Read & learn
Written guides.
Understand Jev, one idea at a time. Walkthroughs, recipes, and writeups — our notes first, the original next.
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.Experiments
Every category, from games and tools to repositories and writeups, traced to a primary source.
Real-time research powered by
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.
405 experiments · showing 361–405
Compare open-source Jev alternatives in Beam's playground, then take the request into your own application.
SOURCE SCREENSHOTEXPAND ↗
Play Pong against Jev and watch its movement, shot selection, probabilities, and fallbacks in a live decision monitor.
SOURCE SCREENSHOTEXPAND ↗
A JevNPC trial asks whether a threatened Minecraft villager should ignore danger or call the guards.
SOURCE SCREENSHOTEXPAND ↗
from the source
criteria.put("IGNORE", "Start no new action...");criteria.put("CALL_GUARD", "Request help from the listed eligible guards...");String instructions = "Which available response should this NPC take now to stay safe?";
Triage messages, classify CSV rows, interpret voice commands, or let Jev steer Snake from a Java web playground.
SOURCE SCREENSHOTEXPAND ↗
from the source
var state = game.state(semantics);var decision = model.decide(state, Game.QUESTIONS);var choice = Answer.get(answers, Game.MOVE, Answer.Choice.class);var move = Direction.valueOf(choice.choice().toUpperCase(Locale.ROOT));return new Turn(game.step(move, random), ...);
Watch Jev choose a legal Tetris placement from a heuristic shortlist, then play the selected move.
SOURCE SCREENSHOTEXPAND ↗
from the source
client.choose(QUESTION_ID, JevPromptSupport.state(snapshot), INSTRUCTIONS, criteria);return selected.move();
AutoNomousBot shows Jev a Minecraft world snapshot, lets it choose from available actions, then performs the selection.
SOURCE SCREENSHOTEXPAND ↗
from the source
jevClient.askChoice(state, question, fallbackId)actionExecutor.execute(client, chosen);
This canary-rollout demo keeps the state machine in charge: it decides which transitions exist, Jev weighs evidence only at model-eligible branches, and the captured run holds at 5% traffic before promoting as evidence firms up.
SOURCE SCREENSHOTEXPAND ↗
A demo incident-response agent that puts the loop in Temporal and the judgment in Jev: typed next-action choices, a severity score, and safety probabilities drive durable activities, with retries, worker crashes, and a human-approval signal all surviving restarts.
SOURCE SCREENSHOTEXPAND ↗
One Minecraft body with a split brain: GPT-6 Astra plans, and Jev answers action, safety, and urgency in a single parallel call.
SOURCE SCREENSHOTEXPAND ↗
Freedoom, ViZDoom, and a decision model that has never held a shotgun: the dashboard plays Jev's run back with a dollar figure next to every call.
SOURCE SCREENSHOTEXPAND ↗
Solo Tetris where Jev picks both the strategy for the next few pieces and a board-health score for the current stack.
SOURCE SCREENSHOTEXPAND ↗
A Factorio agent that runs on a clean division of labor: Jev picks what to do, ordinary code works out how, and nothing runs unvalidated.
SOURCE SCREENSHOTEXPAND ↗
Server-side snake where every move is one typed choice question, with the board, snake, and food as the state.
SOURCE SCREENSHOTEXPAND ↗
A Minecraft bot asks Jev what to do next all the way to a diamond — every tree punch, craft, and tunnel is one typed choice.
SOURCE SCREENSHOTEXPAND ↗
Play chess against Jev, Stockfish, or both at once — Stockfish narrows the position to five candidate moves and Jev picks whichever suits its current personality.
SOURCE SCREENSHOTEXPAND ↗
Two small games, one decision-maker. In Snake, Jev picks a direction each tick from options the server has already checked for traps; in Sudoku, it fills in the most constrained cell one digit at a time.
SOURCE SCREENSHOTEXPAND ↗
One laptop hosts the game and everyone else joins from their phone. Each player writes two truths and a lie; Jev guesses the lie, then the real answers come out and everyone sees whether the humans or the model read the room better.
SOURCE SCREENSHOTEXPAND ↗
Jev calls every swipe in this 2048 clone, and a direction only counts if the four probabilities add up to a clean one.
SOURCE SCREENSHOTEXPAND ↗
A Next.js chess app whose API route forwards each position to the System One endpoint as one typed choice question per move.
