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.

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Mission control for Claude Code: run many sessions in parallel with multi-account isolation, transcript viewer, cost tracking, and memory dashboards. Windows + macOS (Apple Silicon).

Local-first AI memory MCP server — query your ChatGPT, Claude Code, Cursor & Codex history from any LLM. DuckDB+parquet.

A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)