vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.