Install NodeTool, open a template, run it, edit it, ship it as a Mini-App.

Step 1 — Install

Requirements

Component Minimum Recommended
RAM 8 GB 16 GB+
Disk 10 GB free 50 GB+ for models
GPU None 8 GB+ VRAM for local inference
OS macOS 13+, Windows 10+, Ubuntu 22+ Latest

No GPU? Use cloud providers with your own keys. See hardware notes.

Install

  1. Download from nodetool.ai
  2. Run the installer
  3. Launch — no setup wizard

Dashboard

Python and inference engines install on demand the first time you use local models. See the installation guide for platform notes.

Local models (optional)

  1. Open Models in the sidebar
  2. Pick:
    • Flux or Qwen Image for images (8–12 GB VRAM)
    • Llama or Qwen for text
  3. Wait for downloads (~20 GB)

Cloud-only: open Settings → Providers, paste your key from OpenAI, Anthropic, or Google. Skip the local download.


Step 2 — Run a workflow

Open a template from the Dashboard.

Templates

Movie Posters

  1. Dashboard → Templates → Movie Posters
  2. The graph opens: inputs on the left, an agent in the middle, image generator on the right, preview at the end.
  3. Type into the inputs:
    • Title: Ocean Depths
    • Genre: Sci-Fi Thriller
    • Audience: Adults who love mystery
  4. Press Ctrl/⌘ + Enter to run.

Creative Story Ideas

Editor

  1. Dashboard → Templates → Creative Story Ideas
  2. Set inputs:
    • Genre: Cyberpunk
    • Character: Rogue AI detective
    • Setting: Neon-lit underwater city
  3. Run it.

Step 3 — Edit

  1. Save with Ctrl/⌘ + S.
  2. Change inputs and re-run.
  3. Click a node to see its settings on the right. Hover a connection to see the data flowing through it. Press Space and search “Preview” to drop a preview node anywhere on the canvas.

Step 4 — Ship as a Mini-App

A Mini-App hides the graph and exposes only the inputs and outputs.

  1. Open the workflow.
  2. Click Mini-App in the toolbar.

For a custom UI, see VibeCoding.


Next

Goal Page
How workflows work Key Concepts
Full interface User Interface, Workflow Editor
More examples Gallery, Cookbook
Models and providers Models & Providers
Deploy Deployment
Stuck Troubleshooting, Debugging

Discord · GitHub · Glossary