Awesome Jev [](https://awesome.re)

September 20, 2026 · View on GitHub

A curated list of applications, libraries, tools, and resources for Jev, TypeSafe's flagship System One model.

English | 简体中文

Send state and typed questions; get structured answers your code can use directly.

Jev launched in early access on 15 September 2026. This list is unofficial and not affiliated with TypeSafe AI. Pull requests are welcome — the ecosystem is young and growing fast.

Contents

What is Jev?

Large language models generate text. Jev does not. It evaluates typed questions against a state and returns values your code can branch on, sort by, and route with — plus calibrated probabilities and confidence.

QuestionGoalReturns
ChoicePick one option from a listchoice, probabilities, confidence
ScoreRate the state on a rubricscore, probabilities, confidence
NoulIs this statement true?noul (0–1)

Questions in one request run in parallel against the same state. Atomic questions, composed in code.

Official

Community

SDKs & Clients

Official first, then community clients. Community packages are not affiliated with TypeSafe unless noted.

  • Python SDK - Official client. pip install typesafe-sdk. Docs: Python SDK.
  • JavaScript / TypeScript SDK - Official client. npm install @typesafe-ai/sdk. Docs: JavaScript SDK.
  • System One adapter (Python) - Official drop-in TypeSafeClient replacement backed by LLM APIs, for comparing Jev against chat models on the same questions. pip install system-one-adapter.
  • Vercel AI SDK provider - @ai-sdk/typesafe-ai plus experimental_evaluate. Use typeSafeAi.evaluationModel('jev-latest') or the Gateway id typesafe-ai/jev.
  • Elixir SDK - Community Hex package typesafe_sdk for system_one and model listing. Docs: HexDocs.
  • Jev (Elixir OTP) - Hex package jev: Jev as a peer GenServer; answers arrive as messages you pattern-match, with network-free tests
  • Ruby SDK - Community Ruby 3.1+ client: Noul / Choice / Score, retries, model listing, thread-safe pooled HTTP. No async client.
  • RubyLLM TypeSafe - TypeSafe provider for RubyLLM 2 with offline model metadata and typed responses.
  • typesafe-ai-rails - Rails integration on top of the official Python SDK: config, usage/cost telemetry, opt-in confidence policies.
  • Rust SDK (typesafe-ai-rs) - Independent async and blocking client for System One.
  • TypeSafe AI for Rust - Another Rust client: async + blocking transports, typed responses, observable retries.
  • typesafe-rs - Latency-focused Rust transport SDK aiming for behavioral parity with the official clients.
  • s1-rs - Rust derive layer for Choice / Score / Noul, typed question sets, confidence gates, and network-free tests.
  • Advocaat - Small TypeScript client with tagged helpers for chances, choices, and scores.
  • Scala / ZIO SDK - Community ZIO client with a small DSL for noul / choice / score.
  • .NET SDK - Community client for typed questions and confidence-scored answers.
  • PHP SDK - Unofficial PHP client: typed DTOs, promises, and exceptions. Used by the Laravel package below.
  • Laravel TypeSafe Jev - Unofficial Laravel 12/13 integration: config, facade, scoped DI, and a recording fake on the PHP SDK.
  • jev-go - Unofficial Go client for typed judgments and calibrated probabilities. go get github.com/Gaurav-Gosain/jev-go.
  • Stumble/jev-go - Unofficial dependency-free Go SDK for TypeSafe direct and Vercel AI Gateway, with typed questions, retries, an interactive CLI, and an installable agent skill
  • jevclient - Unofficial async Python client (pip install jevclient). Typed Noul / Choice / Score helpers, separate from the official typesafe-sdk.
  • LlamaIndex Jev - Unofficial LlamaIndex reranker (JevRerank) and router (JevSingleSelector / JevMultiSelector) on the official Python SDK
  • Swift SDK - Unofficial Swift 6.4 client aligned with the Python SDK 0.6.0 API, including Linux
  • TypeSafe AI Swift SDK - Unofficial dependency-free Swift 6 client for Choice / Score / Noul, with strict concurrency, configurable authentication and retries, and network-free tests

Applications

Open-source products and demos that put Jev in a real loop.

