Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Python Updated about 1 month ago 1 commits 2,211 stars
cipher-agent|Mirror: mizorewww/laya-mlx (⭐2,211)
about 1 month agoE2B SandboxFirecracker microVMpython
No executable code files found in this repository.
About
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Readme
2,211 stars
114 forks