Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
A public registry · independent & community-run
Explore the Jev ecosystem.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Watch & learn
Video guides.
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
Experiments.
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.
The directory03 / 03 · Experiments
Find something worth exploring.
Every category, from games and tools to repositories and writeups, traced to a primary source.
Same ideas.
Different paths.
This is the full registry, not just the featured picks. Figures like speed, cost, and stars are maker-reported or captured snapshots, not JevMade measurements.
1613 experiments · showing 961–1020
These charts place Jev's Thai standardized-exam results alongside those of 110 other models.
SOURCE SCREENSHOTEXPAND ↗
A chess evaluation that gives Jev an explicit list of moves and measures how well it chooses.
SOURCE SCREENSHOTEXPAND ↗
typesafe-oracles tests when a typed Jev judgment is more useful than a conventional language-model call.
SOURCE SCREENSHOTEXPAND ↗
from the source
npm run dataset # build the binary corpus -> .sandboxes/episodes.jsonnpm run run # arm A (Jev) + arm B (Haiku via `claude -p`)npm run run:api # arm C (Haiku via the API — the honest baseline)npm run report # accuracy, confidence separation, calibration, costnpm run run:repeat # 5 independent runs of arm A
An introduction to Jev and its unusual restriction: it can decide, but it can't write an answer.
SOURCE SCREENSHOTEXPAND ↗
AIAvatarKit uses Jev to decide whether a speaker has finished after half a second of silence.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Jevで音声対話のターンエンド判定やってみた。発話終了後0.5秒後にJevでターンエンドしたかど...
AINews examines the tradeoff behind Jev: give up free-form answers to get fast decisions with probabilities.
SOURCE SCREENSHOTEXPAND ↗
Search for a flight with Jev choosing browser actions and a small language model filling in text only when needed.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Breaking: Browser Use + Jev = Ultrafast ⚡
Findings flights took 7s and cost only $0.0...
A demo of Jev operating a computer, with a maker-reported speed and cost comparison against Opus 5.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i built computer use using @typesafeai ! it is 155x cheaper than opus 5, ~20x faster, a...
Watch Jev drive ConsoleChaosRacing through its Python API, with every racing decision shown on screen.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Typesafe system_one … Jev ちゃん
運転できるらしいから ConsoleChaosRacing を運転して...
Hamilton Ulmer's DuckDB extension classifies CSV, Parquet, or table rows with Jev from inside SQL queries.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I made a DuckDB extension where you can use @typesafeai 's Jev to do quick classificati...
This Chinese-language roundup introduces early Jev projects for readers who have API access but need ideas for using it.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Jev 这个 waitlist 还是很给力的，昨天申请，今天就能用上。
给已经拿到 API、但还不知道怎...
Check the news article you are reading for political framing, article type, topic and loaded language.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I built Ground Truth, a tiny browser extension that analyzes the news article you’re re...
Developers discuss TypeSafe's claim that software needs an AI model for decisions, not another chatbot.
SOURCE SCREENSHOTEXPAND ↗
Gabriel Anhaia builds a TypeScript ticket router with Jev and unpacks the launch claims.
SOURCE SCREENSHOTEXPAND ↗
An X feed filter that asks Jev to hide posts matching rules you write in plain language.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I built a browser extension with Jev @typesafeai that can hide/collapse posts on X base...
This tool tests social-video hooks against a panel of roughly 100 detailed synthetic personas.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I built near-real-time A/B testing of TikTok/Instagram hooks against a 100 rich persona...
These field notes compare zero-shot Jev with an internal fine-tuned classifier and inspect the confidence scores.
SOURCE SCREENSHOTEXPAND ↗
from the source
“was pumped to get early access to @typesafe_ai's Jev, pointed it at an internal benchma...
This experiment places Jev before each proposed agent action and blocks steps judged unsafe.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Tested TypeSafe’s Jev (no-text, probability-only model) as an AI agent safety monitor....
Víťa Vacek's gomoku harness performs tactical filtering locally, then asks Jev to choose among the surviving moves.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I built a Jev harness to play Gmoku.
How it works - instead of asking to evaluate all...
Daniel White explains Jev and its typed-question API in a 34-second video.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Spent the evening making sense of this, so here's Jev in 34 seconds.
Super excited to...
Niels Mouthaan tests Jev inside a Grammarly-style writing assistant for macOS.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Built a Grammarly-like Mac app with Jev.
Jev is TypeSafe’s first “System One Model”, b...
