Frequently asked questions

NodeTool is the open creative AI workspace. Every major model from every major provider — FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, and more — wired into one node-based canvas you run on your own machine or in the browser. Image, video, music, and text live on the same canvas, alongside planning agents that run multi-step jobs.

Yes. The full codebase is AGPL-3.0 on GitHub. Studio and Cloud share the same source — no closed-source layer, no "pro" tier hiding the good features. Self-host any time.

BYOK is bring your own keys. You connect your own provider accounts and pay each provider directly at their list price. NodeTool never marks up model calls, never issues proprietary credits, and never runs inference on its own servers. Your keys, your bill, your data.

No. There are no credits and no markup. You bring your own API keys and pay each provider their list price directly. You can also run local models with Ollama, MLX, or llama.cpp in the desktop app for no per-call cost at all.

Studio is the desktop app: free, open source, runs on your machine, and supports local models via MLX, Ollama, and GGUF. Cloud is the same workspace in the browser — zero setup, no GPU required, and your keys still go to providers directly. Same workflows either way.

Frontier models including Flux, Seedance, Wan, Veo, Kling, Hailuo, Qwen Image, Whisper, ElevenLabs, and Suno — called through providers like FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, Together, Groq, Mistral, OpenRouter, and HuggingFace. Local inference runs via MLX, Ollama, llama.cpp, vLLM, and LM Studio.

Yes. NodeTool Studio runs open-weight models on your own hardware through MLX (Apple Silicon), Ollama, llama.cpp, vLLM, and LM Studio. Nothing leaves your machine unless you call a cloud provider yourself.

ComfyUI is a node editor for diffusion models. NodeTool is the studio around it: image, video, music, and words on one canvas, every major model a click away, and editing tools — masks, inpaint, relight, layers — built in. Both are node-based and open source.

Closed canvases lock you into a credit system and a curated model roster. NodeTool is open source and BYOK. Your workflows, files, and keys belong to you, and you can switch providers the moment a better model ships.

A node-based workflow is a pipeline you build by connecting boxes (nodes) on a canvas instead of writing code. Each node does one thing — load an image, call a model, crop a video — and edges carry data from one node's output to the next node's input. The whole graph runs top to bottom, so you can see and rewire every step.

A diffusion model generates images (or video, or audio) by starting from random noise and removing it step by step until a coherent result emerges, guided by your prompt. Flux, Stable Diffusion, and most image generators are diffusion models. In NodeTool you run them as nodes alongside everything else.

RAG is retrieval-augmented generation: before a language model answers, it retrieves relevant chunks from your own documents and feeds them in as context, so the answer is grounded in your data instead of only the model's training. NodeTool has built-in vector search and document nodes to build RAG pipelines on the canvas.

A planning agent takes a goal, breaks it into steps, picks a model or tool for each step, and executes them in order — adjusting as it goes. In NodeTool an agent is a node on the canvas, so you can wire its output into the rest of your workflow.