  • Jev Ultrafast - Browser agent from Browser Use. Jev picks an operation and a DOM element in one request; a small LLM writes text only for TYPE_TEXT. Zürich → London on Google Flights in ~7s. Library, local inspector, and measurements included.
  • Jev Web Analyzer - Community project that analyzes a public SaaS landing page as clean Markdown and asks Jev ten bounded Choice questions about first-visit understanding, including the first change to make.
  • JevBrowserExt - Chrome extension (Manifest V3) port of Jev Ultrafast: Jev picks the operation and DOM element in one request, a small text model writes typed values, and it runs in the user's own tabs through OpenRouter, TypeSafe or Cloudflare; includes a 17-task headless-Chromium suite with recorded traces.
  • jev-align (Sutro) - Unofficial active-learning CLI that evaluates CSV, Parquet, and JSONL rows with Jev, asks people to label uncertain and audit samples, and uses GEPA to propose improved definitions
  • Jev for Chrome - Unofficial Chrome extension (Manifest V3) port of Jev Ultrafast: Jev picks the operation and DOM element in one request, a small text model writes typed values, and it runs in the user's own tabs through OpenRouter, TypeSafe or Cloudflare; includes a 17-task headless-Chromium suite with recorded traces.
  • jev-ego - Browser agent on ego lite: one TypeSafe request picks operation + indexed element; agent-facing observe/act/suggest/step CLI
  • jev-browser - Unofficial browser automation: an LLM plans the outcome, Jev decides each click/type on a Playwright snapshot (~300 ms/call). Ships as a library, CLI, and MCP server (npx -y -p jev-browser jev-browser-mcp).
  • Jev Browser (Vlad Terin) - Agent skill + runtime: Codex plans, Jev selects elements, a runner acts and verifies each step.
  • typesafe-computer-use - macOS computer-use loop: OCR the screen, Jev classifies the next action, then click. About $0.0002/step.
  • Yappy - macOS voice agent (closed source, public write-up with measurements). On its hosted plan Jev picks the operation and target control from the window's accessibility table each step; a chat model writes text only for typing, and the full agent takes over when confidence drops. Author-reported: 275–690 ms per decision, $0.003 for five.
  • Mobile Jev - Android agent on Mobilerun: Jev decides each tap. Opens Uber, SFO → Golden Gate, payment screen in ~21s / 9 actions. Live studio, CLI, and traces. No ADB.
  • Unclutter - Chrome / Firefox extension: Jev classifies nonessential page elements; local template rules hide them on later visits.
  • TypeSafe AdBlock - Chrome extension: Jev judges whether a DOM element is an ad and removes it. BYOK, no backend. Author calls it a demo, not a real ad blocker
  • HA-Jev - Unofficial Home Assistant integration: typed questions about entity state become sensors and automation actions, with a target picker that builds the state from the user's own entities and usage, cost, and daily-budget entities alongside the answers
  • Every - Semantic code-search CLI: a yes/no question against every function, ranked by Noul probability.
  • blink - Codebase search: an ensemble of walkers asks Jev which file answers a natural-language query
  • Jev Search - Unofficial web search app using Jev's Choice and Noul judgments to select sources, time ranges, and query candidates, then rank results retrieved through Search1API
  • neo4jev - Neo4j graph navigation: at each node Jev chooses which relationship to follow, with beam search over log-probabilities
  • hono-jev-router - Experimental Hono router: Jev matches an incoming request to a plain-language route description
  • sqlite3-jev - SQLite C extension: jev_noul / jev_choice / jev_score as SQL functions via libcurl
  • jevql - Unofficial psql-shaped CLI and Go/TypeScript/Python SDKs for vanilla Postgres: jev() / jev_prob / jev_choice / jev_score in plain SQL with no extension, the SQL runs on the server and Jev judges the surviving rows in batches
  • jev-resilience - Unofficial Spring WebFlux starter: a semantic circuit breaker that uses Jev to catch silent HTTP 200 failures
  • tripwire - Unofficial AI SDK middleware and OpenAI-compatible proxy: seven Jev checks on every LLM response in ~100 ms, confidence-gated
  • ProgressGate - Detects semantic stagnation in agent loops: Jev judges the trajectory; code returns CONTINUE / WARN / REPLAN / HALT
  • jev-harness - Unofficial production layer around Jev: policy, confidence gate, shadow mode, recipes, and an eval CLI
  • jev-tree - Recursive Choice over a taxonomy so catalogs larger than Jev's 255-option cap still fit
  • jev-shell-history - Fish-style zsh autosuggestions: Jev ranks recent history as you type
  • Supercov - Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first
  • Jev Review - Staged code-review workflow and local dashboard driven by focused Jev calls.
  • Foreman - Software-factory loop: Codex implements; Jev independently judges completeness, tests, and whether a human is needed.
  • Jev Drone - MuJoCo quadrotor: control and safety stay in code; Jev handles slower tactical judgments.
  • Jev Plays StarCraft - Structured-state harness for the original StarCraft shareware campaign, with verified run and probability traces.
  • Jev × Civilization II - Original Civ II in a browser; Jev chooses empire, city, research, and unit actions. Experimental; no verified win yet
  • Jev Trade - Live Hyperliquid desk: each tick Jev answers Choice questions for long/short, open/close/hold, and leverage; code places or pulls the quote. Dry-run by default; a live key sends real orders. Demo: jev-trade.com.
  • Jev Trader - One buy/sell decision per Monad block on Kuru's MON-USDC book. Live demo: jev-trader.vercel.app.
  • Human Compiler - Paste corporate prose; Jev scores passive-aggression, urgency, and information density, then code emits rustc-style diagnostics. Live: human-compiler.asfarlab.fun.
  • JEVMETER - Live Jev meter on any video: every sentence scored, rendered as a 16:9 edit. Demo: Chetaslua.
  • jev-audio-beeper - Low-latency audio insult detector: Jev decides, ffmpeg beeps in ~466 ms without rewriting the rest of the track.
  • jev-askable-arm - Zero-shot English goals on a simulated Franka. Jev chains hardcoded primitives.
  • jev-codex-router - Per-turn Codex routing: Jev picks model, thinking depth, and speed mode.
  • jev-router - Per-turn routing for Claude Code and Codex: Jev sends simple work to the fast tier and hard work to the strong tier. npm i -g jev-router.
  • jev-secret-detection - Secret-in-diff detector with repeatable Jev verdicts.
  • commit-miner - Rust CLI that classifies commit diffs with Jev: bug fixes, security/CWEs, and change types. HTML/CSV reports.
  • jev-eval-agent - Public eval harness for early Jev tests.
  • Jev Logs - OpenTelemetry log triage: Jev scores diagnostic value and priority before an expensive LLM looks at the archive.
  • Smart home assistant demo - Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers, LLM only for splits and chit-chat. Source is slated for GitHub at release.
  • jev.nvim - Neovim plugin that splits the buffer into functions with Treesitter, scores each against a plain-language question with Jev, and ranks answers by probability in the quickfix window.
  • jev-skip - Browser extension that reads the YouTube caption track and paints a per-segment sponsor probability on the seek bar before the intro ends, with no crowd database, reporting catching 77% of SponsorBlock's sponsor seconds across 23 videos at $0.0008 a video.

