Vibe Coding Discovermlx-serve
View on GitHubNative LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
Native Zig inference server and macOS app for running MLX and GGUF models on Apple Silicon. Exposes OpenAI, Anthropic, and Ollama-compatible APIs, with a built-in chat and agent UI plus image, video, audio, music, and 3D generation.
Use Cases
Run local LLMs on Apple SiliconServe models through OpenAI-compatible APIsServe models through Anthropic-compatible APIsConnect coding agents to local modelsGenerate images, video, music, and speechUse MCP tools with a local chat agent
Built With
- Language
- Zig
- Frameworks
- MLX · llama.cpp · MCP
Tags
local inference · Apple Silicon · MLX · GGUF · OpenAI API · Anthropic API · Ollama API · multimodal generation · MCP · coding agents