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.
378 experiments · showing 1–60
A playful collection of decision demos spanning dispatch, moderation, search, desktop control and a 32-agent arena.
Speak an English or Ukrainian drawing command while pointing, and Jev translates it into an action on a tldraw canvas.
Jev plays headless Doom from object bearings, distances, health, and ammo rather than game frames.
Jev plays NES Super Mario Bros. by choosing controls from emulator state rather than pixels.
A simulated Panda robot asks Jev how to move a block over a barrier.
Jev picks a flight path through each pipe, then Flappy Bird turns that route into precisely timed flaps.
Jev steers a Pac-Man recreation using structured game state.
Jev places Tetris pieces by considering holes, stack height and the current board.
Astra plans a Minecraft route while JEV chooses bounded actions for a recorded, source-verifiable playthrough.
Compare Jev with other controllers on simulated Panda pick-and-place, stacking, and obstacle-crossing tasks.
Combine cryptocurrency market data with a sample of X posts to produce a buy, sell, hold, or take-profit decision card.
Jev steers through traffic, junctions, and highway merges by choosing from paths generated inside a 3D driving simulator.
Laya and Jev play the same T-Rex course; watch their choices, response times, and last-second safety saves as the dinosaurs dodge obstacles.
Monitor a terminal-style Nifty 50 trading dashboard where Jev ranks symbols and decides take-profit targets.
Paste a chat with a crush and inspect Jev’s per-message readings of emotion, intent, affinity, and reply quality.
Use a chat-shaped command bar where Jev chooses real tools and arguments but never writes the response itself.
Jev pilots a MuJoCo drone by making a fresh flight decision from physics state on every tick.
Make Jev “chat” by sampling its probability distribution over the next character or token, one request at a time.
Give Jev an art prompt and watch its color distributions become a textured 560-pixel painting.
A simulated robot uses layered Jev decisions to close drawers and move a soup can.
Study BTC five-minute market snapshots, Jev class scores, paper entries, settlements, and recovery in a live dashboard.
Explores Jev-style decisions for StarCraft II macro and micromanagement across several controller configurations.
Watch pixel-art residents choose whom to visit, where to wander and how long to wait with Jev while an LLM handles conversation and memory.
Watch Jev choose among Pokémon Red actions assembled from emulator memory while deterministic code handles menus, movement, battles, and progression.
Receive a suggested next move after each sentence in a live sales call, with Jev’s confidence beside it.
Jev guides a simulated Franka Panda through manipulation tasks by choosing its intent, movement, and gripper commands.
Design three trading bees, then watch them race on OKX paper futures while Jev makes every market decision.
Watch Jev steer Snake, choosing from the legal moves the game gives it.
Submit a startup idea and Jev returns one of three verdicts: kill it, fix it or ship it.
Jev takes the keyboard and mouse to play the original StarCraft shareware.
A two-model Brotato player: Jev handles the dodging, and a slower strategist decides what to buy.
A drone-swarm simulation with a choice of local or Jev controllers.
Follow BTC and ETH perpetual decisions in a web blotter that marks each Jev-directed order BUY or SELL.
Send Jev through the first level of NES Super Mario Bros.
Follow a glowing, Jev-piloted fly through a 3D garden as it dives at wandering goblins.
A second Twitch chat column that helps you find the questions, jokes or helpful messages among the noise.
Four browser demos use multilingual Laya weights for typed decisions in Gomoku, Big Two, a maze, and a Chinese playground.
Try Python examples that use Jev to route support requests, check invoices, and triage security incidents.
An installable coding-agent skill can ask Jev to critique work after each turn.
Assign Jev a chore in Stardew Valley and follow each action it chooses from a live control panel.
Turn X into a labeled feed of substance, humor, chit-chat, promotion, or junk, with optional off-topic and AI-written filters.
A collection of Jev experiments spans support routing and a 3D driving simulation with visible sensor input.
A mobile-friendly playground collects 110 Jev use cases, games, dilemmas and model challenges.
Ask Jev is a retro Chinese advice desk for everyday dilemmas, with yes-or-no, choice and regret-risk modes.
Race Jev against Claude, Gemini, or a local model in a real-time Tetris duel with a shared piece sequence.
Watch Jev walk, fish, cook, fight, trade, and recover through a RuneScape world using about fifty available actions.
Watch a classifier awkwardly become a chatbot by choosing each next word from a tiny fixed vocabulary.
Play poker hands toward a target score while BLUFF's optional Jev autopilot studies the table and chooses its next line.
Compare Jev's mine probabilities with an exact solver on reproducible Minesweeper boards.
Collapse LinkedIn bait, promotions, sponsored posts, and blocked topics while keeping an inspectable score line on each post.
Use Jev as a fast conversational gate before a Discord voice bot’s speech model and server tools respond.
A Three.js quickscope arena pits the player against a Jev-controlled opponent.
Watch Jev choose a character, stage, upgrades, and movement in the real Linux Steam version of Vampire Survivors.
Watch Mario split into four alternate timelines when he dies, with the surviving run becoming the one that continues.
Race an F1 car against Jev as it picks racing lines, works the pedals, and learns where to push next lap.
Watch Jev leave home, choose Charmander, and battle its rival in Pokémon Red by handling the game's real branch points.
Play a MIDI keyboard and hear a Jev-driven partner answer on the next beat or bar.
A Street Fighter II agent that reads the game state and asks Jev for Ryu's next move.
Overlays Jev judgements on live WeChat messages and publishes the experiment’s failed accuracy tests.
In this browser stealth game, Jev judges the guards' actions while deterministic code runs the world.
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