# MADEVAL/FerryAI

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

**Commercial license**：Commercial OK — 可商用，通常只需保留著作權聲明/授權條款

**Stars**：56
**Source**：https://github.com/MADEVAL/FerryAI