JevMade hello@JevMade.com

A public registry · independent & community-run

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 1,612 entries
The directory03 / 03 · Experiments

Find something worth exploring.

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.

1612 experiments · showing 841–900

A Pi extension that sends agents back to work when Jev determines they stopped before completing the task.

Source screenshot of pi-agent-foreman
SOURCE SCREENSHOTEXPAND ↗
from the source { "typesafe": { "type": "api_key", "key": "..." }}
— ★ 0 Agent tooling

A Pi coding coprocessor that uses Jev gates to review changes from the initial baseline and record an append-only activity trail.

Source screenshot of pi-jev-code
SOURCE SCREENSHOTEXPAND ↗
choice ★ 0 Agent tooling

Ask Jev to choose, score or answer yes-or-no questions without leaving a Pi coding session.

Source screenshot of pi-typesafe
SOURCE SCREENSHOTEXPAND ↗
from the source sidecar=/absolute/path/to/pi-typesafemkdir jev-playgroundcd jev-playgroundgit initpi -e "$sidecar/src/extension.ts"
choicescorenoul ★ 0 Agent tooling

A Pi extension that exposes five tools for narrow Jev judgments while leaving thresholds and actions in application code.

Source screenshot of pi-typesafe-jev
SOURCE SCREENSHOTEXPAND ↗
noul Does `ticket_message` request a refund?
choicescorenoul ★ 0 Agent tooling

A standard-library Python gateway that checks prompts for risk and routes safe requests to a suitable model.

Source screenshot of switchboard
SOURCE SCREENSHOTEXPAND ↗
from the source client ─► POST /v1/chat/completions │ ├─ 1 Jev call, 4 questions in parallel (questions.py) │ injection? harmful? pii? (Noul each) tier: small | large | uncle... ├─ policy.py (pure code) risk ≥ 0.80 → 403 block · 0.40–0.80 → allow + fla...
choicescorenoul ★ 0 Agent tooling

A provider-agnostic judgment layer that gates a coding workflow from product requirements through release.

Source screenshot of zcode-jev
SOURCE SCREENSHOTEXPAND ↗
noul ★ 0 Agent tooling

A five-event browser-use benchmark with one prompt and one shared clock, accompanied by a compact Jev-driven agent.

Source screenshot of browser-use-olympics
SOURCE SCREENSHOTEXPAND ↗
from the source open -na "Google Chrome" --args --remote-debugging-port=9333 --user-data-dir=/tmp/fastlo...echo 'TYPESAFE_API_KEY=...' > ~/.config/typesafe/env # chmod 600node olympics.mjs # full course; registers as "Almond-fastloop"node almond-fastloop.mjs task_booking.json # single task
choice ★ 0 Browser & computer use

A Python control loop that combines Jev action choices with Mobile MCP for Android automation.

Source screenshot of jev-mobile
SOURCE SCREENSHOTEXPAND ↗
choice ★ 0 Browser & computer use

A drop-in Playwright MCP wrapper that uses Jev to triage page state, prune snapshots, gate risky actions, and screen prompt injection.

Source screenshot of jev-playwright-mcp
SOURCE SCREENSHOTEXPAND ↗
from the source claude mcp add jev-playwright --env TYPESAFE_API_KEY=tsk_YOUR_KEY_HERE -- \ node /absolute/path/to/jev-playwright-mcp/cli.js --jev-mode=all --headless
— ★ 0 Browser & computer use

A bounded exploratory browser-testing tool with Jev-guided actions, deterministic assertions, and replayable evidence.

Source screenshot of JevTest
SOURCE SCREENSHOTEXPAND ↗
— ★ 0 Browser & computer use

A Chrome extension that reranks Google results with Jev and collapses sales pages and SEO filler.

Source screenshot of sift
SOURCE SCREENSHOTEXPAND ↗
scorenoul ★ 0 Browser & computer use

A Go browser-automation tool where Jev selects each semantic action.

Recorded frame of turbo
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
— ★ 0 Browser & computer use

An alternative X client that uses Jev rules to decide which timeline posts to keep or hide.

Source screenshot of dmx.to
SOURCE SCREENSHOTEXPAND ↗
— Apps & data pipelines

An experimental tool that scores X drafts on viral dimensions while the author writes.

Source screenshot of draftpulse
SOURCE SCREENSHOTEXPAND ↗
score ★ 0 Apps & data pipelines

A proof of concept that uses Jev judgments and FFmpeg to censor selected words in audio with low latency.

