raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Latest release v0.13.4 · 3 Sept 2026

These files are raullenchai/Rapid-MLX's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

3,667Stars on the repository
3Files it configures its agents with
782Tokens loaded in every session
3Agents configured

Instructions

Skills

Commands