Rapid-MLX
An open-source OpenAI- and Anthropic-compatible LLM inference server and Mac app for Apple Silicon, built on MLX and focused on reliable tool calling for coding agents.
Rapid-MLX is an inference server and Mac application for running large language models on Apple Silicon through Apple's MLX framework, exposing both an OpenAI-compatible API and an Anthropic Messages-compatible API. It focuses on reliable tool calling for coding agents such as Claude Code, Codex CLI and Aider, with 27 tool-call parser modules including an auto-detect fallback.
It supports continuous batching of concurrent requests, a radix prefix cache with state snapshots for hybrid models that is saved to disk on shutdown and restored at startup, and a quantized key-value cache. Its documentation includes a feature comparison against other local inference tools such as oMLX, Ollama, LM Studio and mlx-lm, along with a published benchmark methodology.
It is licensed under Apache-2.0.