JevMade

Sign in

Explore the Jev ecosystem.

Learn, build, and play with Jev — from deep technical guides to creative experiments.

Make & explore

Experiments.

See what builders made with Jev. Games, tools, repositories, articles, and more — traced to their sources.

Featured experiment Jev experiments by Nader Dabit
Recorded frame from Jev experiments
Explore 2,140 entries
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 Firecrawl

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 121–180

A table-tennis game where Jev's answer is the paddle's target pixel and a tiny local servo simply moves there.

Source screenshot of Human vs JEV · Table Tennis
SOURCE SCREENSHOTEXPAND ↗
from the source return {"place": { "type": "choice", "instructions": ("The ball is coming toward your face at x=%.0f. Where should the CE... "when the ball arrives, so that the ball hits your face? Work out w... "will be at x=%.0f, then pick the position closest to it. Your padd...
choice ★ 1 Playable demos & bots

A ring-maze game that asks Jev for the best move from every cell, then colors each played or overruled step.

Source screenshot of Chakravyuha — Jev guides Abhimanyu
SOURCE SCREENSHOTEXPAND ↗
from the source // A POLICY can be asked for in parallel questions, because a policy is a// function of the cell alone. So: one question per cell — "standing at ring R,// sector S, which move begins the optimal route to the centre?" — with that// cell's own doors listed as the options. Every question is self-contained, so
choice ★ 1 Playable demos & bots

An AI player tackles Unreal Tournament 99 on a real Windows 98 machine.

Source screenshot of llm-lan-party
SOURCE SCREENSHOTEXPAND ↗
from the source move: choice("What movement should the player take right now?", { advance: "Move forward, toward the objective or nearest enemy.", retreat: "Move backward, away from danger.", strafe_left: "Strafe left.",
choicenoul ★ 1 Playable demos & bots

Two Jev brains perform a fixed piano piece, choosing hand and finger positions for each 100-millisecond slice ahead of time.

Source screenshot of Jev Piano
SOURCE SCREENSHOTEXPAND ↗
from the source A hand has a fixed span and five fingers that never cross. A note sounds only if a finge...already resting on that exact key when its moment arrives. Every 100 ms slice of the pie...question to [TypeSafe's Jev](https://docs.typesafe.ai/introduction): where does this han...and which key does each of its fingers rest on. Jev answers with option ids from the lis...offered, never a key name or a coordinate.
choice ★ 1 Playable demos & bots

A pixel-art experiment that asks Jev to choose the colors from a short brief.

Source screenshot of TypeSafe Pixels
SOURCE SCREENSHOTEXPAND ↗
from the source export const BRIEF_QUESTIONS = { boundary: { type: 'score', criteria: VERT, instructions: "Where, top to bottom, does the main boundary between the picture's tw... focal_present: { type: 'noul', instructions: 'Does the picture have one clear focal object that the eye goes to fir...
scorenoul ★ 1 Playable demos & bots

An endless Three.js cyberpunk arena shooter uses Jev to drive combat decisions.

Source screenshot of cyber-breach-jev
SOURCE SCREENSHOTEXPAND ↗
from the source ┌───────────────────────────┐ │ TypeSafe AI Jev Model │ │ (or Local RLCD Engine) │ └─────────────┬─────────────┘ │
choicescorenoul ★ 0 Playable demos & bots

A visual lab runs Jev and scripted agents across several games and emulator platforms.

Source screenshot of jev-games
SOURCE SCREENSHOTEXPAND ↗
from the source uv run jev-games play --game mario --policy scripted --decisions 20uv run jev-games play --game kungfu --policy scripted --decisions 20uv run jev-games play --game doom --policy scripted --decisions 20uv run jev-games play --game mario --policy jev --decisions 10
— ★ 0 Playable demos & bots

Jev plays Snake by reading the board and picking a direction on every tick.

Source screenshot of jev-snake
SOURCE SCREENSHOTEXPAND ↗
from the source snake_game/├── game.py # pure game rules and state transitions├── jev_agent.py # typed Jev adapter├── state.py # game state -> JSON-compatible AI state├── config.py # defaults and environment overrides
choicescore ★ 0 Playable demos & bots

Jev plays Atari Pong by answering one movement question per frame without receiving raw coordinates.

Source screenshot of pong-jev
SOURCE SCREENSHOTEXPAND ↗
from the source bridge/pong_bridge.py ALE/Pong-v5 behind a JSON step APIsrc/core.ts arithmetic, wording, the question, the baseline policysrc/jev.ts TypeSafe System One client, one POST, no SDKsrc/bridge.ts HTTP client for the environmentsrc/agent.ts the play loop, emits ticks and never prints
choicescore ★ 0 Playable demos & bots

A Jev pilot flies through a Python river shooter inspired by Atari's River Raid.

Source screenshot of river-run-typesafe
SOURCE SCREENSHOTEXPAND ↗
from the source .venv/bin/python -m typesafe_pilot # watch it play in r....venv/bin/python -m typesafe_pilot --lockstep # game waits for eac....venv/bin/python -m typesafe_pilot --headless --frames 3000 # no window, prints....venv/bin/python -m typesafe_pilot --record play.mp4 --seconds 60 # save a video with....venv/bin/python -m typesafe_pilot --human # fly it yourself (n...
score ★ 0 Playable demos & bots

Human Compiler turns prose into compiler-style diagnostics for traits such as passive aggression and corporate jargon.

Source screenshot of human-compiler
SOURCE SCREENSHOTEXPAND ↗
from the source Compiling input.txt (--mode corporate) Lexing 0.4ms 4 paragraphs, 7 sentences, 62 words Analyzing 812ms jev-1.13.0, 45 questions, 1203 tokensPASSIVE_AGGRESSION ████████░░ 0.82CORPORATE_BULLSHIT █████████░ 0.94
choicescorenoul ★ 0 Playable demos & bots

Upload a dataset, pose a question and watch Jev classify every row.

Source screenshot of Jev Gamecast
SOURCE SCREENSHOTEXPAND ↗
from the source CONVEX_URL=https://<deployment>.convex.cloudCONVEX_WRITE_SECRET=<operator-provisioned-secret>CONVEX_DEPLOY_KEY=<Convex production deploy key, Vercel Production only>OPENROUTER_KEY=<operator-provisioned-secret>JEV_API_KEY=<operator-provisioned-secret>
choicescorenoul ★ 0 Playable demos & bots

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

Sign in first so we can reply to you. Submissions are reviewed, not published automatically.

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.