by 10086ggqq
A browser-based T-Rex runner uses typed-decision models and distilled agents to choose actions
Typed decisions (choice / score / noul) drive a 7.5k-parameter System 1 that plays Chrome's T-Rex runner — distilled from a rollout planner, and reproducible at 133 ms of perception lag
Related projects
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
laya
receptron
Runs Laya typed-decision models from Node.js and TypeScript through ONNX Runtime
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya
laya-ultrafast
ipenywis
Runs a browser automation agent using local Laya decisions through MLX
laya-playground
wdobry
A local website combines Laya model demos, games, a benchmark, and an agent skill