Jev is the decision model from TypeSafe AI, and most of the examples on this site run on it. A decision model returns a typed answer, such as a choice, a score or a yes or no with a probability, instead of free text, so the surrounding code can act on it directly. The builds listed here come from GitHub, X, YouTube and blogs. They include Jev Ultrafast from browser-use, which picks each browser action, jarrodwatts/jev-trader, which makes a trade decision on every block, and 1kpapers by Hassan, which sorts research papers into topics. Use the filters to narrow by job, language or source. Read each entry's own notes before you copy it.
638 entries
Showing 1 to 48 of 638
Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.
19k starsFlight search 7.1 s
Attempt to run a Jev-style System One decision model locally on a single RTX 3090. Companion site at openjev.com. The repository was renamed to TheoLeeCJ/SemIf on GitHub, and the old openjev URL now redirects to it.
TheoLeeCJOpenopenjev on github.com4.1k starsJSON vs direct 5.21x slowerPeak throughput 20.03 dec/s
Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.
jarrodwattsOpenjev-trader on github.com2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block
Official agent skill for Claude Code, Codex and other agent environments; installs via claude plugin marketplace add typesafe-ai/skills or npx skills add typesafe-ai/skills. MIT licensed.
Open reimplementation that trains a small model to choose among a changing list of text options, emitting one probability per option in a single forward pass. Ships Doom, chess and Wikispeedia demos.
Independent community collection of use cases, patterns, prompts and starter code for Jev, explicitly not official. It also links sibling collections by the same author and two related projects that report their own cost figures.
MCP server that gives Claude Code, Codex, Amp, OpenCode and other agents ten Jev judgment tools, each returning typed probabilities they can branch on. The author calls it early software.
320 starsPer call 150-500 ms
Walks through the Choice, Score and Noul primitives live in the TypeSafe playground, with speed and cost numbers and their caveats.
CJ from Syntax explains what Jev is, how it works, and walks through several use cases and demos. 17 minutes.
Vercel CTO reports Jev saturated an existing classifier eval that had used Gemini 2.5 Flash Lite and ran about 6x faster. Original post; TypeSafe's quote-tweet is a separate item.
Malte Ubl (@cramforce)OpenRan Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite on x.com220k viewsSpeed vs Gemini 6x faster
Cloudflare's launch post for Clef and Clef-flash, two decision models on Workers AI that accept the Jev request format and open weights under Apache 2.0. It covers the architecture, Cloudflare's own benchmark tables against Jev, Kev and Laya, and a new reinforcement learning service.
Michelle Chen (@michellechen)140k viewsOpenIntroducing Clef: our open-source decision models, and new RL fine-tuning platform on blog.cloudflare.com
Cloudflare's live leaderboard for decision models on the Jev Decision Index suite, with Clef, Clef-flash, Jev, Kev-9B and Laya plotted by score and latency. Cloudflare built and ran it, so treat the ranking as vendor-run.
Cloudflare (@ritakozlov)41k viewsOpenDecision Model Leaderboard on clef-evals.workers-ai-mle.workers.dev
AI News daily roundup leading with the Jev launch, summarising RLCD and TypeSafe's 20-200x speed and 40-400x cost claims. Its recap of reactions notes posters using Jev as a structured classifier, judge and routing policy where text generation is unnecessary.
Argues Jev's speed comes mainly from constrained single-token generation and aggressive prefill, techniques reproducible with existing LLMs, rather than a new architecture. Still treats very fast structured output as a new primitive, while doubting Jev matches frontier models on raw intelligence.
The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.
Claude Code plugin that replaces the compaction summary with Jev decisions. Every tool call and result is scored in one request against the whole conversation, stale ones are dropped or truncated, and everything kept stays verbatim. Also usable as an npm library.
Rust desktop automation that reads apps through the OS accessibility tree instead of pixels. Its jev-desktop skill takes a plain-language goal and has Jev pick one operation and one target element per turn, so the 150-element tree never enters the agent's context.
1.6k starsToken reduction 78-96%
macOS computer-use loop that OCRs the screen, classifies the next action with Jev, then clicks. Author reports roughly $0.0002 per step.
Aaron Levin (awlevin)Opentypesafe-computer-use on github.com935 starsCost/decision $0.0002, 155xLatency 0.13-0.38s
Open source skills that read a morning's news feed with Jev and tell a list of brands which stories to act on. In a demo run it read 384 headlines and matched them to 15 brands in 24.9 seconds for $0.19, against 4 of 384 for $0.77 on Claude Opus 5 over the same feed.
Elvis (@elvissun)Opennewsjack on newsjack.sh851 starsCost $0.19vs Opus/headline ~390x cheaper
Vercel Labs CLI for generating from the terminal. Its evaluate command takes a state plus typed questions and defaults its evaluation model to typesafe-ai/jev on the AI Gateway, with -m jev as the shorthand and an --input flag for text or JSON state.
Agent skills for Hermes, Claude Code and Codex that hand Jev the routing decisions: which model tier to use, which search results to open, which memory passages to read and which hide injected instructions. Ships a dashboard with an on, shadow and off switch and publishes measured latencies per skill.
