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.

Turn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.

Drive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.