Workflows,
not screens

The open-source visual workspace for AI media workflows. Arrange typed nodes on an infinite canvas, connect them, and run the graph — image, video, audio, text, and 3D, with your own provider keys.

Run in your browser

The full canvas, right here. Projects persist in this browser's storage and can be exported as .json at any time. Your provider keys stay in your browser and ride along only on your own requests — nothing is stored server-side.

Open the canvas

Run it locally

The same app from source, on your machine. Local adds what a hosted page cannot:

  • Projects and generations as real files on your disk
  • Local models via Ollama and ComfyUI, at $0
  • Durable background runs that outlive the tab
  • Headless CLI, HTTP API, and an MCP server