NodeTool is an open-source, agent-first creative workspace. Tell the agent what to make. It builds the project with image, video, audio, and text models, and you edit every part of the result.
The usual way
- Write the idea in a chat app
- Generate stills in an image app
- Animate them in a video app
- Cut them with music in an editor
Four subscriptions, a downloads folder, and no record of the steps. One change means doing it all again.
With NodeTool
- Write one brief
- The agent drafts, boards, renders, and cuts
- Open the project and change any part
One project on your own keys. Every step stays editable and re-runnable.
The agent builds. You stay in control.
- No programming needed. The agent picks the models, connects them, runs them, and fixes errors it finds.
- Nothing is hidden. What it builds is an ordinary storyboard, timeline, or graph. Open it, swap a model, rewire a step, and run again.
- Send a note, not a restart. Ask for a change to one shot and only that shot renders again.
- Agents inside workflows. Put an agent node in your own graph to plan, decide, and call tools.
What you keep
Bring your own keys
Connect OpenAI, Anthropic, Gemini, FAL, KIE, Replicate, and the video specialists. Keys are stored encrypted, with the encryption key in your operating system's keychain in Studio.
No markups
If an image costs $0.03 at the provider, you pay $0.03 to the provider. No credit packs. NodeTool takes no cut.
A project file that opens anywhere
The board, the script with its takes, and the multi-track cut are documents you can open and edit again. Workflows and mini apps export as a .nodetool bundle you can import anywhere.
Open source, end to end
Studio and Cloud are built from the same AGPL-3.0 source, with no paywalled features. Read it, fork it, or host it yourself.
An open studio and a hosted platform
| Topic | NodeTool | Hosted platforms |
|---|---|---|
| Models | Every major provider, switched in one click | The list they picked |
| When a better model ships | Add it the day it ships | Wait for them to add it |
| What you pay | Provider list prices, on your own keys | Their credits |
| What you keep | The board, the takes, and the multi-track cut as an editable project | An exported video. The project stays in their app. |
| Source | Open, AGPL-3.0 | Closed |
| Where it runs | Desktop app and browser, self-host any time | Their servers only |
| Local models | Run on your own GPU in Studio, offline | Not available |
Head-to-head
Comparing NodeTool with a specific tool? Each page covers features, pricing, and when to pick which.
ComfyUI
Deep local image control. NodeTool adds video, audio, and text, and runs an exported ComfyUI graph as a node.
Figma Weave (Weavy)
A hosted canvas on credits. NodeTool is open source and runs on your own keys.
n8n
Connects business apps. NodeTool is built for creative AI and media generation.
Dify
Mostly text apps. NodeTool adds native image, video, and music generation.
Flowise
Chatbots on a canvas. NodeTool builds those too, next to media generation.
Langflow
Text pipelines. NodeTool adds image, video, and music on the same canvas.
Already have a tuned ComfyUI graph? It keeps working inside NodeTool. See ComfyUI.