 | Pi extension suite for Jev-powered context compaction and model routing. |
| hunch | ★ 1 | Python | 2026-09-19 | Semantic code review with Jev, plain-English rules, and installable agent skills. |
| limpet | ★ 1 | Python | 2026-09-19 | A Stop hook that stops your coding agent from stopping too early. Plain-language rules, judged by jev. |
| ask-jev | ★ 1 | PowerShell | 2026-09-19 | Utilizing Jev, the RLCD-type model provided by TypeSafe AI, to independently and cheaply judge agentic coding sessions. |
| jev-flash-router | ★ 1 | TypeScript | 2026-09-20 | MCP server that uses Jev to route coding-agent decisions such as file selection, task paths, and test-impact checks. |
| omp-typesafe | ★ 1 | TypeScript | 2026-09-19 | TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent. |
| pi-jev-helm | ★ 1 | TypeScript | 2026-09-20 | Pi extension that classifies tasks with Jev and routes each run to an explicitly configured model. |
| jev-mcp (BYK) | ★ 1 | TypeScript | 2026-09-22 | An eval-first MCP server for TypeSafe's Jev, a System One model that returns typed judgments (noul, choice, score) with probabilities instead of generated text. |
| askjev (pZacca) | ★ 1 | TypeScript | 2026-09-22 | Unofficial MCP server for Jev (Typesafe AI) |
| jev-toolkit | ★ 1 | TypeScript | 2026-09-22 | 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. |
| jev-skill-router | ★ 1 | Python | 2026-09-22 | 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. |
| dsh-jev-verify | ★ 1 | JavaScript | 2026-09-22 | Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design. |
| jevonian | ★ 1 | TypeScript | 2026-09-22 | Local model-routing proxy where Jev selects the model route and reasoning depth, and also judges which tool history can be compacted. |
| jev-routed-agent | ★ 1 | Python | 2026-09-23 | LangChain and Flask agent where Jev chooses among knowledge, calculator, weather, and chat routes, with a local-rule fallback. |
| codex-jev-router | ★ 1 | JavaScript | 2026-09-24 | Portable Jev router for cost-aware Codex subagent model and reasoning selection. |
| pi-agent-foreman | ★ 0 | TypeScript | 2026-09-19 | Send Pi agents back to work when they stop before the job is done. |
| switchboard | ★ 0 | Python | 2026-09-19 | Guardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python. |
| typesafe-demo-mcp | ★ 0 | TypeScript | 2026-09-19 | MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools. |
| AskJev-MCP | ★ 0 | JavaScript | 2026-09-20 | MCP server for typed Jev Choice, Noul, and Score judgments with probabilities and confidence. |
| decide-mcp | ★ 0 | TypeScript | 2026-09-19 | Configurable decision MCP server with AI SDK, Jev, percentage scores, and bias-profile routing. |
| pi-jev-router (gloridifice) | ★ 0 | TypeScript | 2026-09-20 | Jev model-routing integration for the Pi coding agent. |
| jevkeep | ★ 0 | TypeScript | 2026-09-20 | Codex plugin that uses Jev to preserve useful conversation excerpts alongside compacted summaries. |
| pi-jev-code | ★ 0 | TypeScript | 2026-09-19 | Single-agent Pi coding coprocessor with Jev semantic gates, baseline-to-current diff review, and append-only observability telemetry. |
| pi-typesafe-jev | ★ 0 | TypeScript | 2026-09-19 | 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. |
| frost | ★ 0 | Go | 2026-09-19 | A flexible and configurable CLI model router using TypeSafe Jev. |
| check-risk | ★ 0 | TypeScript | 2026-09-19 | A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge. |
| jev-compaction (picaye) | ★ 0 | JavaScript | 2026-09-20 | Hermes context compaction that has Jev score tool calls, drops stale content, and preserves everything retained verbatim. |
| jev-plugins | ★ 0 | — | 2026-09-20 | Cursor and Hermes plugin marketplace for JEV Labs routing tools. |
| jev-builder-loop | ★ 0 | Python | 2026-09-19 | Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act). |
| typesafeai-review | ★ 0 | Python | 2026-09-19 | Using Typesafe.AI to generate diff reviews. |
| agent-gate-loop | ★ 0 | TypeScript | 2026-09-19 | Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev. |
| omp-jevens-classifier | ★ 0 | TypeScript | 2026-09-19 | Jev-powered model-judged permission gate for OMP (TypeSafe System One). |
| jev-review (thiago-ss) | ★ 0 | Python | 2026-09-19 | Autonomous Jev pull-request review with typed decisions, calibrated approval gates, and trusted-owner escalation. |
| pi-typesafe | ★ 0 | TypeScript | 2026-09-19 | Pi coding-agent extension built on the TypeSafe AI System One API (Jev). |
| hermes-jev-router | ★ 0 | Python | 2026-09-19 | Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending. |
| zcode-jev | ★ 0 | TypeScript | 2026-09-19 | Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic. |
| agent-handoff-gate | ★ 0 | Python | 2026-09-19 | Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent. |
| jev-agent-kit | ★ 0 | JavaScript | 2026-09-22 | jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies. |
| Jev-Checkpoint | ★ 0 | TypeScript | 2026-09-22 | A local MCP server that uses TypeSafe Jev to confidence-gate an AI agent’s next step, routing uncertain decisions to proceed, deeper review, or human input. |
| progressgate | ★ 0 | TypeScript | 2026-09-22 | Detect semantic stagnation in AI agent loops |
| jev-packs | ★ 0 | Python | 2026-09-22 | Evidence-gated registry of Jev question packs — curated questions, golden cases and measured evidence for Jev-compatible decision endpoints |
| JevGuard | ★ 0 | TypeScript | 2026-09-22 | Claude Code + Codex CLI plugin that verifies the agent follows project rules through a System One (Jev) model |
| jev-atlas | ★ 0 | Python | 2026-09-22 | Map where Jev and System One models actually belong in your project, test the strongest ideas, then implement them. A skill for Claude Code and Codex. |
| jev-retrieval | ★ 0 | Rust | 2026-09-24 | Code and document search CLI combining BM25 recall with Jev verification and calibrated reranking. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| cua | ★ 25,790 | HTML | 2026-09-22 | Computer-use platform with a Jev recipe where the model selects one bounded action candidate and the client validates it before execution. |
| Jev Ultrafast | ★ 9,291 | Python | 2026-09-19 | Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed. |
| agent-desktop | ★ 1,441 | Rust | 2026-09-22 | Desktop automation runtime with a Jev skill that chooses UI operations and targets from accessibility-tree candidates. |
| celesto | ★ 958 | Python | 2026-09-22 | Agent-computer platform with a runnable pull-request review lab where Jev judges whether findings are introduced, supported, and actionable. |
| reticle | ★ 828 | TypeScript | 2026-09-24 | Runtime perception layer that gives web and desktop agents Jev-style machine-readable state. |
| surf-cli | ★ 624 | TypeScript | 2026-09-23 | Optional Jev commands find, filter, and verify browser elements, then select bounded actions subject to confidence and write-authority checks. |
| Jev-cu | ★ 584 | JavaScript | 2026-09-23 | 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。 Only send text, not screenshots.. |
| typesafe-computer-use | ★ 537 | Python | 2026-09-19 | Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS. |
| mobile-jev | ★ 240 | JavaScript | 2026-09-19 | Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo. |
| jev-browser-use | ★ 206 | JavaScript | 2026-09-19 | 5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp. |
| jev-browser | ★ 155 | TypeScript | 2026-09-19 | Browser use using Typesafe's Jev model. |
| unclutter | ★ 136 | TypeScript | 2026-09-19 | WXT browser extension: Jev-powered page clutter removal with reusable template rules. |
| arc-cua | ★ 128 | Python | 2026-09-23 | Jev selects the next UI operation from the targets and actions exposed by the current desktop state. |
| jev-voice-browser | ★ 126 | JavaScript | 2026-09-19 | 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. |
| webctl | ★ 125 | Go | 2026-09-23 | Smart web search CLI for agents, backed by Jev. Saves a lot of tokens. |
| fast-browser-use | ★ 121 | Python | 2026-09-23 | A fast browser-use skill powered by local LLMs via single-token reflexes. Fast, local-first, zero hallucinations. |
| jev-browser | ★ 94 | TypeScript | 2026-09-24 | Indexed browser automation where Jev selects a control and Playwright executes it. |
| jev-use | ★ 92 | Swift | 2026-09-23 | Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model. |
| jev-desktop | ★ 63 | JavaScript | 2026-09-23 | TypeSafe Jev action selection inside Codex Computer Use. |
| playwright-recast | ★ 60 | TypeScript | 2026-09-23 | Jev chooses camera moves, emphasis, and timing from a rendered Playwright recording and bounded direction candidates. |
| typesafe-adblock | ★ 58 | JavaScript | 2026-09-19 | 🧹 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. |
| ghosthands | ★ 51 | Python | 2026-09-23 | Give an agent real hands and eyes: undetectable, DOM-independent GUI automation. A $4 USB-HID microcontroller for hands, a vision grounding model for eyes, any LLM for a brain. |
| vibecheck | ★ 42 | JavaScript | 2026-09-19 | Chrome extension: vibe-check your X posts with TypeSafe's Jev before you hit Post. |
| computer-use-cache | ★ 42 | JavaScript | 2026-09-23 | Jev judges whether a cached computer-use workflow is semantically reusable for the current request. |
| jev-cua | ★ 34 | Swift | 2026-09-24 | macOS voice and text control where Jev selects UI actions in an observe–act–verify loop. |
| jev-browser-skill | ★ 33 | TypeScript | 2026-09-23 | Isolated Playwright Chromium driven by Jev. A coding agent (or you) runs a. |
| Jevbridge | ★ 25 | TypeScript | 2026-09-19 | ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode. |
| ulka | ★ 23 | TypeScript | 2026-09-23 | Experimental browser agent powered by FX, Jev, and Vercel AI Gateway. Bring your own API key to read pages and automate browser tasks. |
| jev-browser (Ying-Kai-Liao) | ★ 22 | JavaScript | 2026-09-19 | Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server. |
