Open-source
agent-first creative workspace
Create and edit images, video, audio, and text with agents that work alongside you. Describe what you want, let the agent build it, then take over whenever you like. You get an editable project, not just a finished file. Run supported local models through Ollama or MLX, or connect cloud providers with your own API keys.
Free · AGPL-3.0 · macOS, Windows, Linux · No account required · All downloads
- Script, storyboard, sketch, timeline, 3D
- Your own API keys, no token markups
- Runs offline, files stay on your disk
Build with connected nodes instead of a single prompt. Read the visual node-based AI guide and start from an editable template.
One film shouldn't take five separate apps.
Pitch it, let the agent run it, then direct the final cut — one desktop app, one editable project, and nothing leaving the machine unless you send it.
01Pitch
Tell the agent your concept, style, and tone. It drafts the script, casts the voices, and sets the visual direction.
02Automate
The agent boards the scenes, generates the footage, syncs the audio, and cuts it on a multi-track timeline. On your keys, at provider prices.
- Board created
- 6 stills rendered
- 6 clips animated
- Score laid under
- Cut assembled
03Direct
Jump in at any moment. Swap a voice take, re-roll a clip, trim frames. The agent lays the foundation. You cut the final.
Privacy, speed, and no usage fees.
Everything Studio does, it can do without a network connection. Your prompts, your files, and your models all stay on your own hardware.
Works fully offline
Once your local models are downloaded you can disconnect from the internet and keep working, whether you are travelling or on a machine with no network at all.
Your files never leave the device
Projects, footage, prompts, and takes stay on your disk. Nothing is reported back to us, and nothing leaves the machine unless you call a remote provider on purpose.
Run open weights locally
Ollama, MLX for Apple Silicon, llama.cpp, and Hugging Face all work with the same building blocks. Pick any open model and pay no usage fees. When a cloud model is the better call, plug in your own API keys and pay the provider's price with no markup.
Use your GPU to the fullest
NVIDIA graphics cards on Windows and Linux, Apple Silicon on macOS. Image, video, and audio work runs on your own hardware.
Own your model library
The built-in model manager downloads and organizes model files and shares them across workflows, so you keep exactly the models you want.
The agent lives here too
The chat agent drives every editor through the same tools you click, and the whole toolbelt speaks MCP — point Claude Desktop or Claude Code at Studio and they can build and run workflows on your machine.
What Studio asks of you.
Running everything on your own machine means taking on a few jobs the cloud would otherwise handle. If any of these feel like too much, NodeTool Cloud runs the same workflows in your browser.
Hardware matters, if you run models locally
Working through hosted providers needs no graphics card at all. Running open weights on your own machine does: for serious local work we suggest 16GB or more of RAM and at least 4GB of graphics memory.
You manage updates
When a new release comes out, you install it. Builds are signed and notarized for macOS and Windows, so updating stays simple.
Disk space, if you download models
The app installs and downloads nothing else on its own. Open weights are large, so if you want them: allow around 20GB for a small starter set, and considerably more for image and video models.
Every model you need. On your own keys.
Route your shots through the best video, image, audio, and language models, or run open weights on your own hardware. Switch in one click. Pay each provider directly, at their published price.
Hello
HuggingFace
Search, download, and manage models straight from Hugging Face.
Organize your local library without leaving the app.
The full workspace, running locally.
Studio is not a lite edition. The canvas, the agent, and every editor — script, storyboard, sketch, timeline, 3D, and mini apps — ship in the desktop app, and the agent drives all of them through the same tools you click.
Studio runs on your machine.
Cloud runs in your browser.
Same workflows, same building blocks, same providers, both AGPL-3.0. Cloud is our hosting of the code you can run yourself. Switch between them whenever you like.
NodeTool StudioYou are here
Local-first desktop app
Best for: artists with a good graphics card or an Apple Silicon Mac, big local model collections, offline work, and everything kept on their own disk.
- Where it runsYour machine (macOS, Windows, Linux)
- Install requiredThe desktop app. Model downloads are optional
- Local models (Ollama, MLX, GGUF)Yes — runs entirely on your hardware
- Bring your own API keysAll providers — keys stored locally
- Works offlineYes — fully offline with local models
- Where your data livesOn your disk only
- GPU requirementsNone, unless you run models on your own hardware
- UpdatesYou install new releases
- Source code100% open source (AGPL-3.0)
- CostFree — pay only for the cloud APIs you use
NodeTool CloudAlpha
Hosted in the browser · Alpha preview
Best for: studios and solo artists who want to skip the hardware setup and work from any device, still on their own keys.
- Where it runsHosted by us — open in any browser
- Install requiredNone — sign in and start building
- Local models (Ollama, MLX, GGUF)Not available — cloud APIs only
- Bring your own API keysAll providers — keys stored encrypted
- Works offlineNo — needs an internet connection
- Where your data livesOur managed storage (encrypted at rest)
- GPU requirementsNone — heavy jobs run on cloud APIs
- UpdatesAlways on the latest version
- Source code100% open source (AGPL-3.0) — self-host any time
- CostFree while it is in alpha, a hosting subscription at full release — provider bills are yours either way
One recommendation, not two: use Studio for work you are being paid for — it is the finished edition. Cloud is for looking around without installing anything, and it is in alpha until further notice. Workflows move freely between the two.
100% open source. Always.
Studio is released under AGPL-3.0. Every building block, every provider, and every line that runs it is on GitHub. Read it, copy it, or host it yourself. There is no separate paid version.
View source on GitHubMade with working creatives
NodeTool is open source under AGPL-3.0. Star it on GitHub, join us on Discord, and share workflows with the artists and studios already using it on real jobs.
Get in
touch
Questions, bug reports, feature requests — we answer.