Demos & Games

Toys, live sites, and realtime agents. Most shipped in the first 48 hours after launch.

  • Yes / No - Free no-signup Noul demo. Ask a question, get yes / no / maybe, with web search when needed.
  • Jev Tetris - Jev picks rotation and column from holes, stack height, and bumpiness.
  • Jev Pac-Man - Maze as JSON; Jev picks the turn at each junction in realtime.
  • typesafe-mario - Super Mario Bros. from structured emulator state.
  • jev-doom-agent - Browser-native Doom with Chocolate Doom WASM, spatial state, and live decision telemetry.
  • jev-gomoku - MoonBit client plus Jev-vs-Jev gomoku; write-up: jev 同士に五目並べで対戦させた.
  • jev-t-rex-runner - Chrome dinosaur game played by Jev.
  • snake-jev - Snake: hundreds of typed direction decisions per run.
  • Jev Guard - Comment-moderation playground.
  • Hollow Creek - Village NPCs that judge you each tick (what to do, how they feel) instead of chatting.
  • Jev mood demo - Talk nicely or nastily over time; structured state tracks mood.
  • Jev Room - One sentence → six room settings. Jev chooses, the app renders.
  • TypeSafe Typewriter - Live Val Town demo: 16 typed judgments update as you type. Launch post: Steve Krouse.
  • got-jev - Game of Thrones roleplay as Jon Snow. A story model writes the scene; Jev answers where he is, how much danger, and what should play under it.
  • Little Airways - Toy archipelago ATC: Jev judges divert / emergency / who lands first from each plane's local state, ~150 ms.
  • jev-plays-pokemon-red - Pokemon Red on PyBoy where deterministic code owns the route and arithmetic and Jev picks only at branches, with every battle turn's faint prediction scored by Brier against the emulator's RAM state.
  • jev-canvas - Draw on a tldraw canvas with your voice and a webcam-tracked finger; Jev decides action, target and place on every partial transcript. English and Ukrainian commands.
  • sudoku-vs-jev - Terminal Sudoku where Python owns the rules and Jev picks one move per turn, steady while forced moves exist and shaky once it has to guess.
  • JevsBistro - Deterministic 3D restaurant sim that replays the same dinner service to compare rule-based, camera-assisted, and Jev-planned waiters, logging each decision's state, options, confidence, and latency.

