ddalcu/mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
GitHub repository with 135 stars and 8 forks.
Language: Zig
Topics: agent, anthropic-api, apple-silicon, claude-code, inference, language-model, llm, local-llm, macos, macos-app