In simple English
This tool turns text descriptions into working web page designs. You type what you want to see, and an artificial intelligence generates the buttons, boxes, and text on your screen. You can ask for changes in plain language until the design looks right. Then you can copy the code to use in your own project. It works with commercial language models and free local models.
What it is
OpenUI is an open-source web application for generating and editing user interface components through natural language prompts. It acts as a self-hosted alternative to proprietary design tools like v0.
What it is good for
Solo builders and designers who want to quickly prototype web pages and export clean HTML or framework code without writing it by hand from scratch.
- Renders generated user interfaces live in your browser as you type changes.
- Supports many backend language models including OpenAI, Anthropic, and local models via Ollama.
- Provides a simple Docker container for running the entire app locally with one command.
- Requires an external API key or a powerful local computer running Ollama to generate designs.
- Generated code often needs manual cleanup and styling adjustments before production use.
- Requires some familiarity with the command line to set up environment variables and run Docker.
Writing interface components by hand from scratch
Ollama
- GoogleChromeLabs/squoosh26k stars
A web page that compresses images in the browser and shows you the result before you save it.
- simple-icons/simple-icons26k stars
More than 3,400 brand logos as single-colour SVG files, released into the public domain.
- phosphor-icons/core394 stars
The raw SVG files and the catalogue for the Phosphor icon family, with no framework package attached.
docker run --rm --name openui -p 7878:7878 -e OPENAI_API_KEY ghcr.io/wandb/openui