The open creative AI workspace
Every model. Your keys. Your canvas.
NodeTool replaces the chatbox with a node canvas where image, video, audio, and LLM models run side by side. Bring your keys, or run everything locally. Open source, AGPL-3.0.
Featured use cases
Three flagship workflows, end to end. Each starts from a few inputs and builds a finished result on one canvas you can re-run, restyle, and re-point at your own story. See all use cases →
Movie Poster Generator
Title, genre, and audience become a batch of theatrical poster concepts.
What you can do
- Mix models from every vendor — Wire Flux next to GPT-5.6 next to ElevenLabs in one graph. Pick the best model per step, not per project.
- Run frontier models locally — Ollama, MLX, and GGUF on your hardware. Works offline. Files never leave your disk.
- Bring your own keys — Pay OpenAI, Anthropic, Gemini, Replicate, FAL, and ElevenLabs directly. No credit markup, no provider tax.
- Ship a workflow as a Mini-App — Hide the graph, expose just inputs and outputs. Share a link, no install required.
- Build agents that drive workflows — Multi-step planning, tool calling, streaming. Drop them into any pipeline.
- Chat with your documents — Local SQLite-vec, embeddings, RAG. Your data never leaves the machine.
- Iterate visually, not via prompts — Click a node, change a value, re-run. Watch data flow through every edge.
Studio or Cloud
Same code, same workflows. Both AGPL-3.0.
NodeTool Studio — desktop
Mac, Windows, Linux. Local inference via Ollama, MLX, and GGUF. Works offline. Prompts and outputs stay on disk. BYOK for cloud providers when you want them.
Download Studio →NodeTool Cloud — browser
Hosted, no install. Same canvas, same nodes. BYOK for every cloud provider — OpenAI, Anthropic, Gemini, Replicate, FAL, ElevenLabs, HuggingFace. No local models.
Open Cloud →No credit markup. Cloud hosts the same code in this repo. Self-host the Docker images any time. You pay providers directly.
What you can build
Image and video
Flux, Qwen, Wan, Seedance, Sora, Veo, Kling on one canvas.
Movie Posters →Story to video
Prompt to storyboard to narration to animation to score.
Movie Trailer Generator →Sound and voice
Music, sound design, narration. ElevenLabs, MusicGen, Whisper in the graph.
Image to Audio Story →Agents
Multi-step agents that plan, call tools, and drive pipelines.
Fetch Papers →More patterns — pipelines, data, RAG, email — in the Cookbook.
Get started
- Download NodeTool for macOS, Windows, or Linux.
- Open a template, press Run.
- Edit, re-run, ship as a Mini-App.
Explore
- New here: Getting Started · Key Concepts · UI
- Building: Chat & Agents · Cookbook · Examples
- Self-hosting: Deployment · Configuration · API
- Extending: Developer Guide · Custom Nodes · CLI