Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Learn, build, and play with Jev — from deep technical guides to creative experiments.
Read & learn
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
Watch & learn
See an idea take shape. Tutorials, demos, and deep dives, organized by topic and credited to their creators.
Make & explore
See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

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.
379 experiments · showing 181–240
Build custom Choice, Score and Noul questions and watch their probability distributions update live.
A CLI and API assess an occupation's exposure to AI layoffs, future path, human accountability and resilience.
LaneBreak assigns support tickets a priority and destination.
MCPMatch uses a two-stage process to pair a user's goal with tools from an MCP catalog.
Live Bitcoin, Ether and XRP prices feed a Jev demonstration that chooses between buying and waiting.
A clinic-triage demo that asks Jev which cases need attention.
A conversational search prototype helps readers find relevant material among hundreds of blog posts and articles.
Spendbrake watches an agent's budget and chooses whether to continue, downgrade the model or stop.
Swarmrouter sends each task to a research, coding, browser, support or writing agent.
TrustGate screens trust-and-safety decisions for independent media publishers.
TypeSafe Typewriter reruns sixteen judgments about a piece of text after every keystroke.
A classifier creates pixel art by answering 256 pixel questions in parallel and refining the result over several passes.
Ask a question and receive Yes, No or Maybe, with live web search available for current facts.
Watch Jev drive ConsoleChaosRacing through its Python API, with every racing decision shown on screen.
Víťa Vacek's gomoku harness performs tactical filtering locally, then asks Jev to choose among the surviving moves.
This demo exposes a WebAssembly build of StarCraft: Brood War through MCP and lets Jev face a Zerg rush.
This game prototype maps a player's free-form tabletop or MMORPG instruction onto a valid in-game action with Jev.
Kevin Madura's ViZDoom agent separates navigation and combat into two Jev decision channels.
This Wikipedia demo asks Jev which link best advances a stated destination from each page's candidates.
Guide a simulated robot arm toward a hidden object as Jev decides when to search, recenter, approach, or hold.
Fight a one-hit karate bout yourself or watch two Jev-controlled opponents spar in the browser.
Place road hazards in a robotaxi's path and watch Jev choose a lane and speed while safety rules remain in force.
Add barriers to a simulated drone course and inspect the short flight moves Jev chooses between checkpoints.
Build a hazardous 3D city drive with pedestrians, fog, red lights, and blocked lanes, then watch Jev respond.
Swim through a shared aquarium while Jev-controlled fish decide when to flee, hunt, eat or wander.
This Flappy Bird player sends Jev a prediction of where the bird will be when its answer arrives.
Direct a simulated disaster-response swarm as Jev checks survivor reports, chooses search sectors, and rates deployment risk.
Play Black on a 9×9 Go board while Jev takes White, or watch it face a simple local opponent.
Fly the same seeded cargo-drone corridor as a human pilot, a geometric baseline, and Jev.
A browser bird asks Jev whether to flap once, twice, or not at all as each pipe approaches.
Who would win in a fight? Jev judges an animal tournament on land, in water and in the air.
Play a complete browser chess game against Jev and inspect how it distributes confidence across legal moves.
Describe a portrait one letter at a time and watch Jev reshape a suspect lineup—or question a hidden suspect directly.
Watch Jev steer Snake toward food and power-ups while live meters reveal its intent, safety calls, and trap risk.
Play chess against Jev in pygame, or give it both colours and watch a fully automated match.
Play animated chess against configurable Jev strategies, or pause a Jev-versus-Jev match to inspect a decision.
Send a Three.js spaceship on mining and combat missions while Jev selects targets and gauges danger.
Build a persistent 3D town where Jev can shape resident intentions and broad regional policies.
Watch Jev decide whether Snake should turn left, turn right or keep going.
Solve four-part harmony quizzes, then switch to an endless Rhodes piano whose chords are chosen by Jev.
Scroll X as Jev washes each tweet in a watercolor gradient mixed from thirteen palette colors.
A Snake experiment where Jev suggests moves and a safety check can reject them.
Read or autoplay an illustrated gamebook while Jev chooses among the exploration and combat actions currently available.
Watch live or recorded Jev turns across six browser games, including 2048, Snake, and a raycaster shooter.
Watch up to six personality-driven fighters battle, or enter the arena yourself while Jev controls the other combatants.
Jev helps the residents of a small simulated town decide how to spend their days.
Play Xiangqi against Jev and inspect score bars for its strongest legal moves.
A wraparound snake keeps moving on a fixed clock while Jev periodically chooses to continue or turn.
A text adventure that uses Jev to understand commands you write in your own words.
Challenge Jev at 15×15 Gomoku after a tactical search narrows each turn to four promising moves.
Uncover a hidden word with yes-or-no questions while Jev judges ambiguity and attempted cheating.
Watch Jev navigate FrozenLake with a full map or tackle MiniGrid DoorKey through a limited field of view.
Analyze a message's tone or watch Jev choose its way through a generated 15-by-15 maze.
Watch a browser snake follow short, code-generated routes selected by Jev.
A browser Snake game autoplays while Jev chooses each direction from the moves currently available.
Choose a musical scale and hear a browser synth continue the melody with Jev-selected notes and rests.
Play browser tic-tac-toe against Jev, which chooses its turn from the squares still available.
Search and browse a persistent fictional web whose generated pages are assembled under Jev’s direction.
Let Jev choose one legal land action for an OpenFront bot based on the current border situation.
Watch Jev play both sides of chess, then replay each move’s probability distribution beside Stockfish’s grade.
Jev, briefly
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.
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.
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.
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
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.
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.
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.
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.
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