| hookmeter-jev | ★ 21 | HTML | 2026-09-23 | ⚡ Millisecond-level Viral Hook Telemetry & Co-pilot for Social Media (Chrome Extension + JEV System 1). |
| jev-mac-voice | ★ 20 | JavaScript | 2026-09-23 | English full-duplex voice control for macOS with OpenAI Realtime, native Accessibility, and Jev. |
| jev-for-chrome | ★ 20 | TypeScript | 2026-09-23 | 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. |
| Jev macOS Loop | ★ 17 | JavaScript | 2026-09-21 | Native macOS automation loop where Jev chooses the next GUI action from OCR, accessibility, and OmniParser observations. |
| x-scanner | ★ 15 | TypeScript | 2026-09-21 | Chrome extension where Jev scores and labels X posts with typed judgments and a live local cost counter. |
| lkclean | ★ 14 | TypeScript | 2026-09-23 | Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision. |
| jev-ultrafast-mcp | ★ 13 | Python | 2026-09-23 | 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. |
| system1-agents | ★ 12 | Python | 2026-09-23 | System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics. |
| jev-chat-for-twitch | ★ 11 | JavaScript | 2026-09-23 | Filter any live Twitch chat with Jev: a bring-your-own-key Chrome extension. |
| jev-social | ★ 10 | JavaScript | 2026-09-20 | Social research agent for Instagram, TikTok, and LinkedIn: Jev repeatedly chooses the next concrete operation and target, while socai executes it in a local Chrome session. |
| live-jev | ★ 10 | JavaScript | 2026-09-19 | 2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model. |
| sift | ★ 9 | JavaScript | 2026-09-21 | Chrome extension where Jev labels X posts by content type and judges which posts should be hidden. |
| xtags | ★ 8 | JavaScript | 2026-09-19 | 在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。 |
| jev-ego | ★ 7 | TypeScript | 2026-09-19 | TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright. |
| AskJev | ★ 6 | TypeScript | 2026-09-19 | AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude). |
| jev-agent-browser | ★ 6 | JavaScript | 2026-09-22 | Browser-agent integration where Jev selects typed actions for research and classification workflows. |
| fastbrowse | ★ 5 | Python | 2026-09-19 | Browser agent where Jev selects actions, an LLM reads and plans, and answers cite page evidence. |
| jev-browser (vinilana) | ★ 4 | TypeScript | 2026-09-19 | Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts. |
| jev-browse | ★ 3 | JavaScript | 2026-09-19 | Drives a real browser with Jev making every decision and Vercel's agent-browser performing every action, with a benchmark. |
| computer_use | ★ 3 | Go | 2026-09-19 | MacOS computer use driven by Jev (TypeSafe System One) as the decision maker. |
| jev-skip | ★ 3 | TypeScript | 2026-09-20 | YouTube extension that asks Jev for the sponsor probability of each caption segment and paints the result on the seek bar without a crowd database. |
| playjev | ★ 3 | TypeScript | 2026-09-21 | Experimental Playwright library for natural-language browser automation, using Jev to turn page state and instructions into typed actions. |
| jev-mobile | ★ 2 | Python | 2026-09-19 | Fast structured Android control loops with TypeSafe Jev and Mobile MCP. |
| jev-frontend-qa | ★ 2 | Python | 2026-09-19 | Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo. |
| otto | ★ 2 | TypeScript | 2026-09-19 | Open-source native computer use for macOS and Windows: TypeSafe Jev, local OCR, and selective planning. |
| jevarena | ★ 2 | TypeScript | 2026-09-20 | Two Jev agents compete in click-only browser games through Browser Use. |
| turbo | ★ 2 | Go | 2026-09-19 | Jev-powered semantic browser use. |
| jev-browser (tontoko) | ★ 2 | JavaScript | 2026-09-19 | One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions. |
| jev-shield (vmendes90) | ★ 2 | TypeScript | 2026-09-19 | Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev. |
| jev-ra | ★ 2 | Python | 2026-09-22 | Browser automation MCP server where Jev chooses the next bounded browser action for a coding agent. |
| barrunto | ★ 1 | TypeScript | 2026-09-19 | A Chrome extension that brings TypeSafe's Jev to X.com to analyze posts as you browse. |
| almond-fastloop | ★ 1 | HTML | 2026-09-19 | Almond-fastloop: Almond's browser computer-use rig (Chrome DevTools + TypeSafe Jev), and the Browser Use Olympics benchmark it is measured on. |
| psearch | ★ 1 | Python | 2026-09-19 | Parallel web search for terminals and agents, with local Chromium and Jev-guided exploration. |
| jev-browser-skill | ★ 1 | JavaScript | 2026-09-22 | Claude Code and Codex browser skill that asks Jev to choose the next browser action. |
| jev-browser-pilot | ★ 0 | Python | 2026-09-20 | Bounded browser and desktop automation where Jev picks one next step while code owns perception, execution, and verification. |
| jev-orb | ★ 0 | Makefile | 2026-09-20 | Push-to-talk voice orb for autonomous browser control using Jev and Metal Whisper. |
| JevTest | ★ 0 | TypeScript | 2026-09-19 | Bounded exploratory browser testing with Jev, deterministic assertions, and replayable evidence. |
| browser-use-olympics | ★ 0 | HTML | 2026-09-19 | 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). |
| jev-browser (KesavanKing) | ★ 0 | Python | 2026-09-19 | Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values. |
| jevlens | ★ 0 | JavaScript | 2026-09-20 | Chrome extension that uses Jev to annotate articles and posts on X and Threads. |
| jev-playwright-mcp | ★ 0 | TypeScript | 2026-09-19 | 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. |
| jev-browser (MahmoudAdelbghany) | ★ 0 | JavaScript | 2026-09-19 | Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included. |
| sloppy-jevs-extension | ★ 0 | JavaScript | 2026-09-19 | Open-source Chrome extension that filters AI-generated prose and ads with Jev. |
| sift | ★ 0 | TypeScript | 2026-09-19 | Chrome extension that re-ranks Google results with TypeSafe Jev and folds away sales pages and SEO filler. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| QuantDinger | ★ 12,029 | Python | 2026-09-23 | Open-source AI Trading OS, agent trading, and vibe trading, with Jev System One integration. Research, build Python strategies, backtest, and paper/live trade across crypto, stocks, and forex. Launch your own multi-tenant trading SaaS with built-in user management, billing, payments, and settlement. |
| genoffice | ★ 7,541 | TypeScript | 2026-09-23 | Jev assigns a calibrated relevance score to each of the top 20 locally recalled files and reranks the search results. |
| xerj | ★ 2,365 | Rust | 2026-09-23 | Jev scores whether each retrieved document answers the query and reranks the search results by that relevance. |
| jev-chat-jarvis | ★ 1,696 | Kotlin | 2026-09-22 | Android conversation copilot where Jev interprets chat context and helps rank candidate replies before the user inserts one. |
| jev-trader | ★ 1,349 | TypeScript | 2026-09-19 | One AI trade decision every Monad block. Jev on Kuru MON-USDC. |
| jev-chat-windows | ★ 467 | Python | 2026-09-24 | Windows WeChat reply assistant that uses local OCR and Jev to classify intent before presenting three manual-send replies. |
| horosa-skill | ★ 419 | Python | 2026-09-23 | When explicitly enabled, Jev selects an astrology technique when keyword routing has no match and extracts settings stated by the user. |
| claude-code-trace | ★ 370 | Rust | 2026-09-23 | Jev scores agent progress, tool use, focus, exploration, recovery, and token efficiency from Claude Code session logs. |
| llm-debugger-vscode-extension | ★ 359 | TypeScript | 2026-09-23 | At each debugger pause, Jev chooses the next debugging action from the stack, locals, nearby source, output, and prior attempts. |
| AIStock | ★ 335 | Python | 2026-09-24 | Stock-analysis application that uses Jev for structured market judgments. |
| tax-doc-classifier | ★ 314 | TypeScript | 2026-09-21 | Tax-document classifier where Jev selects an IRS form and page kind from extracted PDF text. |
| docjev | ★ 307 | Python | 2026-09-23 | A very fast document classifier/splitter using Jev. |
| jev-chat-jarvis-mac | ★ 248 | Python | 2026-09-23 | Jev classifies incoming WeChat or QQ messages by intent and risk before the app presents reply guidance. |
| summarize | ★ 223 | Python | 2026-09-23 | The optional Jev prefilter scores transcript segments before the selected material is sent to the summarizer. |
| siftrank | ★ 210 | Go | 2026-09-23 | Jev compares items against a ranking prompt across repeated batches so SiftRank can produce a converged relevance order. |
| notra | ★ 191 | TypeScript | 2026-09-19 | Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions. |
| crush-monitor | ★ 183 | TypeScript | 2026-09-23 | Crush Favorability Monitor: Use Jev to analyze the emotions, intentions and reply performance of WeChat chats. Deploy locally, use your own API Key.. |
| perch | ★ 171 | JavaScript | 2026-09-23 | Semantic code linting with Jev. |
| OmniStudio | ★ 164 | TypeScript | 2026-09-23 | OmniStudio exposes Jev Noul, Choice, and Score decisions for triage, scoring, content guards, retrieval reranking, and intent routing. |
| Jev-X-Sentiment-Analysis | ★ 162 | Python | 2026-09-23 | An on-demand crypto market intelligence and decision-support terminal powered by TypeSafe AI's System One model (Jev). |
| jev-webmcp-extension | ★ 104 | JavaScript | 2026-09-23 | A small extension that demos the combination of Jev x WebMCP. |
| superterminal | ★ 100 | Rust | 2026-09-23 | Jev ranks command-palette entries against a plain-language query so the intended terminal action appears first. |
| formanator | ★ 98 | Rust | 2026-09-21 | CLI and MCP server for Forma benefit claims that can use Jev to classify receipt line items into reimbursement categories. |
| 332_lab-jev-chat | ★ 94 | Kotlin | 2026-09-23 | Jev Chat Assistant for Windows - PC version of WeChat intent judgment and DeepSeek suggested reply. |
| jev-chat | ★ 91 | TypeScript | 2026-09-23 | A tool calling chat bot built with Jev and no LLM. |
