Rapid-MLXFrom the builder
Rapid-MLX 1.0: a built-in AI agent and new local models for Mac
Rapid-MLX runs local AI on Apple Silicon with a Desktop app, a terminal agent, and OpenAI- and Anthropic-compatible APIs, and local inference needs no account. The release adds a built-in agent harness plus LFM3 text and vision models, a large Ornith model, and MiniMax video with audio.
The Desktop app and engine are free and open source under Apache. Users can start with one local chat, then connect installed coding agents when needed; the harness can read and edit a workspace, run commands, keep resumable history, and offer approval modes or disable action tools.
Rapid-MLX runs AI models locally on your Apple Silicon Mac. Version 1.0 adds a built-in agent harness, LFM3 text and vision models, Ornith 122B, and MiniMax-H3 video with audio.
Saved . A shortened excerpt from the official blog; the original publisher retains authorship.