The project controls a Minecraft Java 1.16.5 player through Mineflayer, using a separate model for planning and Jev for player actions. Configure the model relay and local runtime paths, install dependencies, start the vanilla server, and launch the documented nether-agent workflow.
Games & Simulations for Jev
177 repositories with documented relationships and source evidence.
TypeSafe Mario is an experimental NES controller loop using emulator telemetry and RAM-derived game observations. With Python 3.13, a TypeSafe key and your local game setup, inspect state-demo before running the play command.
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs
Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz
Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.
Two-stage JEV control of a Franka Panda in MuJoCo
1v1 Jev quickscope arena — Three.js + TypeSafe System One
🚀🚀 A 0.8B JEV-like multimodal model playing GUI games directly from raw pixels.
A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state
A browser-native Doom agent experiment with structured spatial state, composable AI controls, live decision telemetry, and a Chocolate Doom WebAssembly runtime.
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code
Real-time drone swarm autonomy simulation using Jev for fast System 1 reflex decisions and collision avoidance, with optional System 2 reasoning for strategic guidance
Jev play Tetris in real-time against other AI models
No project description available.
Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
Interactive experiments with TypeSafe Jev, from support routing to 3D driving simulations with real AI decisions and visible sensor inputs.
Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.
Jevtown: a social network where people write and 10,000 AI personas react
Pokemon Red on PyBoy: code owns the route and the arithmetic, Jev picks at branches in about 100 ms, calibration measured instead of assumed
Zero-dependency System One decision harness: 5 semantic gates saving frontier AI agent tokens on trivial errors & doom loops. Python + TypeScript + Rust. MCP-compatible.
Chess where both players are TypeSafe's Jev model: every move is a typed Choice decision
Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.
Chrome dino game played by Typesafe AI Jev model