GitHub

Pokemon-playing experiment where Jev chooses actions.

Two Jev agents duel at Snake through Vercel AI Gateway.

Penalty shootout powered by Render Workflows, TypeSafe Jev, and Render Postgres.

Family word game for playing with imaginary words, powered by Jev.

Replayable Atari experiments using Jev structured decisions and value questions.

JEV Prix simulation with five AI drivers, procedural circuits, BYOK Jev, and saved replays.

Pokemon Red on PyBoy where Jev chooses legal actions only at branches and each battle turn logs a Brier-scored faint prediction.

Jev-powered game and decision experiment.

Uses Jev to classify and organize GitHub stars.

Trading application that uses Jev for market decisions.

Async library and CLI that turns a week of news into one sentiment score per ticker, using Jev by default.

Binance testnet trading bot that uses Jev to judge news.

TypeScript application built around TypeSafe Jev decisions.

TypeScript application exploring TypeSafe Jev as a System One decision layer.

Neovim plugin that has Jev score each function against a plain-language question and ranks results in quickfix.

Chrome extension that uses Jev to annotate articles and posts on X and Threads.

Push-to-talk voice orb for autonomous browser control using Jev and Metal Whisper.

Bounded browser and desktop automation where Jev picks one next step while code owns perception, execution, and verification.

Two Jev agents compete in click-only browser games through Browser Use.

YouTube extension that asks Jev for the sponsor probability of each caption segment and paints the result on the seek bar without a crowd database.

Social research agent for Instagram, TikTok, and LinkedIn: Jev repeatedly chooses the next concrete operation and target, while socai executes it in a local Chrome session.

Cursor and Hermes plugin marketplace for JEV Labs routing tools.

Hermes context compaction that has Jev score tool calls, drops stale content, and preserves everything retained verbatim.

Codex plugin that uses Jev to preserve useful conversation excerpts alongside compacted summaries.

Jev model-routing integration for the Pi coding agent.

MCP server for typed Jev Choice, Noul, and Score judgments with probabilities and confidence.

Pi extension that classifies tasks with Jev and routes each run to an explicitly configured model.

MCP server that uses Jev to route coding-agent decisions such as file selection, task paths, and test-impact checks.

Pi extension suite for Jev-powered context compaction and model routing.

Claude Code plugin that has Jev compare each pending tool call with the session plan before allowing, escalating, or blocking it.

Pi context pruning that uses Jev to drop or truncate stale tool calls while preserving retained content verbatim.

Commit-time review gate where Jev judges plain-language rules against agent-written code.

Pre-commit hook where Jev checks the message against the staged diff and flags debug leftovers, unmentioned work, and added credentials.

Claude Code Stop hook that asks four Jev questions when files changed without a passing check, blocking unverified completion claims while failing open on errors.

Evaluation framework for detecting AI hallucinations and instruction-following failures with Jev.

Connector for integrating TypeSafe Jev decisions into application workflows.

Local Paseo plugin that exposes Jev evaluations through MCP.

Adds jev(), jev_prob, jev_choice, and jev_score to vanilla PostgreSQL queries through a psql-shaped CLI and Go, TypeScript, and Python SDKs.

JSON-in, typed-decisions-out CLI for the TypeSafe System One API.

Jev (TypeSafe AI) PoC through Game of Thrones.