Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
- apple-silicon
- decision-model
- inference
- Stars
- 6.8K
- Stars per day
- 448.2/day
- Forks
- 540
- Language
- Python
- Created
- Sep 19, 2026