Source screenshot of jev-audio-beeper
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
choicescore ★ 0 Apps & data pipelines

A React and FastAPI application that uses Jev to diagnose CVs and compare them with job requirements.

Source screenshot of jev-resume-analyzer
SOURCE SCREENSHOTEXPAND ↗
from the source # Backendcd backendcp .env.example .env# Edit .env and set TYPESAFE_API_KEYuv sync
score ★ 0 Apps & data pipelines

A single-call guardrail API for detecting prompt injection, jailbreaks, data leaks, and unsafe content with Jev.

Source screenshot of jevegis
SOURCE SCREENSHOTEXPAND ↗
— ★ 0 Apps & data pipelines

A writing tool that uses Jev's feedback to help an AI draft sound more like you.

Source screenshot of mimicry
SOURCE SCREENSHOTEXPAND ↗
scorenoul ★ 0 Apps & data pipelines

A pre-install security gate that uses Jev to inspect npm lifecycle scripts before they run.

Source screenshot of pkg-gate
SOURCE SCREENSHOTEXPAND ↗
from the source npm install pkg-gateexport TYPESAFE_API_KEY="ts_..." # get a key at typesafe.ai
choicescore ★ 0 Apps & data pipelines

s1s

Find your way around a codebase with search results and flow diagrams linked to the source.

Source screenshot of s1s
SOURCE SCREENSHOTEXPAND ↗
score ★ 0 Apps & data pipelines

Watch a support call's scorecard update as the transcript arrives.

Source screenshot of transcript-scorecard
SOURCE SCREENSHOTEXPAND ↗
from the source git clone https://github.com/brandonbryant12/transcript-scorecard.gitcd transcript-scorecardcorepack enablepnpm install --frozen-lockfilecp .env.example .env
score ★ 0 Apps & data pipelines

Ask Jev which support tickets and alerts need attention, or whether a deployment looks risky.

Source screenshot of typesafe-triage-guard
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
choicescorenoul ★ 0 Apps & data pipelines

A small browser game challenges players to outguess Jev.

Source screenshot of beatjev
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
noul ★ 0 Playable demos & bots

Play either side of a browser chessboard while Jev chooses the opposing moves from structured board state.

Source screenshot of chess-jev
SOURCE SCREENSHOTEXPAND ↗
— 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

Arrive in a village of Jev-driven characters and earn their trust before nightfall—or try to get away with a lie.

Source screenshot of Hollow Creek
SOURCE SCREENSHOTEXPAND ↗
— Playable demos & bots

A hundred AI residents go about their lives in a tiny town, with Jev choosing what each does next.

Source screenshot of hundred
SOURCE SCREENSHOTEXPAND ↗
from the source Jev Lab ├── Hundred 100 people, one town └── Jev Shogi human Sente, Jev Gote
choice ★ 0 Playable demos & bots

A terminal tool races through Wikipedia links by asking Jev to rank each possible next page.

Source screenshot of jev-bfs
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
score ★ 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

A MoonBit playground for trying Jev's Choice, Score and Noul question types.

Recorded frame of jev-gomoku
ACTUAL RECORDING12 SEC ↗
noul This message is spam.
choicescorenoul ★ 0 Playable demos & bots

Jev plays browser table tennis from structured telemetry and sends its choices through ordinary Chrome inputs.

Recorded frame of jev-play-ping-pong
ACTUAL RECORDING12 SEC ↗
choicescore ★ 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

Spawn Minecraft bots and give them goals, with a planner choosing the task and Jev handling the immediate actions.

Source screenshot of jev.mods
SOURCE SCREENSHOTEXPAND ↗
— ★ 0 Playable demos & bots

A cyberpunk game of bluffing your way past a border guard powered by Jev.

Source screenshot of last-exit
SOURCE SCREENSHOTEXPAND ↗
— ★ 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

An autonomous agent plays PlayStation 2 games while a live HUD shows Jev's visual telemetry.

Source screenshot of ps2-ai-agent
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"
— ★ 0 Playable demos & bots

Jev supplies the decisions for non-player characters living in a simulation of River Oaks, Houston.

Source screenshot of river-oaks
SOURCE SCREENSHOTEXPAND ↗
— ★ 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

Two hundred people try to break an agent's defenses while a defender uses each breach to improve them.

Source screenshot of siege
SOURCE SCREENSHOTEXPAND ↗
choicescore ★ 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 → hello@JevMade.com