| warrenduffer | ★ 82 | TypeScript | 2026-09-24 | Intraday trading bot where Jev ranks Nifty 50 candidates and deterministic code controls position sizing and risk. |
| jev-voice | ★ 80 | Python | 2026-09-23 | Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation. |
| changelog.earth | ★ 76 | JavaScript | 2026-09-23 | When enabled, Jev performs bounded editorial and title checks on stories selected for an Earth changelog edition. |
| james_library | ★ 74 | Rust | 2026-09-24 | Scientific-agent architecture separating fast local judgment, probabilistic evaluation, evidence, and authorization. |
| jevmeter | ★ 70 | Python | 2026-09-19 | Put a live Jev (TypeSafe) meter on any video: every sentence scored, rendered as a 16:9 edit. |
| prism-liquidity-agent | ★ 69 | TypeScript | 2026-09-22 | Solana liquidity agent with optional Jev shadow judgments for deposit choice, toxic flow, and market-regime stress. |
| shapeshift | ★ 66 | TypeScript | 2026-09-23 | An input that becomes what you mean: one text box that morphs into the right UI as you type. Powered by TypeSafe Jev, works offline. |
| QuantStudio | ★ 58 | JavaScript | 2026-09-23 | Jev evaluates market state from completed candles, live prices, positions, and strategy constraints, then suggests observe, open, or close actions for human approval. |
| JevIntent | ★ 52 | Java | 2026-09-24 | WeChat plugin that uses Jev to analyze message intent, emotion, and reply posture locally. |
| Stratum | ★ 51 | Rust | 2026-09-23 | AI-powered Log Intelligence System - Semantic search, anomaly detection, and root cause analysis for logs using RAG techniques. Built with Rust, Axum, NATS, ClickHouse, and Qdrant. |
| live-jev (okinaaudio) | ★ 39 | Python | 2026-09-22 | Ableton Live controller where Jev maps a short natural-language request to a bounded music-production action. |
| jev-poly-crypto-demo | ★ 37 | TypeScript | 2026-09-24 | Crypto decision dashboard that uses Jev to classify market state and risk. |
| Jev-Moderation-Bot | ★ 36 | Python | 2026-09-19 | Real-time Discord moderation bot: Jev evaluates messages and metadata in parallel to catch phishing, spam, and social engineering with a progressive escalation ladder. |
| jev-suite | ★ 36 | Java | 2026-09-24 | Four decision-quality applications where Jev answers structured questions and deterministic code keeps final authority. |
| call-coach-ai | ★ 35 | HTML | 2026-09-22 | Call-coaching application where Jev evaluates conversation context to surface structured coaching decisions. |
| jev-guard | ★ 35 | Java | 2026-09-24 | Exchange deposit and withdrawal risk-triage gateway where Jev triages and deterministic code adjudicates. |
| jev-recall | ★ 33 | TypeScript | 2026-09-23 | Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev. |
| jev-seo | ★ 31 | Python | 2026-09-23 | Live SEO audit for any website from one homepage URL, judged by Jev. PDF, XLSX and Markdown reports. |
| jev-reviewer | ★ 30 | JavaScript | 2026-09-21 | Systematic-review extraction app where Jev answers structured review forms and points reviewers to quoted source lines. |
| sharp | ★ 30 | TypeScript | 2026-09-23 | Filter your X.com feed with Jev or any LLM. |
| jev-trade | ★ 29 | TypeScript | 2026-09-19 | Live Jev trader on Hyperliquid. |
| jevmail | ★ 27 | TypeScript | 2026-09-21 | Read-only Gmail triage app where Jev assigns each message a tray, urgency score, and human-authorship judgment. |
| pi-codemode | ★ 27 | TypeScript | 2026-09-23 | The jev.ask runtime global lets sandboxed TypeScript programs request calibrated Jev Noul, Choice, and Score answers. |
| commit-miner | ★ 26 | Rust | 2026-09-19 | Classify Git commit diffs and messages with Jev. Bug fixes, security fixes/CWEs, and change types. |
| doc-router | ★ 26 | Rust | 2026-09-22 | Document OCR router where Jev judges page by page whether the existing text layer is usable or OCR is required. |
| SmartMoney-Cub | ★ 26 | Python | 2026-09-23 | Read-only trading journal and review harness: Jev typed judgments, agent integration, and a reproducible finance benchmark. No orders, no advice. |
| blink | ★ 24 | TypeScript | 2026-09-19 | Codebase search powered by Jev from @typesafe-ai. |
| refgarden | ★ 23 | TypeScript | 2026-09-19 | A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections. |
| rikkahub-sillytavern-android | ★ 21 | Kotlin | 2026-09-23 | RikkaHub Plus Huadeng Edition - Android AI chat client & SillyTavern Android tavern compatibility. Connected to API instant chat: prefix cache to save token, semantic memory RAG, Jev intelligent decision-making, QuickJS plug-in, voice call, WeChat QQ Bot; character card, world book Lorebook, default, regular, QR, beautification theme can be imported with one click according to the official semantics of the tavern, without Termux/Node.js. |
| Cheshi | ★ 18 | C | 2026-09-23 | Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app. |
| pi-dcp | ★ 17 | TypeScript | 2026-09-23 | The experimental Jev path scores completed context payloads so users can review and approve what remains available to the agent. |
| hermes-nerve | ★ 17 | Python | 2026-09-23 | 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. |
| jev-yaba-wechat | ★ 17 | Python | 2026-09-23 | Don’t know how to answer the message on WeChat? macOS floating chat assistant: identifies message intent and communication risks, GPT generates a variety of words, Jev evaluates candidates, and fills in WeChat with one click. I will help you think about it and send it to you to order.. |
| jev-gmail-ai-spam-filter-and-labeling | ★ 16 | JavaScript | 2026-09-23 | Self-hosted AI email classifier for Gmail powered by Jev. Create custom labels, organize your inbox, and filter spam with confidence and cost controls. |
| transcript-lens | ★ 16 | TypeScript | 2026-09-23 | YouTube transkriptlerini anlamına göre keşfedin. Türkçe arayüz, Jev analizi, altyazı dışa aktarma ve Vercel kurulum rehberi. |
| yanwai | ★ 15 | Kotlin | 2026-09-24 | Android WeChat module that uses Jev to show emotion probabilities, implied meaning, and communication suggestions. |
| hafiza-os | ★ 14 | Python | 2026-09-23 | Linux, macOS ve Windows için kaynaklı ikinci beyin. Claude Code, Codex ve Antigravity adaptörleri; yerel Markdown kasa, ayrı hafıza incelemesi, isteğe bağlı Mem0/Jev. |
| jev-mail-classifier | ★ 14 | Python | 2026-09-23 | Classify your inbox with Jev (TypeSafe's System One model) — tag, move, flag, and notify, all config-driven. |
| Jev-Trades | ★ 13 | Python | 2026-09-19 | Trading bot with the all new TypeSafe AI's first system one model named as Jev. |
| wechat-jev-assistant | ★ 13 | Python | 2026-09-24 | Windows WeChat assistant that reads and redacts conversations before Jev classifies them. |
| ad-radar | ★ 13 | JavaScript | 2026-09-24 | Browser extension that uses Jev to identify and fold ads and selected topics on social platforms. |
| jevthoven | ★ 12 | TypeScript | 2026-09-23 | AI Music (MIDI) generator powered by Jev. |
| jevocks | ★ 9 | TypeScript | 2026-09-19 | Everyday Stocks Status with Jev. |
| jevlogs | ★ 8 | TypeScript | 2026-09-19 | Open-source Jev log triage for OpenTelemetry. Score the signal before expensive LLM analysis. |
| jsort | ★ 8 | Python | 2026-09-21 | Sorts text along a plain-English criterion using pairwise Jev Noul judgments and a locally fitted Bradley–Terry scale, with uncertainty and reliability reporting. |
| jev-rerank | ★ 6 | Python | 2026-09-19 | Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0. |
| secondlayer | ★ 6 | TypeScript | 2026-09-19 | Self-hosted Stacks data service whose Slack gate and fault-triage paths use Jev decisions. |
| semdecide | ★ 6 | Python | 2026-09-19 | Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev. |
| jev-cli (tumf) | ★ 6 | Python | 2026-09-19 | Small dependency-free CLI for TypeSafe Jev. |
| ai-elo-ranker | ★ 5 | Python | 2026-09-19 | High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking. |
| jev-grug | ★ 4 | TypeScript | 2026-09-19 | Helping JEV speak <3. |
| typesafe-cli (y0usaf) | ★ 4 | TypeScript | 2026-09-19 | Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose. |
| jevsql | ★ 3 | JavaScript | 2026-09-19 | SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded. |
| smart-switch | ★ 3 | Swift | 2026-09-19 | Reimagined window switcher for macOS using frontier artificial intelligence. Predicted by TypeSafe's Jev model. |
| every | ★ 3 | Python | 2026-09-19 | Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev. |
| jev-resume-disqualifier | ★ 3 | Python | 2026-09-21 | Recruiting-screening demo that combines deterministic date and eligibility checks with Jev judgments to route resumes for review or rejection. |
| jselect | ★ 3 | Python | 2026-09-21 | Selects source-linked evidence within a token budget using Jev relevance judgments plus local diversity-aware selection. |
| jev-document-classification | ★ 2 | TypeScript | 2026-09-19 | JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model. |
| typesafe-jev | ★ 2 | TypeScript | 2026-09-19 | Screen a folder of CVs with the TypeSafe Jev decision model: typed judgments, an editable policy, free re-scoring. |
| citation-verifier | ★ 2 | JavaScript | 2026-09-19 | Check whether each cited paper supports the sentence citing it. Claude proves the quote, TypeSafe's Jev scores it, a human decides. |
| jev-tree | ★ 2 | TypeScript | 2026-09-19 | Recursive Jev choice over a taxonomy. Select from more than 255 options without breaking TypeSafe Jev's choice cap. |
| jevibe-check | ★ 2 | JavaScript | 2026-09-19 | A live tone labeler for Bluesky posts and drafts, using TypeSafe's Jev API. |
| jev.nvim | ★ 2 | Lua | 2026-09-20 | Neovim plugin that has Jev score each function against a plain-language question and ranks results in quickfix. |
| btc-jev-signal | ★ 2 | TypeScript | 2026-09-19 | Experimental multi-horizon BTC signal generator using TypeSafe Jev probabilities and Binance market data. |
