ddalcu/mlx-serve
Native local AI inference server and app for Apple Silicon
- Chart
- Not on a chart right now
- Stars
- 2.5k
What it is
A native AI inference server and macOS app built with a Zig backend and Swift frontend that runs without Python on Apple Silicon. It supports chat, coding agents, images, video, music, speech, and 3D models offline while speaking OpenAI, Anthropic, and Ollama APIs.
Who it is for
Developers and Mac users who want to run open AI models and local coding agents offline without Python or external accounts.
Why it is trending
It gained 544 stars today to reach 2,484 total stars, following the v26.11.2 release that added DeepSeek execution across two Macs and GGUF support at MLX speed.
Main features
- OpenAI, Anthropic, and Ollama API compatibility on one port
- Local coding agent integration including Claude Code and Codex
- Image, video, music, voice cloning, and 3D generation
- Distributed model execution across Macs via Thunderbolt 5 or network
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary