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.
2140 experiments · showing 961–1020
A Chrome extension that reranks Google results with Jev and collapses sales pages and SEO filler.
SOURCE SCREENSHOTEXPAND ↗
An open-source Chrome extension that uses Jev to filter ads and prose identified as AI-generated.
SOURCE SCREENSHOTEXPAND ↗
A Go browser-automation tool where Jev selects each semantic action.
ACTUAL RECORDING12 SEC ↗
from the source
npm install -g @sightmap/jev-turbo # installs the sightmap CLI with itexport TYPESAFE_API_KEY=... # the only key you need
A research tool that checks whether cited papers support the sentences that reference them.
SOURCE SCREENSHOTEXPAND ↗
An alternative X client that uses Jev rules to decide which timeline posts to keep or hide.
SOURCE SCREENSHOTEXPAND ↗
An experimental tool that scores X drafts on viral dimensions while the author writes.
SOURCE SCREENSHOTEXPAND ↗
A Jev-powered emoji autocomplete app designed to keep up with live typing.
SOURCE SCREENSHOTEXPAND ↗
A web interface for classifying text with Jev.
SOURCE SCREENSHOTEXPAND ↗
A proof of concept that uses Jev judgments and FFmpeg to censor selected words in audio with low latency.
SOURCE SCREENSHOTEXPAND ↗
from the source
WAV/audio file -> ASR adapter: words + start/end milliseconds -> parallel Jev evaluations (Boolean profanity probability + Score severity) -> threshold + timestamp padding/merging -> ffmpeg mute/beep overlay
A React and FastAPI application that uses Jev to diagnose CVs and compare them with job requirements.
SOURCE SCREENSHOTEXPAND ↗
from the source
# Backendcd backendcp .env.example .env# Edit .env and set TYPESAFE_API_KEYuv sync
A single-call guardrail API for detecting prompt injection, jailbreaks, data leaks, and unsafe content with Jev.
SOURCE SCREENSHOTEXPAND ↗
A writing tool that uses Jev's feedback to help an AI draft sound more like you.
SOURCE SCREENSHOTEXPAND ↗
A pre-install security gate that uses Jev to inspect npm lifecycle scripts before they run.
SOURCE SCREENSHOTEXPAND ↗
from the source
npm install pkg-gateexport TYPESAFE_API_KEY="ts_..." # get a key at typesafe.ai
Find your way around a codebase with search results and flow diagrams linked to the source.
SOURCE SCREENSHOTEXPAND ↗
Scam Shield checks text messages for signs of fraud with Jev.
SOURCE SCREENSHOTEXPAND ↗
Watch a support call's scorecard update as the transcript arrives.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/brandonbryant12/transcript-scorecard.gitcd transcript-scorecardcorepack enablepnpm install --frozen-lockfilecp .env.example .env
This Python package grades code comments against a set of practical heuristics.
SOURCE SCREENSHOTEXPAND ↗
Ask Jev which support tickets and alerts need attention, or whether a deployment looks risky.
SOURCE SCREENSHOTEXPAND ↗
from the source
src/triage/ battery.py generic hazard-battery engine (Noul battery + Score + policy -> actio... client.py real TypeSafeClient, or the offline mock -- see below mock.py offline heuristic double for local dev / tests / CI without a key guardrail.py guard(): message-safety battery on top of battery.py
Jev chooses moves for a playable version of Tetris.
SOURCE SCREENSHOTEXPAND ↗
A small browser game challenges players to outguess Jev.
SOURCE SCREENSHOTEXPAND ↗
from the source
npm installnpx wrangler loginnpx wrangler secret put TYPESAFE_API_KEY # required before the first deploynpx wrangler deploy # → https://beatjev.<you>.workers.dev
Jev controls the paddle of a Next.js brick-breaker in real time.
SOURCE SCREENSHOTEXPAND ↗
Play either side of a browser chessboard while Jev chooses the opposing moves from structured board state.
SOURCE SCREENSHOTEXPAND ↗
An endless Three.js cyberpunk arena shooter uses Jev to drive combat decisions.
SOURCE SCREENSHOTEXPAND ↗
from the source
┌───────────────────────────┐ │ TypeSafe AI Jev Model │ │ (or Local RLCD Engine) │ └─────────────┬─────────────┘ │
A game about linking two seemingly unrelated things in as few steps as possible.
SOURCE SCREENSHOTEXPAND ↗
Arrive in a village of Jev-driven characters and earn their trust before nightfall—or try to get away with a lie.
SOURCE SCREENSHOTEXPAND ↗
A hundred AI residents go about their lives in a tiny town, with Jev choosing what each does next.
SOURCE SCREENSHOTEXPAND ↗
from the source
Jev Lab ├── Hundred 100 people, one town └── Jev Shogi human Sente, Jev Gote
Jev Arcade pairs an industrial duel with a neon survival game, both playable against live AI.