| jlink | ★ 2 | Python | 2026-09-21 | Record-linkage toolkit for Python, CLI, Stata, and R: Jev judges record pairs against a plain-English matching rule and returns auditable probabilities. |
| jevpdf | ★ 2 | TypeScript | 2026-09-24 | PDF reader that uses Jev Noul judgments to highlight lines matching a natural-language question. |
| JevTicktRouter | ★ 1 | C# | 2026-09-19 | A .NET 10 and React 19 application for fast, structured AI-powered ticket triage using TypeSafe Jev. |
| Jackalope | ★ 1 | Rust | 2026-09-19 | Desktop GUI for agentic coding that routes tasks across local agents and accounts, with Jev picking the best agent per task, running basic code-review checks, and supplying context. |
| jev-cli | ★ 1 | TypeScript | 2026-09-19 | CLI for TypeSafe AI's Jev evaluation model — typed questions in, structured JSON answers out. |
| pagegrade | ★ 1 | TypeScript | 2026-09-19 | Browser extension that grades page sections for clarity, writing quality, and on-page SEO with Jev. |
| commentcop | ★ 1 | TypeScript | 2026-09-19 | Put your code comments on trial. Powered by Jev. |
| qualm | ★ 1 | TypeScript | 2026-09-19 | Typed decisions from a System One model. An uncertain answer is a different type from a confident one — and the compiler makes you handle it. |
| jev-audio-beeper | ★ 1 | TypeScript | 2026-09-19 | Low-latency audio censorship POC using Jev typed decisions and ffmpeg. |
| jev-score | ★ 1 | JavaScript | 2026-09-22 | Local-first document evaluation workspaces powered by Jev |
| metis | ★ 1 | Python | 2026-09-22 | Metis: automatic GitHub issue triage powered by TypeSafe AI Jev. A reusable GitHub Action. |
| tiab-review-plugin | ★ 1 | TypeScript | 2026-09-22 | Chrome extension for systematic-review screening where Jev returns per-criterion match probabilities and an inclusion judgment. |
| triagedy | ★ 1 | Rust | 2026-09-22 | Security-alert triage filter where Jev or a local model returns typed dispositions while policy routing remains in code. |
| Jev Subtitle Translator | ★ 1 | Python | 2026-09-23 | SRT translation app whose Jev Noul checks flag subtitle pairs that need human review without rewriting them. |
| jevegis | ★ 0 | TypeScript | 2026-09-19 | Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT. |
| jev-resume-analyzer | ★ 0 | Python | 2026-09-19 | CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI. |
| transcript-scorecard | ★ 0 | TypeScript | 2026-09-19 | ACME live support-call scoring demo with TypeSafe AI, Effect, SQLite, React, Vite, and Turborepo. |
| emoji-jev | ★ 0 | TypeScript | 2026-09-19 | Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app. |
| s1s | ★ 0 | TypeScript | 2026-09-19 | System One Search: navigate and trace code with TypeSafe judgments and repository evidence. |
| JevSysUno | ★ 0 | TypeScript | 2026-09-20 | TypeScript application exploring TypeSafe Jev as a System One decision layer. |
| jev (haibt163) | ★ 0 | TypeScript | 2026-09-20 | TypeScript application built around TypeSafe Jev decisions. |
| pkg-gate | ★ 0 | JavaScript | 2026-09-19 | Pre-install security gate for npm lifecycle scripts using TypeSafe System One. |
| typesafe-comment | ★ 0 | Python | 2026-09-19 | Small Python package that uses typesafe.ai to evaluate code comments on certain heuristics. |
| mimicry | ★ 0 | Python | 2026-09-19 | Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop. |
| newsscore | ★ 0 | Python | 2026-09-20 | Async library and CLI that turns a week of news into one sentiment score per ticker, using Jev by default. |
| draftpulse | ★ 0 | TypeScript | 2026-09-19 | Experimental: live X draft viral scorer powered by TypeSafe Jev. |
| jev-trader (renatosousa) | ★ 0 | Python | 2026-09-20 | Trading application that uses Jev for market decisions. |
| typesafe-triage-guard | ★ 0 | Python | 2026-09-19 | Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate. |
| scam-shield | ★ 0 | TypeScript | 2026-09-19 | Scam text message filter powered by TypeSafe's Jev model. |
| trading-bot-jev | ★ 0 | TypeScript | 2026-09-20 | Binance testnet trading bot that uses Jev to judge news. |
| JevSlop | ★ 0 | TypeScript | 2026-09-19 | Scores public note.com articles across eight Jev dimensions and produces an inspectable AI-slop score. |
| github-star-organizer-jev | ★ 0 | Python | 2026-09-20 | Uses Jev to classify and organize GitHub stars. |
| jev-the-janitor | ★ 0 | Python | 2026-09-22 | A janitor for markdown vaults powered by TypeSafe Jev: Jev votes on each note, your code files it, you review the low-confidence pile. |
| discoprint | ★ 0 | JavaScript | 2026-09-22 | Classify an artist's discography by theme, mood, and lyrical complexity with Jev (TypeSafe AI), and view it as a colorful terminal dashboard |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| typesafe-mario | ★ 286 | Python | 2026-09-19 | A TypeSafe/Jev agent that plays Super Mario Bros. from structured emulator state. |
| quackd | ★ 229 | Python | 2026-09-23 | One offboard CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM) and a decision LLM for cheaper and faster steps (Jev, Laya, and Kev). Supports Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, Jetson, or any ROS. |
| embodied-jev | ★ 164 | Python | 2026-09-22 | EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs |
| laya-vs-jev | ★ 89 | Python | 2026-09-23 | Laya vs Jev: local MLX and hosted AI decisions playing T-Rex side by side, with live metrics and replay recording. |
| jev-drone | ★ 77 | Python | 2026-09-19 | Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz. |
| detroit-ai-player | ★ 56 | Python | 2026-09-23 | Jev uses one typed Choice question to select each narrative action from the options available at a Detroit: Become Human decision node. |
| jev-libero | ★ 43 | Python | 2026-09-21 | LIBERO robot-control environment where Jev chooses fine-grained actions using task state and physics previews. |
| jev-robot-control | ★ 38 | Python | 2026-09-22 | MuJoCo xArm7 study where Jev chooses movement directions and gripper actions from physical feedback. |
| RoboJEV | ★ 35 | Python | 2026-09-23 | Two-stage JEV control of a Franka Panda in MuJoCo. |
| Jev-as-Policy | ★ 34 | Python | 2026-09-23 | The highly anticipated open-source repository for JEV as Policy enables one-click setup of the simulation environment. Evaluations of Astra + JEV on benchmarks such as RoboTwin will also be released soon. |
| Jev_Star | ★ 33 | Python | 2026-09-24 | StarCraft agent experiment using Jev for fast tactical decisions. |
| clash-jev | ★ 26 | Python | 2026-09-23 | A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state. |
| PlayJev | ★ 25 | JavaScript | 2026-09-23 | 🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels. |
| laya-vs-jev-arena | ★ 25 | JavaScript | 2026-09-23 | Laya (open source, local) vs TypeSafe Jev (API): two AI models race in Snake and fight in a Mortal-Kombat-style arena. Every move is a real model decision. |
| robodiag-harness | ★ 22 | Python | 2026-09-23 | AI diagnostic agent for ROS 2 robots — evidence-based, tool-calling, safety-gated. |
| typesafe-snake | ★ 18 | TypeScript | 2026-09-19 | Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code. |
| jev-reflex-autonomy-lab | ★ 17 | TypeScript | 2026-09-24 | Drone-swarm simulation using Jev for reflex decisions and collision avoidance. |
| tsai-sc | ★ 16 | Python | 2026-09-19 | TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities. |
| mario-jev | ★ 12 | Python | 2026-09-19 | Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions. |
| JevTown | ★ 12 | TypeScript | 2026-09-24 | AI-town simulation where Jev selects character actions and responses. |
| Jev Driving Lab | ★ 10 | JavaScript | 2026-09-19 | Interactive experiments from support routing to a 3D driving simulation: structured sensor state in, typed steer, brake, and overtake decisions out. |
| heist-one | ★ 6 | TypeScript | 2026-09-19 | Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world. |
| OneVOneJev | ★ 5 | TypeScript | 2026-09-19 | 1v1 Jev quickscope arena — Three.js + TypeSafe System One. |
| jev-doom-agent | ★ 4 | TypeScript | 2026-09-19 | A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime. |
| jev-plays-pokemon | ★ 3 | Python | 2026-09-19 | Pokémon Red agent that turns structured game state into Jev decisions and validated moves. |
| jev-askable-arm | ★ 3 | Python | 2026-09-19 | Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives. |
| jev-royal | ★ 2 | TypeScript | 2026-09-20 | Jev-powered game and decision experiment. |
| hundred | ★ 2 | TypeScript | 2026-09-19 | 100 AI NPCs live in a tiny town. Jev chooses the next action; the world writes the story. |
| jev-plays-pokemon-red | ★ 2 | Python | 2026-09-20 | Pokemon Red on PyBoy where Jev chooses legal actions only at branches and each battle turn logs a Brier-scored faint prediction. |
| rubikjev | ★ 1 | TypeScript | 2026-09-19 | Challenge the Jev's intelligence in Rubik Cube puzzles. |
| robo-harness | ★ 1 | TypeScript | 2026-09-19 | SO-101 robot-arm workbench where Jev selects bounded joint actions under a spend budget. |
| jev2048 | ★ 1 | TypeScript | 2026-09-19 | Let Jev (TypeSafeAI) solve 2048. |
| tsai-civ2 | ★ 1 | Python | 2026-09-19 | TypeSafe Jev plays original Civilization II in a browser, with live action probabilities. Experimental full-game harness. |
| jev-gomoku (XieChengYuan) | ★ 1 | JavaScript | 2026-09-19 | 弈瞬：双 Jev 五子棋九宫格输入实验台，逐手查看模型决策，支持真实对局回放与实时对战。 |
| last-exit | ★ 0 | JavaScript | 2026-09-19 | A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts. |
| jev-pong | ★ 0 | TypeScript | 2026-09-19 | Pong benchmark where every ball step is a model decision, comparing Jev with LLMs through Vercel AI Gateway. |
| river-run-typesafe | ★ 0 | Python | 2026-09-19 | River shooter game in Python, inspired by Atari's River Raid, played by a TypeSafe AI pilot. |
| river-oaks | ★ 0 | — | 2026-09-19 | NPCs of River Oaks Houston, Texas using Jev to power NPCs. |
| typesafe-minecraft-demo | ★ 0 | JavaScript | 2026-09-19 | A Minecraft Java player controlled by TypeSafe AI, with live decisions, Canadian flag building, and a side-by-side dashboard. |