SOURCE SCREENSHOTEXPAND ↗
No-limit Texas Hold'em where the CPU players think with Jev — bring your own API key and watch the table reason.
SOURCE SCREENSHOTEXPAND ↗
Watch the Jev decision model play 2048 live in your terminal, with average latency and illegal-move corrections on screen.
SOURCE SCREENSHOTEXPAND ↗
Jev plays pong. Each tick it gets the ball and paddle positions and answers one of three moves: up, down, or stay — nothing else can come back.
SOURCE SCREENSHOTEXPAND ↗
Converts the branching story of Detroit: Become Human into decision trees, then lets any model play the game from start to finish.
SOURCE SCREENSHOTEXPAND ↗
A Unity RTS experiment, built for a YouTube video, where unit decisions, route choices, and enemy strategy all come from the Jev API.
SOURCE SCREENSHOTEXPAND ↗
A shared canvas the size of a million emoji, and a machine that paints alongside you.
SOURCE SCREENSHOTEXPAND ↗
Browser chess where code works out every legal move's facts and Jev picks one per turn as a single typed choice.
SOURCE SCREENSHOTEXPAND ↗
A Tetris the model plays by reading. Every possible landing is described in a sentence, Jev picks one, and the board glows with the probabilities before the piece drops.
SOURCE SCREENSHOTEXPAND ↗
A cinematic Earth-to-lunar-orbit flight where Jev picks each navigation action and the page shows its probabilities as the trajectory unfolds.
SOURCE SCREENSHOTEXPAND ↗
Jev plays the moves in Slay the Spire 2 while a Claude Code strategist plans the route, card rewards and boss fights.
SOURCE SCREENSHOTEXPAND ↗
A stealth-game prototype asks Jev for guard actions and squad tactics while ordinary game code handles movement, sight and combat.
SOURCE SCREENSHOTEXPAND ↗
Francesc Sans's turn-based Pac-Man asks Jev at junctions and near ghosts, while ordinary corridor moves stay in code.
SOURCE SCREENSHOTEXPAND ↗
Follow Jev choosing chess moves against human-like Maia-3 opponents, with its alternatives and probabilities displayed on the board.
SOURCE SCREENSHOTEXPAND ↗
Play a Wordle clone or watch a Jev bot choose guesses from a shortlist that code has checked against the clues.
SOURCE SCREENSHOTEXPAND ↗
Write household lighting rules in ordinary English, then replay events to see how Jev applies them to simulated lights and blinds.
SOURCE SCREENSHOTEXPAND ↗
Watch saved city-building runs where Jev picks actions and locations from menus prepared by a scripted Micropolis strategy.
SOURCE SCREENSHOTEXPAND ↗
Build a mine-cart track and write a clue that guides the cart through Jev-controlled switches across five levels.
SOURCE SCREENSHOTEXPAND ↗
Jev chooses legal moves in NetHack 5.0 while ordinary code reads the terminal screen and presses the keys.
SOURCE SCREENSHOTEXPAND ↗
A creator showcase features a 2D fighting game where two Jev-powered agents select moves and adapt strategies in real time.
SOURCE SCREENSHOTEXPAND ↗
A burger-kitchen game with Chinese-language order parsing and a Jev-controlled cooking loop.
SOURCE SCREENSHOTEXPAND ↗
A browser duel in the style of Counter-Strike 1.6: you push down a corridor against an AWP sniper whose peeks, counter-strafes and shots are picked by Jev.
SOURCE SCREENSHOTEXPAND ↗
SpellSpeak Tone reads each line of game dialogue and tags how the speaker feels, how the line lands on everyone present, and whether it asks, answers or dodges.
SOURCE SCREENSHOTEXPAND ↗
@blastore turns a survey-answer contest into a multiplayer TV game show on Spawn, with an AI host judging the answers.
SOURCE SCREENSHOTEXPAND ↗
Sebastian Sochacki's voice-agent security walkthrough pits a £1,000 refund request against an order with only £500 left to refund.
SOURCE SCREENSHOTEXPAND ↗
Play a Jev opponent in eR33t's browser chess arena, or explore its bot matchups, tactics and game replays.
SOURCE SCREENSHOTEXPAND ↗
jev-content-mod uses Jev's harm, category and clarity judgments to feed code rules that approve a post, hide it for review or remove it.
SOURCE SCREENSHOTEXPAND ↗
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 experimentSign in first so we can reply to you. Submissions are reviewed, not published automatically.