Steve Krouse introduces TypeSafe Typewriter, a live demo that asks Jev sixteen questions about your text as you type.
SOURCE SCREENSHOTEXPAND ↗
from the source
“typesafe's jev is fun! live demo you can play with: https://t.co/ctnPF0w70r" / X”
This experiment recreates Jev-like decisions with Qwen 3.8 27B running on Cerebras.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b.
Simila...
Mizchi pits two Jev players against each other in gomoku and documents the match in Japanese.
SOURCE SCREENSHOTEXPAND ↗
jev-rabbit reviews pull requests against project rules written in plain English.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i'm cooking jev-rabbit 🐰
a PR review bot that uses Jev with a set of rules you write...
The Neuron explains how Jev's structured, confidence-bearing decisions differ from chatbot responses and where they fit in workflows.
SOURCE SCREENSHOTEXPAND ↗
Anthony Maio makes the case for Jev as a software component, while questioning claims about a model that cannot hallucinate.
SOURCE SCREENSHOTEXPAND ↗
A Jev-powered bot for Kalshi's short-term Bitcoin, Ether and Solana markets.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I built a little JEV bot to trade on @Kalshi across 15m & 1h #BTC, #ETH, and #SOL m...
TypeSafe cofounder Diogo Almeida explains why he spent two years building a model that makes decisions instead of writing text.
SOURCE SCREENSHOTEXPAND ↗
from the source
“After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not l...
Mike Taylor gives Jev his writing to judge and considers what the same approach could do for agent reviews.
SOURCE SCREENSHOTEXPAND ↗
Duncan's router asks Jev which available model best fits a request, then forwards the prompt there.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Built a model router with Jev by @typesafeai.
Jev decides what model fits your reques...
Choose the best AI model or agent for a task from services you already subscribe to.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i used jev from typesafeai to build a model router cli
you give in a task and current...
Agent Journal compares one holistic judge call with twelve Jev-derived features across three classification tasks.
SOURCE SCREENSHOTEXPAND ↗
This OpenCode browser-use preview uses Jev to choose actions quickly from the current page state.
SOURCE SCREENSHOTEXPAND ↗
from the source
“preview of how fast browser use can be
powered by typesafe's jev and opencode's browse...
skillbox uses Jev to select relevant agent skills directly from the user's query.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i added Jev to skillbox so instead of my dumb agents doing 30 turns on finding the righ...
Juan Macías tries Jev on Spanish data-protection documents and shares where it succeeds.
SOURCE SCREENSHOTEXPAND ↗
from the source
“He probado @typesafeai y la verdad es que merece la pena muchísimo. Tiene unos casos de...
Kyle Jeong shows a remote browser taking instructions from Jev through Stagehand.
SOURCE SCREENSHOTEXPAND ↗
from the source
“we built blazing fast computer/browser use with Jev + @Stagehanddev.
this task cost $0...
This demo exposes a WebAssembly build of StarCraft: Brood War through MCP and lets Jev face a Zerg rush.
SOURCE SCREENSHOTEXPAND ↗
from the source
“Jev is impressive, but it still can’t withstand a StarCraft BW Zerg rush
No one can
(...
Fahim Reza ports a small support-ticket classifier from GPT to Jev and tests it on real customer messages.
SOURCE SCREENSHOTEXPAND ↗
from the source
“i built a tiny support ticket classifier with JEV that initially used GPT, then tested...
This game prototype maps a player's free-form tabletop or MMORPG instruction onto a valid in-game action with Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I have to say, this guys from @typesafeai just did probably the best AI model I ever wa...
A technical introduction to building software around Jev's choices, scores and yes-or-no answers.
SOURCE SCREENSHOTEXPAND ↗
The Register looks at TypeSafe's bid to build AI for software rather than conversation, with Doom as a launch demo.
SOURCE SCREENSHOTEXPAND ↗
An introduction to Jev's decision-only API, calibrated probabilities, response times and pricing.
SOURCE SCREENSHOTEXPAND ↗
A Japanese take on Jev's launch that asks how much of the same behavior a conventional language model can reproduce.
SOURCE SCREENSHOTEXPAND ↗
Vercel's fx tests Jev as the reviewer that decides whether automatically generated shell commands are safe to run.
SOURCE SCREENSHOTEXPAND ↗
from the source
“We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a...
Kevin Madura's ViZDoom agent separates navigation and combat into two Jev decision channels.
SOURCE SCREENSHOTEXPAND ↗
from the source
“I feel like the Jev hello world is playing DOOM
... and it works incredibly well with V...