| jev.mods | ★ 0 | Java | 2026-09-19 | Minecraft mod where Jev tries to finish the game from scratch without a scripted route. |
| jev-snake | ★ 0 | Python | 2026-09-19 | An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick. |
| jev-play-ping-pong | ★ 0 | JavaScript | 2026-09-19 | Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence. |
| jev-t-rex-runner | ★ 0 | JavaScript | 2026-09-19 | Chrome dino game played by Typesafe AI Jev model. |
| roverlab | ★ 0 | TypeScript | 2026-09-19 | A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI. |
| jev-bfs | ★ 0 | Python | 2026-09-19 | Wikipedia link races with direct Jev ranking and a live terminal display. |
| typesafe-jev-drone-demo | ★ 0 | Python | 2026-09-19 | Three.js drone simulator with a Python backend and live Jev navigation decisions. |
| beatjev | ★ 0 | JavaScript | 2026-09-19 | Browser game: try to beat Jev at spotting a spam message. |
| jev-tetris | ★ 0 | Python | 2026-09-19 | A visual TypeSafe demo where Jev chooses verified Tetris placements. |
| typesafe-3d-chess | ★ 0 | TypeScript | 2026-09-19 | 3D chess powered by TypeSafe AI (Jev). AI vs AI by default, or play either side. Multiple difficulty levels. |
| f1 | ★ 0 | JavaScript | 2026-09-20 | JEV Prix simulation with five AI drivers, procedural circuits, BYOK Jev, and saved replays. |
| jev-atari-lab | ★ 0 | Python | 2026-09-20 | Replayable Atari experiments using Jev structured decisions and value questions. |
| jev-gomoku | ★ 0 | MoonBit | 2026-09-19 | MoonBit client for Jev plus a Jev-vs-Jev gomoku match, with timing logs. |
| naimono-lab | ★ 0 | JavaScript | 2026-09-20 | Family word game for playing with imaginary words, powered by Jev. |
| beat-jev | ★ 0 | TypeScript | 2026-09-20 | Penalty shootout powered by Render Workflows, TypeSafe Jev, and Render Postgres. |
| pdoom-protocol | ★ 0 | TypeScript | 2026-09-19 | USER + JEV: P(DOOM) PROTOCOL — co-op platform shooter where TypeSafe Jev plays alongside you. |
| ps2-ai-agent | ★ 0 | Python | 2026-09-19 | Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One. |
| casse-brique-typesafe | ★ 0 | TypeScript | 2026-09-19 | A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code. |
| cyber-breach-jev | ★ 0 | JavaScript | 2026-09-19 | Cyber-Breach: The Jev Protocol - A tactical cyberpunk arena combat game powered by TypeSafe AI Jev System One decision model. |
| JevArena (rolki-png) | ★ 0 | TypeScript | 2026-09-20 | Two Jev agents duel at Snake through Vercel AI Gateway. |
| pong-jev | ★ 0 | TypeScript | 2026-09-19 | TypeSafe's Jev plays Atari Pong. One typed Choice question per frame, no coordinates sent to the model. |
| jev-games | ★ 0 | Python | 2026-09-19 | Visual Jev lab for multiple games and emulator platforms. |
| snake-jev | ★ 0 | Python | 2026-09-19 | Snake controlled by parallel Jev assessments, with one API call per game tick. |
| terrarium | ★ 0 | JavaScript | 2026-09-19 | A sandbox where a TypeSafe System One model presses the controls of a small creature. Code runs the world. |
| typesafe-chess | ★ 0 | JavaScript | 2026-09-19 | Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision. |
| shady-town | ★ 0 | Ruby | 2026-09-19 | Shady Town: social-deduction party game for the living room TV, moderated by TypeSafe Jev. |
| siege | ★ 0 | TypeScript | 2026-09-19 | 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. |
| Agent-JEV-Tetris | ★ 0 | HTML | 2026-09-19 | Using the new model JEV to play the game tetris. |
| jev-plays-pokemon | ★ 0 | Python | 2026-09-20 | Pokemon-playing experiment where Jev chooses actions. |
| Jev RPS | ★ 0 | JavaScript | 2026-09-23 | Commit-reveal rock-paper-scissors game where Jev scores player behavior, predicts the next move, and chooses its own move before the player acts. |
| The Chess of Life × Jev | ★ 0 | TypeScript | 2026-09-23 | Editable Game of Life ruleset bench where Jev evaluates legal cells and chooses each intervention while code advances and verifies the board. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| jev-leftpad | ★ 82 | JavaScript | 2026-09-23 | Left-pad strings with TypeSafe AI's Jev. For reasons. |
| jev-paint | ★ 50 | JavaScript | 2026-09-23 | Use Jev to make art!. |
| jeview | ★ 39 | JavaScript | 2026-09-23 | An unofficial local visualizer for Jev (TypeSafe): a live view of every call your code makes. Not affiliated with TypeSafe AI. |
| jev-explained | ★ 27 | TypeScript | 2026-09-23 | Jev Explained. |
| Jev-Quantum | ★ 27 | Rust | 2026-09-23 | Random Jev-compatible baseline that emits Noul, Choice, and Score probabilities for mocks, lower-bound comparisons, and router evaluation. |
| is-jeven | ★ 27 | JavaScript | 2026-09-23 | Is it even? Ask Jev. |
| jev-design-test | ★ 22 | TypeScript | 2026-09-23 | Jev shadcn-block generator. |
| killmyidea | ★ 21 | TypeScript | 2026-09-19 | Describe your startup idea. Jev decides: kill it, fix it or ship it. |
| Pi-Jev-Guide | ★ 20 | TypeScript | 2026-09-23 | Jev checks configurable Pi agent rules for risk, output redaction, repeated failures, and missing verification at selected workflow stages. |
| typesafe-playground | ★ 20 | TypeScript | 2026-09-24 | Community playground with editable Jev use cases, games, dilemmas, challenges, and A/B comparisons. |
| Jev | ★ 17 | JavaScript | 2026-09-23 | Six live, side-by-side demos of TypeSafe's Jev — a "System One" model that returns typed, probabilistic decisions (70–500 ms, $0.042 per 1M input tokens, output free) instead of generated text. |
| jev-studio | ★ 15 | Python | 2026-09-23 | if you're experimenting with jev it will be easier from here. |
| typesafe-ai-playground (BunsDev) | ★ 14 | TypeScript | 2026-09-19 | Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI. |
| pix-golpe | ★ 13 | Python | 2026-09-24 | Split-screen demo where Jev detects Pix-payment scams and traces the fraud chain. |
| jevbot | ★ 13 | Python | 2026-09-24 | Discord bot demo that lets users converse with Jev-backed typed behavior. |
| jev-me | ★ 12 | Python | 2026-09-19 | A grill-me style interrogation of your idea, with Jev doing the grilling. |
| Awesome Jev Use Cases (whyashthakker) | ★ 12 | HTML | 2026-09-23 | Fifty runnable visual demos comparing Jev typed decisions with an OpenAI structured-output baseline, with fixtures and explicit methodology limits. |
| Instinct | ★ 6 | TypeScript | 2026-09-19 | Instinct: describe a case in free text and Jev picks the UI from a fixed catalog without generating a line of code or copy. |
| jev-autopilot | ★ 4 | TypeScript | 2026-09-19 | This demo uses Jev from TypeSafe AI to autonomously fly a drone in a random city from point A to point B, avoiding obstacles along the way. A trip costs $0.01. |
| typesafe-ai-playground | ★ 3 | JavaScript | 2026-09-19 | Community TypeSafe AI playground: 110 use cases, games, dilemmas and model challenges, with editable prompts, A/B comparisons and a mobile-friendly UI. |
| clarity-judge | ★ 2 | TypeScript | 2026-09-19 | Multi-axis writing quality checker powered by TypeSafe AI's Jev model. Separate named checks, each with its own verdict and confidence. |
| jev-system-one | ★ 2 | Python | 2026-09-19 | A polished OpenAI + TypeSafe Jev terminal interface for answers with transparent decision reports. |
| Should AI Kill Us All? | ★ 2 | JavaScript | 2026-09-19 | Live verdict page: feeds Jev the day’s Florida Man, odd-news, politics and world headlines and asks all three primitives whether AI should kill us all, refreshed every ten minutes. |
| typesafe-arena | ★ 1 | Rust | 2026-09-19 | A playground for TypeSafeAI's Jev Model. |
| jev-playground (Little-Planet-Labs) | ★ 1 | TypeScript | 2026-09-19 | A small Next.js app for experimenting with TypeSafe AI's Jev model (System One). |
| typesafe-ai-playground (markjaquith) | ★ 1 | Rust | 2026-09-19 | A playground for experiments around Jev, TypeSafe's System One model. |
| toolgate | ★ 1 | TypeScript | 2026-09-19 | Agent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev. |
| guard-jev | ★ 1 | TypeScript | 2026-09-19 | Comment-moderation playground: paste a comment, Jev decides what to do with it. |
| got-jev | ★ 1 | TypeScript | 2026-09-19 | Jev (TypeSafe AI) PoC through Game of Thrones. |
| gpt-vs-jev | ★ 1 | TypeScript | 2026-09-19 | Compare GPT generated language with JEV structured Noul decisions on the same input. |
| harden-jev-decides | ★ 1 | TypeScript | 2026-09-19 | JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board. |
| Jev by Example | ★ 1 | JavaScript | 2026-09-23 | Ten runnable agent-decision examples covering memory, retries, context selection, and handoffs, with offline fixtures and optional live Jev calls. |
| human-compiler | ★ 0 | TypeScript | 2026-09-19 | A compiler for human language. Paste text, get diagnostics. Measured by TypeSafe Jev. |
| jev-demos | ★ 0 | Dart | 2026-09-19 | Demos to test the effectiveness of TypeSafe's "Jev" System One Model. |
| jev-ad-preflight | ★ 0 | — | 2026-09-19 | Typesafe/Jev public X demo. |
| jev-should-i-apply | ★ 0 | — | 2026-09-19 | Typesafe/Jev public X demo. |
| jev-user-jury | ★ 0 | — | 2026-09-19 | Typesafe/Jev public X demo. |
| extremely-specific-council | ★ 0 | TypeScript | 2026-09-19 | Twelve members. Zero qualifications. A playful TypeSafe AI council with animated votes, inspectable decisions, and shareable verdicts. |
| jev-bun1 | ★ 0 | TypeScript | 2026-09-19 | TypeSafe の Jev を TypeScript SDK で使ってみる最初の 1 歩. |
| jev-paper-judge | ★ 0 | TypeScript | 2026-09-19 | Feedback on your paper in seconds. |
| Probably | ★ 0 | TypeScript | 2026-09-19 | Probably: live BTC, ETH, and XRP prices with a shared TypeSafe buy-or-wait demonstration. No trades placed. |
| tiny-jev | ★ 0 | HTML | 2026-09-20 | Small browser experiment for TypeSafe Jev decisions. |
| forma-system1-experiment | ★ 0 | TypeScript | 2026-09-20 | Design experiment where Jev picks a design in about a second and Luna writes only the words. |
| jev-dev | ★ 0 | TypeScript | 2026-09-19 | 同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ（affectus + Vercel AI Gateway）. |