Agent Tools

Tools that expose Jev to coding agents and MCP clients.

  • TypeSafe agent skill - Official skill: primitives, patterns, and how to structure evaluations. Claude Code: claude plugin marketplace add typesafe-ai/skills then claude plugin install typesafe@typesafe-ai. Other agents: npx skills add typesafe-ai/skills --skill typesafe-ai.
  • fast-jev-compaction - Claude Code plugin and npm library: Jev scores tool calls and drops stale ones instead of summarizing context
  • SkillRanker - Rust CLI: Jev ranks which agent skill fits the next step from live session context, with Claude Code hooks
  • Jevbridge - Unofficial ACP/MCP adapter: typed Jev decisions and computer use beside Codex, Claude, Grok, and OpenCode
  • eve - Vercel's agent framework. Experimental autoModel defaults to Gateway typesafe-ai/jev to pick a language model from an allowlist.
  • jev-mcp - Node MCP wrapping three cookbook patterns: jev_verify (citation check), jev_screen (prompt-injection / guardrails), jev_find (semantic ranking without embeddings). npx -y github:jkudish/jev-mcp.
  • Jev MCP (Python) - Python MCP server: classify, score, check, match, and screen tools.
  • Jev Review MCP - Local-first MCP: Claude Code, Codex, Cursor, and OpenCode get structured quality review from Jev while they write. Not the same project as Jev Review above.
  • typesafe-mcp - Go CLI and single-binary MCP for Claude Desktop, Claude Code, and Codex.
  • pi-typesafe - Pi extension: one consented, key-managed TypeSafe client, batched typesafe_evaluate, offline-testable transport.
  • pi-jev - Pi extension with a shadow-mode tool-call gate, output judge, and typed jev_ask.
  • pi-warden - Pi guardrails on pi-typesafe: held tool results instead of a dialog; write checks against a project rules file.
  • pi-jev-auto-mode - Pi auto mode: Jev semantically approves bash / write / edit, and fails closed when it cannot decide.
  • Bicameral - Pi coding harness: LLM writes, Jev supplies typed reflexes for policy, loop detection, and review. Explicitly not a sandbox.
  • jev-pref - Turn AGENTS.md preferences into a Jev-powered AI linter: project-specific semantic review rules in jev-pref.json, checked against hunks, staged files, or PRs, with findings fed back to your coding agent. npx jev-pref setup.
  • ask-jev-skill - Hermes skill: ask Jev whenever the agent needs a bounded decision.
  • jev-system-architect - Skill that hunts for brittle semantic logic and turns it into Choice / Score / Noul boundaries.
  • augustus - Design-judgment skill: maps Choice/Score/Noul onto classical methods (decision theory, rerank, routing) with a composition algebra, question-design diagnosis, and falsifying validation gates
  • jev-browser MCP - Same project as above; MCP tools browser_do, browser_check, browser_choose so an agent can drive the page without reading full snapshots.
  • jev-ego - Same project; observe/act/suggest/step on a live ego lite TaskSpace
  • jev-axi - CLI plus Claude Code and Codex hooks: Jev scores each shell command for hazards before it runs and screens fetched text for prompt injection, with routine commands decided locally so nothing is sent
  • jev-belay - Claude Code Stop hook that checks the transcript for evidence before trusting a "done" claim, spending one four-question Jev call only when files changed with no passing check since, and failing open on every error path.
  • jev-commit - Pre-commit hook where one Jev call judges whether the commit message matches the staged diff, flags debug leftovers and unmentioned work, and blocks only when it detects a credential.
  • jev-use - Claude Code, Codex and pi plugin: Jev answers the batched typed questions an agent loop needs, and a typed escalation contract hands writing and low-confidence steps back to the LLM

Research & Open Models

Independent work inspired by Jev's interface. These are not TypeSafe models.

