mizorewww/laya-mlx
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
Language: Python
#apple_silicon #decision_model #inference #laya #local_ai #machine_learning #mlx #modernbert #system_one #typed_decisions
Stars: 2085 Issues: 4 Forks: 105
https://github.com/mizorewww/laya-mlx

mizorewww/laya-coreml
Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.
Language: Python
#apple_neural_engine #apple_silicon #coreml #decision_model #laya #local_ai #modernbert #on_device_ai #typed_decisions
Stars: 1004 Issues: 1 Forks: 65
https://github.com/mizorewww/laya-coreml

ollaya-dev/ollaya
Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.
Language: Rust
#calibration #classification #decision_models #gliclass #jev #laya #llm_routing #local_inference #nli #ollama #onnx #onnxruntime #rust #typesafe #zero_shot_classification
Stars: 741 Issues: 3 Forks: 36
https://github.com/ollaya-dev/ollaya