| Jev Gamecast | ★ 0 | TypeScript | 2026-09-19 | Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data. |
| cartshield | ★ 0 | TypeScript | 2026-09-19 | CartShield — SMB checkout fraud disposition via TypeSafe Jev. |
| harnessjudge | ★ 0 | TypeScript | 2026-09-19 | Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev. |
| hiresignal | ★ 0 | TypeScript | 2026-09-19 | HireSignal — resume first-pass fit+interview via TypeSafe Jev. |
| jevplay | ★ 0 | TypeScript | 2026-09-19 | TypeSafe Jev playground — custom Choice/Score/Noul builder with live distributions. |
| lanebreak | ★ 0 | TypeScript | 2026-09-19 | LaneBreak — support ticket priority+routing via TypeSafe Jev. |
| mcpmatch | ★ 0 | TypeScript | 2026-09-19 | Match user goals to MCP catalog (two-stage) via TypeSafe Jev. |
| pulselane | ★ 0 | TypeScript | 2026-09-19 | PulseLane — clinic triage decisions via TypeSafe Jev. |
| spendbrake | ★ 0 | TypeScript | 2026-09-19 | Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev. |
| swarmrouter | ★ 0 | TypeScript | 2026-09-19 | Route tasks to research/code/browser/support/writer agents via TypeSafe Jev. |
| trustgate | ★ 0 | TypeScript | 2026-09-19 | TrustGate — indie media T&S gate via TypeSafe Jev. |
| typesafe-jev-examples | ★ 0 | Python | 2026-09-19 | Worked ticket-triage and reranking examples for Jev, runnable through OpenRouter with sample data and a Makefile. |
| Search-Function-Test | ★ 0 | JavaScript | 2026-09-19 | A test project based on Jev AI, the goal is to build a search function for a blog/article website that has 100s of articles to search from, So the user can actually use the search as chat to question anything and find related answers/articles. |
| jev-board-lab | ★ 0 | JavaScript | 2026-09-19 | Interactive explorer and Jev question workspace for Jev Board datasets. |
| Job Risk Analyzer | ★ 0 | TypeScript | 2026-09-19 | Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience. |
| typesafe-image-diffusion | ★ 0 | HTML | 2026-09-19 | Diffusion-style pixel art out of a classifier: 256 parallel per-pixel Jev questions plus refinement passes. |
| jev-playground (wustep) | ★ 0 | TypeScript | 2026-09-19 | Can a System One model steer music? Jev picks the plan (enums only); code renders sheet, audio and MIDI. |
| jev-calculator | ★ 0 | TypeScript | 2026-09-23 | A probabilistic calculator where Jev emits one answer character at a time from 13 fixed choices and the UI displays every step’s probability distribution. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| NanoJev | ★ 1,074 | Python | 2026-09-19 | Open 0.6B Jev replica with parallel decisions, complete probability distributions, training pipeline, weights, dataset, and live demos. |
| jevlike | ★ 1,008 | Python | 2026-09-19 | Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos. |
| SREGym | ★ 295 | Python | 2026-09-23 | When enabled for Codex runs, Jev reviews diagnostic tests and incident-resolution submissions from the supplied evidence. |
| jev-align | ★ 278 | Python | 2026-09-23 | Build calibrated AI Functions from human feedback using Jev and GEPA. |
| tasksource | ★ 197 | Python | 2026-09-23 | Tasksource recasts hundreds of classification datasets into Jev-compatible typed questions, answers, and procedural training examples. |
| jev-visual | ★ 150 | Python | 2026-09-19 | An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos. |
| decider | ★ 99 | Python | 2026-09-19 | One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B. |
| jev-arena | ★ 96 | JavaScript | 2026-09-23 | Jev model introduction and actual measurement: use Choice / Score / Noul to convert natural language into typed judgments and probabilities for classification, scoring and routing; supports comparison of comment marking, speed and results with models such as DeepSeek, including CSV/Excel import, original speed playback and offline reporting.. |
| jev-eval-agent | ★ 95 | HTML | 2026-09-19 | Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM. |
| reflex | ★ 79 | Python | 2026-09-19 | A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5. |
| WindTunnel | ★ 69 | TypeScript | 2026-09-19 | WebMCP benchmark comparing browser-agent interfaces, with Jev included as one of the evaluated configurations. |
| jevbench | ★ 67 | Python | 2026-09-22 | JevBench v1 - a benchmark for Jev-class typed decision models: smart, cheap, fast, reliable, open. |
| open-jev (daseinlabs) | ★ 56 | Python | 2026-09-19 | One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo. |
| jev-dataops | ★ 45 | Python | 2026-09-23 | An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation. |
| jevmlx | ★ 40 | Python | 2026-09-19 | Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass. |
| typesafe-ai-benchmark | ★ 32 | TypeScript | 2026-09-19 | This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. |
| jev-calibrate | ★ 31 | TypeScript | 2026-09-23 | Calibrate Jev questions against your own labels: tune criteria on labelled examples, confirm on a held-out set, get a verdict per question. Unofficial. |
| Verdict-open-jev | ★ 28 | Python | 2026-09-19 | Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground. |
| mini-jev | ★ 24 | Python | 2026-09-19 | Mini-Jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B — read the option letter's logits instead of generating JSON. Preregistered experiment, results, teaching bench. |
| jev-capability-atlas | ★ 24 | Python | 2026-09-23 | Independent, evidence-based map of when TypeSafe's Jev actually holds up vs. breaks down — real API-call receipts, not a leaderboard. 中文为主的双语 repo。. |
| LitJev | ★ 21 | Python | 2026-09-19 | A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text. |
| jev-on-a-laptop | ★ 18 | Python | 2026-09-19 | Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo. |
| jev-column-race | ★ 16 | JavaScript | 2026-09-19 | Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper. |
| open-alternative-jev | ★ 16 | Python | 2026-09-19 | Open alternative to Jev: typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with benchmarks. |
| openjev (zhihz) | ★ 16 | Python | 2026-09-19 | Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev. |
| jeval | ★ 16 | Python | 2026-09-23 | Measures what your Jev classifier's confidence is really worth, and sets the human hand-off line from what a mistake costs. |
| system-one | ★ 14 | Python | 2026-09-19 | Batched single-token choice inference for open language models, compatible with TypeSafe. |
| jev-rag-benchmark | ★ 14 | Python | 2026-09-23 | Reproducible benchmark for measuring Jev reranking quality, latency, and cost in RAG. |
| system-one-open | ★ 13 | Python | 2026-09-19 | Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal). |
| jevbetter | ★ 12 | Python | 2026-09-19 | A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike. |
| TypeAR | ★ 12 | Python | 2026-09-19 | Type-safe one-decision-per-token decoding engine for autoregressive LLMs, inspired by Jev. |
| jev-benchmarks | ★ 11 | Python | 2026-09-19 | Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks. |
| jev-as-a-judge | ★ 11 | Python | 2026-09-19 | Using Jev as an evaluator. |
| Jev_apps | ★ 11 | Python | 2026-09-19 | 看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons. |
| dejevu | ★ 10 | Python | 2026-09-24 | Browser-agent comparison that benchmarks a one-look open-model policy against the Jev demo. |
| jevify | ★ 9 | Python | 2026-09-19 | An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments. |
| openvons | ★ 9 | Python | 2026-09-19 | 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. |
| jev_stock | ★ 9 | Python | 2026-09-19 | An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data. |
| jevcal | ★ 8 | Python | 2026-09-19 | Stop guessing confidence thresholds: calibrate, threshold, and drift-check typed decision models (TypeSafe Jev) against an LLM teacher. |
| jevfire | ★ 8 | JavaScript | 2026-09-19 | JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks. |
| typesafe-local | ★ 6 | Python | 2026-09-19 | Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon. |
| LegalForecastBench | ★ 5 | Python | 2026-09-19 | LegalForecast-MTD benchmark alpha and official evaluation workflows. |
| jev-korean-benchmark | ★ 5 | Python | 2026-09-19 | Reproducible early-access evaluation of Jev on Korean understanding and medical text, with runtime and cost evidence. |
| jev-lm | ★ 5 | TypeScript | 2026-09-19 | A word-level language model whose output layer is Jev: n-gram drafter, Noul chunk verification, bits-per-token eval. |
| daf-jev | ★ 4 | Python | 2026-09-19 | Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill. |
| jev-little-airways | ★ 4 | HTML | 2026-09-19 | A show-and-tell capability study for Jev, TypeSafe's System One decision model. |
| jev-search-rerank-eval | ★ 4 | Python | 2026-09-19 | Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured. |
| jev-ood-calibration | ★ 4 | Python | 2026-09-22 | Reproducible evaluation of Jev calibration on synthetic support tickets and public classification benchmarks. |
| jev-chat | ★ 3 | Python | 2026-09-19 | A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities. |
| jev-curate | ★ 3 | Rust | 2026-09-19 | High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul). |
| jev-harness | ★ 3 | TypeScript | 2026-09-19 | 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. |
| openjev (DECRUX9812) | ★ 3 | Python | 2026-09-20 | Open, local reimplementation of a Jev-style decision layer for job postings. |
| jev-behavior-study | ★ 3 | Python | 2026-09-19 | Independent Jev 1.13.0 behavior study: report, controlled prompt experiments, raw results, and offline verification. |
| jev-dspy-lab | ★ 3 | Python | 2026-09-22 | Reproducible calibration and selective-risk benchmarks for Jev/TypeSafe decisions in DSPy workflows |
| system-one-gemma | ★ 2 | Python | 2026-09-19 | 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. |