  • jevlike - Train a small one-pass scorer that maps context + N text options to a probability per option. Includes Doom / chess vision demos and a Wikispeedia next-click example. Explicitly not a reproduction of TypeSafe's architecture or RLCD.
  • openjev - Can we run something Jev-like on a home RTX 3090? Reads option logits instead of generating text. Not TypeSafe's model.
  • PocketJev - On-device iPhone visual decisions with MLX + Qwen3-VL option logits. Camera + 3-choice, no text generation, ~1s, no photo saved.
  • jev-visual - Educational Jev-like visual inference on Apple Silicon: shared multimodal context, candidate scoring, sorting-factory / Breakout / gesture demos. Not TypeSafe's model
  • jevmlx - Jev-style parallel constrained decisions for any MLX model on Apple Silicon: schema-valid JSON in one forward pass
  • JEVfire - Jev-inspired parallel decisions for CUDA LLMs via vLLM, with a browser Mario demo (~71 ms/action locally)
  • decider - Qwen3.5-2B fine-tune that emits typed decisions with calibrated probabilities in one pass. Unofficial; not TypeSafe's architecture.
  • LitJev - 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. Unofficial; not TypeSafe's model.
  • PlayJev - Qwen3.5-0.8B-Base fine-tuned to play ten browser games from 448 px frames: one forward pass per move, a probability over the game's option list read off the option letters, no generated text. Open weights and a demo of all ten in the browser. Unofficial; not TypeSafe's model.
  • typesafe-ai-benchmark - Side-by-side of Jev vs Qwen 3.8 27B on Cerebras for the same System One questions. Video: Shannon.
  • Jev Rerank Bench - Reranking comparison with raw provider responses, scoring code, uncertainty intervals, and documented limits.
  • Jev Spam Eval - Exploratory zero-shot spam study vs trained TF-IDF baselines, with post-hoc-tuning caveats.
  • Jev Phishing Bench - 2,000 emails: Jev vs Claude Haiku 4.5 on click-or-not, with calibration, latency, and cost. Haiku wins accuracy here.
  • jev-agent-failure-benchmark - Who&When Pro (injected agent failures): Jev vs a strong LLM on who / which step / error category.
  • jev-sec-bench - Blind prompt-injection and vulnerable-code detection benches on public corpora, built on jev-go.
  • Jev DSPy Lab - Unofficial DSPy companion that records and replays TypeSafe calls while measuring calibration, selective risk, confidence-gated abstention, latency, tokens, and modeled cost.
  • jevcal - Unofficial CLI that fits a per-question confidence threshold to a target accuracy on your own labeled data, verifies it on a held-out split, shows how much traffic still needs an LLM fallback, and fails CI when a Jev update breaks the locked thresholds
  • ASSAY-001 - Independent pre-registered check of Jev calibration and type safety on Banking77 / CLINC150. Split verdict, full logs. Write-up: donttrustme.ai
  • Jev search rerank eval - 9,831 labelled pairs: Jev rerank vs BM25 / bge-m3, with judge-circularity measured. Fusion wins; Jev alone does not beat embeddings
  • Smoking-history extraction benchmark - 1,000 synthetic notes: Jev vs OpenAI structured outputs on accuracy, cost, and latency

Cookbooks

Official, copy-pasteable workflows. Full index: console cookbooks and docs index.

Patterns

Architectural recipes from the docs.

See also: How to build with TypeSafe, use-case map, confidence.

Articles

Independent measurements, experiments, and news. Official posts live under Official.

  • MrJev/awesome-jev - Selective list behind a 10-star bar, with hands-on reviews at mrjev.com recording what each tool sends and where.
  • typesafe-ai on PyPI - Community redirect shim. The real package is typesafe-sdk; this name was registered to block slopsquatting. Not affiliated with TypeSafe.

Contribute

See CONTRIBUTING.md. In short: open a pull request that adds a project with a link and a one-line description. Useful, interesting, and actually built on Jev (or clearly inspired by its interface).

License

CC0 1.0 — this list is dedicated to the public domain.