Mohammed Shehu walks through Jev's decision-making API and shows how to call it from Python.
SOURCE SCREENSHOTEXPAND ↗
This Wikipedia demo asks Jev which link best advances a stated destination from each page's candidates.
SOURCE SCREENSHOTEXPAND ↗
from the source
“@drefrajo @Neriousy @typesafeai @opencode Yes. Each page has some link candidates and t...
See how Jev fares in solved poker spots—and how much the wording of the game state changes its play.
SOURCE SCREENSHOTEXPAND ↗
choice
Hero is on the turn and it is hero's turn to act. Which action from `decision.legal_actions` should hero take? · check / all_in
Guide a simulated robot arm toward a hidden object as Jev decides when to search, recenter, approach, or hold.
ACTUAL RECORDING12 SEC ↗
Fight a one-hit karate bout yourself or watch two Jev-controlled opponents spar in the browser.
SOURCE SCREENSHOTEXPAND ↗
Place road hazards in a robotaxi's path and watch Jev choose a lane and speed while safety rules remain in force.
SOURCE SCREENSHOTEXPAND ↗
Add barriers to a simulated drone course and inspect the short flight moves Jev chooses between checkpoints.
SOURCE SCREENSHOTEXPAND ↗
Build a hazardous 3D city drive with pedestrians, fog, red lights, and blocked lanes, then watch Jev respond.
SOURCE SCREENSHOTEXPAND ↗
Swim through a shared aquarium while Jev-controlled fish decide when to flee, hunt, eat or wander.
SOURCE SCREENSHOTEXPAND ↗
This Flappy Bird player sends Jev a prediction of where the bird will be when its answer arrives.
ACTUAL RECORDING12 SEC ↗
Jev and an OpenRouter model race to score on identical Snake boards.
SOURCE SCREENSHOTEXPAND ↗
Direct a simulated disaster-response swarm as Jev checks survivor reports, chooses search sectors, and rates deployment risk.
SOURCE SCREENSHOTEXPAND ↗
Play Black on a 9×9 Go board while Jev takes White, or watch it face a simple local opponent.
SOURCE SCREENSHOTEXPAND ↗
Match Jev against a text model in chess, where Jev selects legal moves and its opponent must produce valid notation.
ACTUAL RECORDING12 SEC ↗
Jev, briefly
A decision model, not a chatbot.
A chat model generates text token by token and hopes you parse it. Jev never generates a word. Your code sends the state of the world plus typed questions; Jev returns every answer in one parallel pass — typed values with calibrated probabilities and a confidence score your code can trust. About 70–500 ms end to end, $0.042 per million input tokens, output free. Trained with what TypeSafe calls Reinforcement Learning for Calibrated Decisions.
choice Pick one of these.
You define the options. Jev returns the chosen option, a probability for every option, and a confidence. The workhorse of routing, agents, and games — the answer space is always legal, so there is nothing to parse and nothing to hallucinate.
score Rate this on a rubric.
You describe ordered levels — say trivial / normal / critical. Jev returns the level, the probability of each, and a confidence. Scores turn fuzzy judgment (“how severe is this log line?”) into a number-free decision your code can branch on.
noul Is this statement true?
You assert a statement; Jev returns the probability that it is true — a noul. Moderation, verification, guardrails, “does this diff actually fix the bug?”: one question, one calibrated probability.
Official material lives at typesafe.ai and docs.typesafe.ai. JevMade is an independent community registry — not affiliated with or endorsed by TypeSafe AI.
Recurring lessons
Patterns that keep showing up.
One decision per tick
Games, drones, trading bots, and browser agents all converge on the same loop: serialize the state, ask one decisive question, act, repeat. Jev’s latency makes the loop feel instant — the model lives inside the control loop, not outside it.
Confidence as a gate
The answer says what; the confidence says whether to act. The most reliable entries threshold on confidence to route edge cases to a slower model or a human — automation with an honest escape hatch.
Shrink the choice space in code
Makers rarely ask Jev to pick from everything. Local tactics prune 225 gomoku moves to ~40; DOM filters turn a page into an element table; code narrows options, Jev judges within them.
Jev judges, LLMs talk
A recurring split: Jev makes every decision cheaply and instantly, and a small LLM is only invoked when a human-facing string must actually be written. Decision and generation are separate budgets.
Made something with Jev?
Send the link — repo, live demo, post, or video — plus a line on what it does and which primitives it uses. Every entry is verified against its primary source before it ships.
Submit your experiment → hello@JevMade.com