What is OpenUI?
OpenUI is an open-source tool designed to make building UI components fun, fast, and flexible. It is used at W&B to prototype next-generation tooling for building powerful applications on top of LLMs. OpenUI lets you describe UI using your imagination and see it rendered live, allowing for easy conversion to React, Svelte, Web Components, and more.
Key Features
- Visual UI component builder
- Supports multiple LLM services (OpenAI, Groq, Gemini, Anthropic, Cohere, Mistral)
- Docker and Python support
- Live demo available
- LiteLLM integration for connecting to various LLM services
- Groq model support
Running Locally
- Docker (preferred): Forward API keys and run Docker container.
export ANTHROPIC_API_KEY=xxx export OPENAI_API_KEY=xxx 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
- From Source / Python: Clone repository, set up virtual environment, install dependencies, and run the server.
git clone https://github.com/wandb/openui cd openui/backend pip install . export OPENAI_API_KEY=xxx python -m openui
Live Demo
Try the live demo at http://openui.fly.dev.
Development
- Codespace: Set up Codespace with necessary environment variables and run the server.
- Gitpod: Use OpenUI via Gitpod with preconfigured OpenAI.