Jev ecosystem projects — page 139

An AI (TypeSafe's Jev) plays official Tetris live, level 1 to 30 — pixels in, keypresses out

Watch Jev (TypeSafe) play heads-up No-Limit Hold'em, with decision probabilities on the side panel. Money/points scoreboard, offline CI, no secrets.

Jev Policy Engine is the first universal Policy-as-Code SDK built for TypeSafe AI's Jev System One model. It allows RevOps, DevOps, and Security teams to define strict, deterministic AI governance rules in YAML, and execute them at high speed.

Small demos of Jev (TypeSafe) through the Vercel AI Gateway: wiki race, town of agents, bullet chess, and more

7 projects built with TypeSafe Jev — dev tools and games

Small projects built with Jev (TypeSafe AI's typed-decision model)

Ingress LLM firewall: a reverse proxy that screens each request with one batched TypeSafe Jev System One call for jailbreaks, indirect injections, and data exfiltration before an expensive model runs

Practice lab for TypeSafe Jev prototypes

Can TypeSafe Jev solve RCOS capability routing at scale? Falsification-first experiment, verdict KEEP EXPERIMENTAL (ranker not brain), full receipts.

Terminal ASCII RPG where every NPC thinks with Jev (TypeSafe AI System One) — design draft

A resume screener built using Typesafe's new System One Model - Jev

claude-code-sifter

Per-prompt model routing for Pi, driven by Jev (TypeSafe System One)

Route OpenAI-style chat requests to a model and reasoning effort, using TypeSafe's Jev decision model as the classifier

Example: TypeSafe AI's Jev model reading sales call transcripts against a product capability library

Runnable samples for Jev, TypeSafe AI's System One model. Send state and questions carrying their own answer options, then branch on the typed value that comes back.

Agent skill: call the Jev (TypeSafe System One) Decision API from Claude Code, Cursor or any agent

A Claude Code skill for TypeSafe's Jev (System One) model — Choice/Score/Noul design guidance, patterns, and SDK reference.

Finds the turns where Claude Code should have loaded one of your skills and did not, judged by TypeSafe's Jev. Audit CLI plus the mod that fixes it live.

Jev (TypeSafe System One) skill and CLI for coding agents: when to use typed semantic decisions and how to invoke them

Community Jev skill market and assistant for automation testing, finance research and voice workflows. Computer Use is an independent repository.

TypeSafe Jev plays Battleship: one ~100-question typed fan-out per turn returns a calibrated hit-probability heatmap that is also the move policy.

An inbox with judgment. MCP server that files every note, link and meeting line by itself: TypeSafe's Jev decides the kind, the project, the urgency and the duplicates, and your text is never rewritten.

CLI for evaluating Microsoft Outlook email with TypeSafe AI’s Jev model.