Organization repository on GitHub
An arcade where AI models play games, one fast typed decision at a time.
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Demos & Experiments
System One Arcade
A Bun workspace pairing a typed decision API over System One providers with a React arcade where decision models play games and every call is stored and ranked. The sample code calls Jev through OpenRouter with boolean, choice and score questions.
- Stars
- 1
- Language
- TypeScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- desplega-ai
- Last verified
- Oct 2026
- Languages
- TypeScript
- Platforms
- BrowserOpenRouterSQLite
- Capabilities
- Open sourceRequires API key
Highlights
- Bun workspace with @system-one/ai, one typed API over five decision-model providers including TypeSafe.
- The sample calls openrouter with ~typesafe/jev-latest and boolean, choice and score questions over text, JSON, image or audio state.
- React arcade ranks models; every call is stored in SQLite with tokens, cost, latency and error codes.
- Default budget of 1 USD per UTC day, configurable per provider; over-cap calls return 429.
- Games: Arena on Ring and Plane fields in lockstep or real-time clocks, plus Attention with a 9x9 curiosity grid.
Quickstart
bash
bun install
cp .env.example .env
bun test
bun run devWatch out
README and GitHub metadata reviewed 2026-10-17; the digest truncates the usage sample mid-call, and the latency and provider comparisons come from the author's own arcade runs rather than an external benchmark. Live calls need provider keys.
Questions about this entry
Short answers drawn from the linked project or page.
A Bun workspace with two packages: @system-one/ai, a typed API over System One and decision-model providers, and an arcade where decision models play games against each other while a server stores and ranks every call.
The sample decision calls the OpenRouter provider with the ~typesafe/jev-latest model id, and the package also ships a direct TypeSafe provider that takes TYPESAFE_API_KEY; arcade presets include Jev mirror matches and a Jev swarm.
Typed questions answered with probabilities: boolean with P(yes), choice over named options with per-option probabilities, and score over ordered levels with the most probable level and a probability-weighted score. Any answer can also be a refusal.
bun install, copy .env.example to .env and fill in the keys you have, then bun run dev opens the arcade on localhost:3300. bun test runs unit tests with no network, and bun run smoke makes live calls to credentialed providers.
The default budget caps spend at 1 USD per UTC day, configurable per provider through the SYSTEM_ONE_BUDGET environment variable. A public deployment can also cap per visitor and per IP, and calls over a cap fail with HTTP 429.
Every decide, transcribe and generate call is stored in a SQLite database at data/arcade.sqlite with tokens, cost, latency and error code, plus a scores table. Images and audio are stored only as a sha256 hash and size.
Game runs report metrics per model, and the ranking API aggregates mean and sum per game and metric, filterable by field, clock, policy, provider and model. Draws and the share of stay moves show up in the rankings too.
More Jev resources like this
A demo that has three decision models read recent news and price Polymarket and Kalshi questions, then compares their probabilities with live market odds and replays how each model changed its mind article by article.
Jev Demos & Experiments#community#github#demo
Community
yorkeccak/model-vs-marketTypeScript
yorkeccak/model-vs-marketTypeScriptA browser visual IDE for composing Jev API requests: build a state plus Choice, Score, Noul and Box questions with image assets, preview and validate the request JSON, send it, and read the answers as visual cards instead of raw JSON.
Jev Demos & Experiments#community#github#typescript
Community
MoeclubM/PlayJevTypeScript
MoeclubM/PlayJevTypeScriptPac-Man where the characters are driven by System One decision models: TypeSafe's jev (typesafe/jev-1.13.0, the default) and others Opper serves, with the model's odds drawn on the board and a leaderboard benchmark.
Jev Demos & Experiments#community#github#typescript
Community
joch/jevmanTypeScript
joch/jevmanTypeScriptA learning lab for decision models: TypeSafe Jev and Microsoft Decision-1 route support tickets in under a second for about $0.02 per 1,000 calls, while Claude handles the hard cases. It ships an interactive site, a benchmark, calibration tests and docs.
Jev Demos & Experiments#community#github#benchmark
A benchmarking studio and real-time simulator that pits Jev (remote TypeSafe System One), a local Laya model and the optimal blackjack Basic Strategy against each other on identical deterministic shoes. It scores every deviation turn by turn and runs headless batches of up to 100,000 rounds.
Jev Benchmarks & Evaluations#community#github#blackjack
Community
mrbanana55/decision_blackjackPython
mrbanana55/decision_blackjackPythonA one-page playground and test bench for TypeSafe Jev: pick a backend, load an example and run typed questions against Jev through OpenRouter or TypeSafe, an LLM baseline, or a keyless mock — all speaking the same /v1/systemone contract, with an inspector for the answer distributions.
Jev Demos & Experiments#community#catalog-import#logicrw
Community
creativoma/here-we-go-jevTypeScript
creativoma/here-we-go-jevTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.