NodeTool Cloud is in alpha. Try it

All solutions
For self-hosters

Self-Hosted AI Workflows

Deploy NodeTool on infrastructure you own. The same open-source app that runs on your laptop starts from one `docker-compose.yml`, so a team can run workflows, models, and data behind its own firewall instead of a SaaS vendor's.

  • One Docker Compose file to stand up your own server
  • Your database, your storage, your uptime — no vendor lock-in
  • AGPL-3.0 open source, so nothing is held back for a paid tier

The workflow behind it

Data flow

One canvas.
The whole production.

Script, storyboard, footage, sound, and the cut — on one canvas, with the editing tools sitting right next to the models. You direct the whole piece instead of generating parts of it.

Workflow Editor
Node workflow turning a campaign brief and product photo into a generated product video

Scripting & casting

Go from prompt to screenplay in seconds. Draft dialogue, cast character voices, and audition alternate line readings with automatic word-level sync.

Any model you can reach

Route your shots through Flux, Seedance, Wan, Whisper, ElevenLabs, Suno, and the rest, on your own keys. Studio adds open weights running on your own hardware. No platform lock-in.

A real timeline, not a black box

Instead of a single unfixable video file, the agent hands you a fully editable multi-track project. Fine-tune every frame, layer, and audio stem.

Edit where you generate

Mask, retouch, extend, relight, upscale, layer, and composite. The tools you reach for live on the same canvas as the models.

Frequently asked questions

How do I self-host NodeTool?

Run it with the reference `docker-compose.yml` in the repository, or the `packages/deploy` tooling for more control. It's the same open-source app you'd run on the desktop, pointed at your own storage and database.

Do I still bring my own model keys when self-hosting?

Yes. Self-hosting NodeTool controls where the app and your data live; you still connect your own provider keys, or run local/open-weight models on the host's own hardware.

Why self-host instead of using a SaaS workflow tool?

You own the data, the uptime, and the deployment. There is no per-seat bill, no vendor deciding what changes next, and the same AGPL-3.0 source runs whether it's on your laptop or your server.

Build it on your own machine

Download the open-source studio for macOS, Windows, and Linux. Open the template and direct it yourself, on your own keys.