A macOS menu bar companion with two modes: type a task and Jev picks what to click from a local OmniParser running on CoreML, looping for up to 12 actions, or talk to Gemini Live, which takes one desktop action per turn.
Milind S (@milindlabs)Openmilind-soni/tiptour-macos on github.com662 starsAction limit 12 actions
Staged code-review workflow with a local dashboard, where Jev judges code changes or a whole codebase.
Places Jev as a fast supervisor above slower Codex coding agents. Codex workers do the engineering while Foreman independently assesses whether the work is complete, requirements are met, tests suffice, or human input is needed.
A Minecraft agent that pairs an Astra planner with Jev as the real-time controller, with native run recording, tested routes and run verification.
536 starsFastest run 8m 43s, -40%Decisions used 131 Jev calls
Curated list of official resources and community projects for TypeSafe, System One models and Jev, with a GitHub Pages site. Sections cover docs, SDKs, agent tooling, browser agents, games/robotics, evaluations and showcases.
A browser skill for Codex where Jev handles navigation, clicks, toggles and scrolling while Codex stays in charge of text input, visual judgment and the final check.
447 starsSpeed 5-10x faster
Web search in plain language where Jev chooses sources, time ranges and search terms, then scores each result for relevance, with retrieval through Search1API. Returns links and snippets with visible relevance scores and editable filters, and writes no answers.
A TypeScript classifier that sends each PDF page's text to Jev as a choice over 261 IRS forms and 7 page kinds, with a second call only for five corporate forms and their schedules. Its eval reports 0 wrong pages on 314 filled TaxCalcBench forms at about $0.001 per page, 34x cheaper and 6x faster than the Sonnet pipeline it replaced.
Nakshatra Saxena (@nedwize)Openkyotofin/tax-doc-classifier on github.com419 starsCost per page $0.001vs prior setup 34x cheaper
Agent that plays Super Mario Bros. by feeding structured emulator state to Jev and acting on the returned controller action.
Standalone Android agent for Mobilerun where Jev makes every action decision, with a React studio UI and an Uber booking demo.
droidrunOpenmobile-jev on github.com377 starsUber demo ~21s, 9 actions
Automatic per-turn model routing for Claude Code and OpenAI Codex. Jev sends simple work to the fast model tier and difficult work to the strong tier while preserving each CLI's native tools, sessions, permissions and authentication.
Curated list of Jev / TypeSafe System One applications, libraries and resources.
PostgreSQL extension that lets you filter, rank and classify rows with plain-language conditions, such as WHERE jev(tickets, 'the customer is angry'). Adds jev_prob, jev_choice and jev_score functions that compose with joins, GROUP BY and ORDER BY, with no index or embeddings. Published on PGXN.
realZachiOpenpg-jev on github.com329 stars2k rows, cold ~3.5s, $0.0122k rows, cached ~50ms
MCP server for TypeSafe shipped as a single static Go binary with no Node or Python runtime. Sends usage guidance to the client so the agent writes better questions.
Official drop-in replacement for TypeSafeClient that sends the same typed questions to ordinary LLM APIs, so developers can compare Jev against an LLM on cost, speed and answers.
A CLI from Sutro for building AI functions with Jev: it finds uncertain examples, has you label them, and uses GEPA to improve the function.
Streams speech word by word from the browser's Web Speech API to a Node server, which asks Jev about a dozen typed questions per partial transcript, such as intent, target element and whether the command is complete, and decides whether to act before the sentence finishes.
271 starsDecision latency ~250-350 msCost per call ~$0.0002
Papers, open reproductions and independent evaluations behind System One models and Jev, rather than a tools directory.
270 starsEntries 142Open reproductions 39
Per-call model routing for Codex: Jev answers four choice questions to pick the model tier and thinking depth, so the cheapest sufficient model serves each call. A 7-day replay of 237 real turns measured about 60% savings against always using Astra, under an older policy.
262 starsHistorical replay ~-60% cost
Browser-use tool driving a real headless browser through an MCP server, CLI or library, with Jev choosing the actions. Returns text, markdown, HTML or accessibility-tree output plus traces and screenshots.
256 starsWikipedia nav ~4s, $0.0016
Self-hosted, versioned skills library for AI agents. Serves skills over MCP with scoped clients, and adds optional Jev recommendations for which skill to reach for.
Official TypeScript/JavaScript client published to npm as @typesafe-ai/sdk (v0.6.0), requiring Node.js 20+ and shipping ESM, CommonJS and type declarations.
Unclutter is a WXT browser extension that removes page clutter using Jev decisions, with reusable template rules per site.
Official Python client for the TypeSafe System One API, published to PyPI as typesafe-sdk with sync (TypeSafeClient) and async (AsyncTypeSafeClient) clients.
Local-first MCP plugin giving Claude Code, Codex, Cursor and OpenCode structured code-quality scores (correctness, complexity, modularity, security) while they work. Sends focused diffs to Jev and keeps keys and code local.
Generative engine optimization platform that tracks brand mentions across ChatGPT, Claude, Gemini and Perplexity. Jev runs its chat router, GEO judge and feedback classifier by default, with LLM fallbacks; the NOTRA_JEV_CLASSIFIERS setting turns it off.
Nothing matches those filters
Clear a filter to widen the search, or send us the thing you were looking for.