| jev-rerank-bench | ★ 2 | Python | 2026-09-19 | Can a decision model beat dedicated rerankers? TypeSafe Jev vs Cohere Rerank 4 vs ZeroEntropy zerank-2 vs a chat-model baseline: 14 datasets, every raw API response, bootstrap ranges on every gap. |
| jevgpt | ★ 2 | TypeScript | 2026-09-19 | A chatbot built on a model that cannot generate text (TypeSafe AI's Jev, driven autoregressively). |
| calibre | ★ 2 | Python | 2026-09-19 | Calibration and confidence-based routing measured on Banking77: 80.2% accuracy at $0.103 per 500 decisions. |
| jev-for-engineers | ★ 2 | Python | 2026-09-19 | Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies. |
| jev-sec-bench | ★ 2 | Go | 2026-09-19 | Blind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go. |
| jev-research-eval | ★ 2 | HTML | 2026-09-19 | Reproducible Jev Ultrafast research-browser eval harness + field note (QC’d cases, suite runner, report generator). Not investment advice. |
| trade-jev | ★ 2 | Python | 2026-09-19 | Backtest Jev (TypeSafe) as a BUY/SELL/HOLD trader on NQ L10 order-book data. |
| mcts-agent | ★ 2 | Python | 2026-09-19 | Discriminative Monte Carlo Tree Search using TypeSafe Jev System One Primitives and Gemini. |
| jev-gate | ★ 2 | TypeScript | 2026-09-19 | 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. |
| jev-exploration | ★ 2 | Python | 2026-09-19 | Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code. |
| jev-benchmark | ★ 2 | Python | 2026-09-19 | Benchmarks and a playground for TypeSafe's Jev (System One) model: chess, and who-is-the-player-talking-to for speech-to-text game NPCs. |
| jev-does-not-play-dice | ★ 2 | JavaScript | 2026-09-24 | Reproducible experiments on Jev probability calibration, uncertainty, and forecast preservation. |
| jev-phishing-bench | ★ 1 | Python | 2026-09-19 | Jev (TypeSafe) vs Claude Haiku 4.5 on 2 000 phishing emails: accuracy, calibration, latency, cost. Reproducible benchmark. |
| paper-package | ★ 1 | Python | 2026-09-20 | Reproducible Jev research manuscript, evidence, and paper package. |
| decisionbridge | ★ 1 | HTML | 2026-09-19 | A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds. |
| RISC-jeV | ★ 1 | Python | 2026-09-19 | I tortured Jev into being a RISC-V CPU. |
| jev-freeform | ★ 1 | JavaScript | 2026-09-19 | An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice. |
| typed-decisions | ★ 1 | Python | 2026-09-20 | Jev-shaped typed-decision models with measured latency, accuracy, calibration, and training cost. |
| jev-synergy-screening | ★ 1 | Python | 2026-09-19 | Jev (TypeSafe System One) × ASReview SYNERGY abstract screening demo — Choice/Noul vs gold labels. |
| qwen-rlcd | ★ 1 | Python | 2026-09-19 | Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B. |
| kyotsu-ai-bench | ★ 1 | HTML | 2026-09-19 | AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard). |
| jev-agent-failure-benchmark | ★ 1 | Python | 2026-09-19 | Benchmarking Jev (Typesafe.ai) against a strong LLM on the Who&When Pro agent-failure-attribution benchmark (text subset). |
| jev-routing-experiment | ★ 1 | Python | 2026-09-19 | Benchmarking TypeSafe's Jev decision model as a cost-efficient LLM router on RouterArena. |
| openjev-experiments | ★ 1 | Python | 2026-09-19 | Experiments with openjev, an open Jev-style option-logit runner, on local models. |
| padflow-jev-evals | ★ 1 | Python | 2026-09-19 | Typed-decision benchmark from PadFlow (land development SaaS): schemas, anonymized labeled rows, and a runner for confidence-calibrated models like TypeSafe Jev. |
| stuntdouble | ★ 1 | JavaScript | 2026-09-23 | Drop-in /v1/systemone shadow proxy that forwards requests to Jev and local decision models, recording agreement, calibration, latency, cost, and policy-level differences. |
| Typesafe_chess_eval | ★ 0 | Python | 2026-09-19 | An evaluation of typesafe AI chess. As it turns out, the AI isn't doing really well even though chess is not a particularly open-ended game. Still, it's only a prototype and this probably wasn't optimzied for games. |
| jev-spam-eval | ★ 0 | Jupyter Notebook | 2026-09-19 | Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines. |
| jev-shadcn-lint-eval | ★ 0 | JavaScript | 2026-09-19 | A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output. |
| system-one-adapter-rust | ★ 0 | Rust | 2026-09-19 | Rust port of TypeSafe system-one-adapter (LLM-backed system_one evaluations). |
| jev-deferred-crispification | ★ 0 | TeX | 2026-09-19 | Position paper: the Hidden-Markov and fuzzy primitives missing from TypeSafe AI's Jev and System-One decision models. Two lemmas, one principle (Deferred Crispification), one architecture (BSF-S1). |
| jev-alpha-bench | ★ 0 | Go | 2026-09-19 | Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall. |
| jev-headline-bench | ★ 0 | Go | 2026-09-19 | Can Jev pick the winner of a real headline A/B test? 64.5% across 10,984 Upworthy randomized experiments, 74.7% when the difference was decisive. |
| jev-report | ★ 0 | Python | 2026-09-19 | 发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表. |
| jev-playground (hegargarcia) | ★ 0 | TypeScript | 2026-09-19 | Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes. |
| jev-finance-benchmark | ★ 0 | — | 2026-09-19 | Typesafe.ai model jev finance benchmark. |
| jev-anotacao-sentencas | ★ 0 | Python | 2026-09-19 | Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo. |
| jev-vs-luna | ★ 0 | Python | 2026-09-20 | Reproducible review-classification comparison measuring Jev and Luna accuracy, latency, and cost. |
| jev-lab | ★ 0 | TypeScript | 2026-09-19 | TypeScript experiments, evaluations, and latency benchmarks for TypeSafe's Jev model. |
| misereru-slide-jev | ★ 0 | JavaScript | 2026-09-19 | Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides. |
| shade-arena-jev-monitor | ★ 0 | Python | 2026-09-19 | Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro. |
| PocketJev | ★ 0 | Swift | 2026-09-19 | On-device iPhone visual decision tool using MLX and Qwen3-VL direct option logits. |
| jev-jp-address | ★ 0 | TypeScript | 2026-09-19 | Jev (TypeSafe) 性能評価プロジェクト — 日本郵便 KEN_ALL をマスタに、AI SDK 経由の Jev が住所のあいまい一致にどこまで使えるかを検証. |
| jev-trace-classifier | ★ 0 | Python | 2026-09-19 | Application of TypeSafe Jev (noul judgment primitive) on the collusion.wiki corpus: agent vs human page authorship, head-to-head vs local Qwen3.8-Flash-Next. |
| jev-secret-detection | ★ 0 | Python | 2026-09-19 | Measures how well TypeSafe's RLCD-Jev model spots real secret credentials in file snippets. |
| FinancialPredictionJev | ★ 0 | Python | 2026-09-19 | Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good). |
| typesafe-oracles | ★ 0 | JavaScript | 2026-09-19 | Evaluating TypeSafe's System One primitives (Choice/Score/Noul) — where a typed oracle beats an LLM call. |
| jev-pick-and-place-study | ★ 0 | Python | 2026-09-19 | A small reproducible MuJoCo pilot comparing Jev, Claude Haiku, and reactive rules for pick-and-place. |
| thaiexam-jev-charts | ★ 0 | HTML | 2026-09-19 | Charts: TypeSafe Jev evaluated on Thai standardized exams vs 110 other models. |
| jev-calibration-audit | ★ 0 | Python | 2026-09-22 | Independent API-only calibration audit of TypeSafe AI's Jev decision model |
| labs | ★ 0 | Python | 2026-09-22 | Research workspace containing reproducible TypeSafe Jev evaluation and safety-judgment experiments. |
| jev-certify | ★ 0 | Python | 2026-09-22 | Research toolkit applying conformal risk control and prediction-powered inference to certify Jev routing thresholds. |
| jevals-data | ★ 0 | — | 2026-09-22 | Independent benchmark data for TypeSafe's Jev (System One model) vs LLMs: accuracy, calibration, cost. Boards + per-decision logs, CC-BY-4.0 |
| jev-eval | ★ 0 | TypeScript | 2026-09-22 | TypeSafe's Jev vs gpt-5.4-mini and gpt-5.6-luna on four public classification sets: cases, per-item answers, scoring, charts |
| jev-evaluation | ★ 0 | Python | 2026-09-22 | Adversarial Jev evaluation suite with preregistered predictions, request logs, and reproducible experiment artifacts. |
| jev-orderby-bench | ★ 0 | Python | 2026-09-22 | Does ORDER BY over a Jev probability put rows in a defensible order? Independent ranking, calibration and invariant measurements of TypeSafe AI's Jev: passes six pre-registered gates on 360 labeled rows, fails four of six on graded product relevance. |
| Jev no ENEM | ★ 0 | Python | 2026-09-23 | Reproducible evaluation of Jev Choice decisions on 182 valid ENEM 2025 questions, with raw results, accuracy, calibration, and latency analysis. |
| jev-skillbench | ★ 0 | Python | 2026-09-24 | Benchmark of Jev as a malicious agent-skill detector on MalSkillBench with verify-and-escalate evaluation. |
| Project | Stars | Language | Added | Description |
|---|---|---|---|---|
| awesome-jev-tools | ★ 659 | — | 2026-09-23 | Decision-oriented directory of 152 linked Jev tools and practices, with inclusion criteria, caveats, and source attribution. |
| awesome-jev-by-typesafe | ★ 641 | Python | 2026-09-20 | Evidence-backed Jev use cases, patterns, prompts, and starter code. |
| awesome-typesafe-jev | ★ 431 | HTML | 2026-09-22 | Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations. |
| awesome-jev (yibie) | ★ 411 | Python | 2026-09-19 | A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions. |
| jev-skill | ★ 384 | Python | 2026-09-22 | An awesome collection of Jev use cases, workflows, and agent skills. |
| awesome-typesafe | ★ 351 | CSS | 2026-09-19 | Curated list of official resources and community projects for TypeSafe, System One models, and Jev, with a GitHub Pages site. |
| awesome-jev | ★ 217 | — | 2026-09-19 | A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions. |
| awesome-jev (Amal-David) | ★ 176 | Python | 2026-09-24 | Curated Jev demos, projects, SDKs, skills, source links, and an X showcase gallery. |
| awesome-jev (kydlikebtc) | ★ 168 | Python | 2026-09-23 | Machine-readable bilingual Jev example catalog organized by decision pattern, with call-site vetting, compatibility notes, and CI link checks. |