SOURCE SCREENSHOTEXPAND ↗
Play tic-tac-toe or Connect Four against Jev while conventional code enforces the rules.
SOURCE SCREENSHOTEXPAND ↗
A terminal tool races through Wikipedia links by asking Jev to rank each possible next page.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/komikat/jev-bfs.gitcd jev-bfsuv sync --lockeduv run jev-bfs --install-browseruv run python -m unittest discover -s tests -v
A visual lab runs Jev and scripted agents across several games and emulator platforms.
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
A MoonBit playground for trying Jev's Choice, Score and Noul question types.
ACTUAL RECORDING12 SEC ↗
noul
This message is spam.
Jev plays browser table tennis from structured telemetry and sends its choices through ordinary Chrome inputs.
ACTUAL RECORDING12 SEC ↗
Jev plays Snake by reading the board and picking a direction on every tick.
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
Jev plays the Chrome dinosaur runner.
SOURCE SCREENSHOTEXPAND ↗
A playable Tetris asks Jev to choose each piece's rotation and column from the board state.
SOURCE SCREENSHOTEXPAND ↗
Spawn Minecraft bots and give them goals, with a planner choosing the task and Jev handling the immediate actions.
SOURCE SCREENSHOTEXPAND ↗
A cyberpunk game of bluffing your way past a border guard powered by Jev.
SOURCE SCREENSHOTEXPAND ↗
A cooperative platform shooter puts a Jev-controlled partner beside the player.
SOURCE SCREENSHOTEXPAND ↗
Jev plays Atari Pong by answering one movement question per frame without receiving raw coordinates.
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
An autonomous agent plays PlayStation 2 games while a live HUD shows Jev's visual telemetry.
SOURCE SCREENSHOTEXPAND ↗
from the source
export TYPESAFE_API_KEY="your_api_key_here"export TYPESAFE_MODEL="jev-latest"export EMULATOR_WINDOW_TITLE="PCSX2"export TARGET_FPS="30"
Jev supplies the decisions for non-player characters living in a simulation of River Oaks, Houston.
SOURCE SCREENSHOTEXPAND ↗
A Jev pilot flies through a Python river shooter inspired by Atari's River Raid.
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...
A 3D planetary rover sandbox tests autonomous choices made with TypeSafe AI.
SOURCE SCREENSHOTEXPAND ↗
Jev moderates a living-room social-deduction game designed for a shared television.
SOURCE SCREENSHOTEXPAND ↗
Two hundred people try to break an agent's defenses while a defender uses each breach to improve them.
SOURCE SCREENSHOTEXPAND ↗
Jev considers several questions about the board at once to choose Snake's next move.
SOURCE SCREENSHOTEXPAND ↗
from the source
git clone https://github.com/siroccomask/snake-jev.gitcd snake-jevuv synccp .env.example .env
Jev presses the controls of a small virtual creature while deterministic code runs its world.
SOURCE SCREENSHOTEXPAND ↗
Play either side of a 3D chessboard against Jev, or watch two Jev players face off.
SOURCE SCREENSHOTEXPAND ↗
Two Jev agents play chess, choosing every move through a typed Choice question.
SOURCE SCREENSHOTEXPAND ↗
Jev controls a Minecraft Java player through tasks such as gathering lumber and building a Canadian flag.
SOURCE SCREENSHOTEXPAND ↗
from the source
{ "model": "jev-latest", "state": { "scenario": "lumber", "goal": "Find trees, collect 10 new logs, then return to the starting position.",
CartShield assigns a fraud disposition to checkout activity for small online shops.
SOURCE SCREENSHOTEXPAND ↗
Crowdcheck simulates how 10,000 AI readers might react to a post before publication.
SOURCE SCREENSHOTEXPAND ↗
Twelve deliberately unqualified AI councillors vote on unusually specific questions.
SOURCE SCREENSHOTEXPAND ↗
from the source
TYPESAFE_API_KEY=your-key-hereTYPESAFE_MODEL=jev-latest
Harness Judge labels each agent step as acceptable, worth retrying, needing escalation or ready to stop.
SOURCE SCREENSHOTEXPAND ↗
HireSignal gives resumes a first-pass fit assessment and an interview recommendation.
SOURCE SCREENSHOTEXPAND ↗
Human Compiler turns prose into compiler-style diagnostics for traits such as passive aggression and corporate jargon.
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
Upload a dataset, pose a question and watch Jev classify every row.
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>
A 3D robot companion reacts through typed Jev decisions rather than generated dialogue.
SOURCE SCREENSHOTEXPAND ↗
An interactive room changes in response to the visitor's words, using presets or live Jev decisions.
SOURCE SCREENSHOTEXPAND ↗
A public demo uses Jev to review an advertisement before it runs.
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.