Repolode
Submit
wandb

wandb/openui

Describe a UI in plain language, see it rendered live, and iterate on it with any supported LLM.

Open-source alternative to:v0

View on GitHubWebsite
Stars
22,634
Forks
2,058
Open issues
89
Last commit
4 days ago

What is it?

OpenUI is an open-source tool for generating user interfaces from natural-language prompts. You describe the UI you want, and it renders the result live in the browser so you can request changes and see them applied immediately. It can also convert HTML into React, Svelte, Web Components and similar formats.

The app supports OpenAI, Groq, Anthropic, Gemini, Cohere, Mistral and any OpenAI-compatible endpoint. Through LiteLLM it can reach many other providers, and local models can be used via Ollama. Configuration is done with environment variables, and the project can run as a Docker container, from source with Python and uv, or in a Codespace or Gitpod workspace.

The project is built by Weights & Biases, which uses it to prototype tooling for LLM-based applications. It is positioned as an open alternative to v0.

Key features

  • 01Generates UI from text prompts and renders the result live.
  • 02Supports iterative changes to an existing design.
  • 03Converts HTML into React, Svelte, Web Components and other frameworks.
  • 04Connects to OpenAI, Groq, Anthropic, Gemini, Cohere, Mistral and OpenAI-compatible endpoints.
  • 05Runs local models through Ollama.
  • 06Ships as a Docker image or runs from source with Python.

Use cases

  • Prototyping interface ideas quickly from a written description.
  • Converting existing HTML mockups into React or Svelte components.
  • Experimenting with different LLM providers for UI generation.
  • Running UI generation fully on local models with Ollama.

Quick start

  1. 1

    Run the Docker container with your API keys

    docker run --rm --name openui -p 7878:7878 -e OPENAI_API_KEY -e ANTHROPIC_API_KEY -e OLLAMA_HOST=http://host.docker.internal:11434 ghcr.io/wandb/openui
  2. 2

    Open http://localhost:7878 in your browser and generate UIs

Things to know

  • Requires an API key from an LLM provider such as OpenAI, or a local Ollama setup, to generate UIs.
  • Described in the README as not as polished as commercial alternatives like v0.

Topics

#generative-ai#llm#ui-generation#react#tailwindcss#html#litellm#ollama#ai#html-css-javascript

FAQ

What is openui?
Describe a UI in plain language, see it rendered live, and iterate on it with any supported LLM. OpenUI is an open-source tool for generating user interfaces from natural-language prompts. You describe the UI you want, and it renders the result live in the browser so you can request changes and see them applied immediately. It can also convert HTML into React, Svelte, Web Components and similar formats.
Is openui free to use? What license does it have?
openui is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is openui still maintained?
Actively maintained. The last commit to openui was on Oct 16, 2026.
What can I use openui for?
Prototyping interface ideas quickly from a written description. Converting existing HTML mockups into React or Svelte components. Experimenting with different LLM providers for UI generation. Running UI generation fully on local models with Ollama.
How do I install openui?
Run the Docker container with your API keys: docker run --rm --name openui -p 7878:7878 -e OPENAI_API_KEY -e ANTHROPIC_API_KEY -e OLLAMA_HOST=http://host.docker.internal:11434 ghcr.io/wandb/openui Open http://localhost:7878 in your browser and generate UIs
Where can I get openui?
The source code and installation instructions are on GitHub: https://github.com/wandb/openui

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects