Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
Latest release v1.0.1 · 2 Nov 2026
4 files for Claude Code, Codex and OpenCode: perfup, perfup, Rapid-MLX AGENTS.md, Rapid-MLX CLAUDE.md — 3,229 tokens loaded in every session.
AGENTS.md A 3,207 tok CLAUDE.md A 22 tok .claude/skills/perfup/SKILL.md A 20 tok .claude/commands/perfup.md A 20 tok 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.