| awesome-jev (fatwang2) | ★ 166 | JavaScript | 2026-09-19 | A source-backed Jev project directory with a reusable Jev-only GitHub review workflow. |
| awesome-jev-gallery | ★ 159 | JavaScript | 2026-09-22 | 🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev. |
| awesome-jev-projects | ★ 131 | JavaScript | 2026-09-19 | Awesome Jev: source-backed open-source ecosystem radar, plain-language project discovery, and automatic GitHub sync. |
| awesome-jev (Promethe-us) | ★ 122 | — | 2026-09-22 | Curated index of Jev projects, integrations, and learning resources. |
| awesome-jev (kraayenjon) | ★ 98 | — | 2026-09-22 | A curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities. |
| awesome-jev (AnotiaWang) | ★ 87 | — | 2026-09-19 | A curated list of awesome Jev / TypeSafe System One applications, libraries, and resources. |
| awesome-jev-use-cases | ★ 80 | — | 2026-09-22 | Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API examples. CC0, sponsored by AY Automate. |
| awesome-jev (hellogumbo) | ★ 76 | JavaScript | 2026-09-20 | Community directory of projects built on Jev and TypeSafe System One. |
| awesome-jev (AppitStudio) | ★ 73 | Python | 2026-09-22 | Curated Jev resources and runnable examples for typed AI decisions. |
| awesome-jev (OmniJev) | ★ 69 | Python | 2026-09-19 | Papers, open reproductions and independent evaluations behind System One models and Jev. |
| awesome-jev-zh | ★ 56 | HTML | 2026-09-22 | Jev / TypeSafe System One 中文精选列表：官方资料、SDK、爆款应用、Agent 工具、开源复现与独立评测，附中文上手指南，每日自动收录 GitHub 热门项目。 |
| awesome-jev (BeatAPI) | ★ 38 | JavaScript | 2026-09-22 | We only curate source-reviewed JEV-related projects with 100+ GitHub stars — integrations, tools, open models, and experiments. Live gallery: beatapi.io/awesome-jev |
| awesome-jev-typesafe | ★ 31 | JavaScript | 2026-09-20 | CC0, awesome-lint-clean Jev list organized by what users can install, with model limitations documented up front. |
| jev-hub | ★ 23 | CSS | 2026-09-22 | JEV HUB · X 上关于 TypeSafe AI「系统一模型」Jev 的长文与演示视频聚合（保留原链与作者）｜ 谁是专家 出品 |
| jev-radar | ★ 19 | — | 2026-09-22 | 📡 全网最全 · The world's most comprehensive tracker of the Jev (TypeSafe AI System One) ecosystem — 220+ documented cases · 108 confidence-graded entries · verified & rescanned every 3 hours · API access guide included |
| awesome-jev-usecases (anandi1989) | ★ 16 | — | 2026-09-22 | Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results |
| jev-cookbook | ★ 16 | JavaScript | 2026-09-22 | Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxonomies, dedupe, PII detection, extraction, search re-ranking and a browser agent. |
| awesome-jev-usecases (aliaihub) | ★ 15 | — | 2026-09-22 | Evidence-backed use cases, patterns, and guidance for building with Jev, TypeSafe AI's System One model. Every claim is labeled and sourced. |
| awesome-jev-live | ★ 13 | Python | 2026-09-22 | Awesome Jev — evidence-graded index of TypeSafe System One: SDKs, MCP tools, agents, apps and open models. 20 languages, rebuilt every 2 hours. |
| jev-directory | ★ 13 | HTML | 2026-09-23 | A browsable directory of what Jev can do — 50 runnable. |
| awesome-jev (tanxarx) | ★ 10 | — | 2026-09-23 | CC0 Jev ecosystem list that resolves original project sources and covers open models, agents, research, applications, and critiques. |
| awesome-jev (MrJev) | ★ 9 | Python | 2026-09-22 | A curated list of projects, integrations, and resources for Jev, TypeSafe AI's System One model. |
| awesome-jev (ckaraca) | ★ 9 | Python | 2026-09-23 | CC0 Jev directory with 98 linked repositories grouped across SDKs, agents, applications, data workflows, open models, and resources. |
| awesome-jev (jtnkminimal) | ★ 3 | Python | 2026-09-22 | A curated projects built with Jev, TypeSafe's System One model. |
| awesome-jev-use-cases (SeeAPI) | ★ 3 | Python | 2026-09-23 | Source-attributed Jev casebook that separates author-reported results from independently verified behavior and documents limits. |
| awesome-jev-verified | ★ 2 | JavaScript | 2026-09-23 | CC0 catalog where code entries link to pinned Jev call sites and claims are labeled against a stated verification method. |
| jevusecases | ★ 1 | TypeScript | 2026-09-20 | Tracks real products and experiments people are shipping with Jev. |
| awesome-jev (sontakey) | ★ 1 | Python | 2026-09-22 | Unofficial list of insanely useful TypeSafe AI Jev / System One projects |
| awesome-jev (rhc98) | ★ 1 | TypeScript | 2026-09-22 | Projects built on Jev (TypeSafe AI's System One model), curated by Jev itself. |
| Jev-Case | ★ 0 | TypeScript | 2026-09-20 | Curated collection of Jev and System One cases from across the web. |
These entries point to a subdirectory or pull request inside a larger repository, so a project-specific Star count would be misleading.
| Project | Stars | Language | Description |
|---|---|---|---|
| agentgateway Jev guardrail example | N/A | — | Jev as an LLM prompt guardrail inside the agentgateway proxy, with tracing and cost tracking. |
| TrainLCD Jev rerank | N/A | — | Pull request adding Jev to station-suggestion reranking in the TrainLCD transit app. |
| Milvus Search with Jev | N/A | Python | Milvus Search with Jev applies Jev to choose among retrieved Milvus results inside the Milvus bootcamp RAG example. |
Jev takes a state plus one or more typed questions and returns structured answers that code can use directly. It does not generate prose.
| Primitive | Use it to | Returns |
|---|---|---|
Choice |
Select one option from a known set | Selected option, probabilities, confidence |
Score |
Place something on an ordered rubric | Score, level probabilities, confidence |
Noul |
Estimate whether a statement is true | Probability from 0 to 1 |
Questions in one request share the same state and are evaluated independently. Complex decisions should be split into narrow questions and composed in ordinary code. Authorization, arithmetic, thresholds, side effects, and fallback behavior should remain in code.
New to Jev? Start with TypeSafe's official Introduction, then continue with Primitives, Confidence, and Patterns.
Most directories tell you that a project uses Jev. This list also records:
- What Jev decides — the exact judgment made inside the project.
- Decision anatomy — state → question → answer → code action.
- Call-site evidence — a link to the implementation when one is public.
- Reproduction status — whether a runbook exists and whether an independent reviewer ran it.
- Metric provenance — official, author-reported, or independently reproduced.
- Freshness — the last human review date and current project status.
- Reusable patterns — the architecture that transfers to other products.
We optimize for inspectability and usefulness, not list size or GitHub stars.
Project — What Jev decides.
Primitive: Choice · Pattern: Typed tool dispatch
Evidence: Call site verified · Maintainer runbook · Metrics author-reported
Verification labels describe separate facts. They are not a score or ranking.
| Label | Meaning |
|---|---|
| Public source | The repository is public and its README describes a concrete Jev workflow. |
| Call site verified | A maintainer located public code that calls Jev and consumes its answer. |
| Demo only | A public demo shows the behavior, but no inspectable call site was found. |
| README claim | The upstream project says it uses Jev; the call site has not been verified. |
| Maintainer runbook | The upstream project provides setup and execution instructions. |
| Reviewer reproduced | An independent reviewer ran the documented workflow and recorded the date. |
| Author-reported metric | The number comes from the project author and has not been independently reproduced. |
| Third-party reproduced | A separate public source repeated the measurement with a documented method. |
| Resource | Purpose |
|---|---|
| TypeSafe AI | Product overview and access. |
| Documentation | Official concepts, API, SDK, patterns, and cookbook pages. |
| API reference | Current request and response contract. |
| Models | Current aliases, versions, pricing, and limits. |
| Workflow evaluations | TypeSafe's published workflow methodology and results. |
A listed project must:
- Be publicly accessible and citable.
- Explicitly use Jev, provide an official Jev resource, or document an independent Jev-style implementation.
- Make a concrete typed decision that can be described in one sentence.
- Link to the strongest available evidence.
- Disclose the submitter's relationship to the project.
A project does not need high GitHub stars. Experimental and early-stage work is welcome when its status and evidence are described accurately.
We exclude generic AI projects that merely resemble Jev, link dumps without a concrete decision, inaccessible sources, copied documentation, and performance claims without a traceable source.
Open a GitHub issue using the project submission template.
Please include:
- Project or repository URL
- Your relationship to the project
- What Jev decides
- Jev call-site URL, when public
- Primitive or primitives used
- Runbook or demo URL
- Metric sources and measurement method
- Optional localized summaries
Submissions without a public call site may enter the review queue and can be added after the implementation is verified.
To edit catalog data, verification metadata, translations, or repository tooling, read CONTRIBUTING.md. It contains the schema, editorial rules, evidence requirements, localization workflow, and validation commands.
Awesome Jev is an independent community resource. It is not affiliated with or endorsed by TypeSafe AI. TypeSafe, Jev, and System One are names or marks of their respective owner.
Schema-valid output is not the same as a correct decision. Evaluate Jev on your own data, set thresholds according to risk, keep consequential actions behind deterministic checks, and provide an appropriate human fallback.
This project is released under the MIT License, unless a file states otherwise. Linked projects retain their own licenses.
Last catalog review: 2026-09-24