
OpenUI
Not yet source-checkedLink check failingDescribe a UI in natural language and see it rendered live in HTML, React, Svelte, or Web Components
Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked How we rate
In short
OpenUI is an open-source tool that renders natural language prompts into live HTML, React, or Svelte UIs. It supports various LLMs and local models for free prototyping.
Frontend developers and design-engineering teams who want an open, self-hostable sketchpad for prompt-driven UI prototyping with a choice of hosted or local LLMs.
Non-technical users who want a managed no-code SaaS, or teams that need a governed design system with tokens, a11y guarantees, and Figma round-tripping.
OpenUI is an open-source (Apache-2.0) UI prototyping playground from Weights & Biases that lets you describe an interface in natural language and watch an LLM render it live in the browser. You type a prompt like "a pricing card with three tiers and a comparison table," and OpenUI produces working HTML/Tailwind, previews it in a sandbox, and lets you iterate by asking for changes ("make the middle tier stand out," "add a monthly/annual toggle"). Once the layout is close, you can convert the same component into React, Svelte, Vue, or Web Components without leaving the app.
The project is model-agnostic. It ships with adapters for OpenAI, Anthropic Claude, Google Gemini, Groq, Cohere, Mistral, and anything else routable through LiteLLM, plus Ollama for running local models (Llama, Qwen, etc.) with no per-token cost. That flexibility is the main reason teams pick it over closed hosted alternatives: you point it at your own key or your own GPU box, and the generated code is yours.
OpenUI is aimed at frontend developers, designers who write a bit of code, and internal-tools teams who want a fast sketchpad for component ideas before wiring anything into a real codebase. Typical workflows include roughing out marketing sections, exploring dashboard layouts, generating starter components for a design system, and using it as a teaching tool for prompt-driven development. The hosted demo at openui.fly.dev is a shared reference deployment; serious use is expected via `docker run` or a source install, where you control the models, rate limits, and data.
OpenUI is the most credible open-source answer to Vercel v0: same core loop of prompt-to-live-preview, but you own the code, you pick the model, and Ollama lets you run it end-to-end for free. The hosted fly.dev demo is unreliable and often 502s, so treat it as a teaser and self-host if you actually want to use it. Output is prototype-grade, not production design-system-grade.
— The AI Tool Bible editorial team
Pros
- ✅ Fully open source under Apache-2.0 with an active W&B-maintained repo
- ✅ Model-agnostic: OpenAI, Anthropic, Gemini, Groq, Cohere, Mistral, plus local Ollama models via LiteLLM
- ✅ Live in-browser preview of generated HTML/Tailwind with iterative edit prompts
- ✅ Converts generated components to React, Svelte, Vue, or Web Components on demand
- ✅ Runs locally via Docker or source, so prompts and code never leave your infra
- ✅ Ollama support means you can prototype UI with zero API cost on your own hardware
- ✅ Good teaching artifact for prompt-driven, LLM-assisted frontend work
Cons
- ⚠️ Public demo at openui.fly.dev is a shared instance and is frequently down or rate-limited (502s are common)
- ⚠️ Bring-your-own-key: no managed billing, no team accounts, no SSO out of the box
- ⚠️ Output quality tracks the underlying model; small local models produce noticeably weaker layouts
- ⚠️ Generated code is component-scoped scaffolding, not a full design system with tokens, a11y audits, or tests
- ⚠️ No native integration with Figma, Storybook, or existing component libraries
- ⚠️ Self-hosting requires Docker/Python know-how and your own model credentials
Facts
- Open source
- Yes
- Model used
- Model-agnostic via LiteLLM: OpenAI GPT-4o/4.1, Anthropic Claude 3.5/3.7, Google Gemini, Groq, Cohere, Mistral, and local Ollama models (Llama, Qwen, etc.)
- Hacker News
- 1 story · top 5 points · last Apr 6, 2024 · checked Nov 17, 2026
Where this tool sits
Use cases
Frequently asked
- How much does OpenUI cost to use?
- OpenUI is free and open-source under the Apache-2.0 license. The hosted demo is free, and self-hosting costs nothing. You only pay for the API keys of the LLMs you choose to plug in, or run local models via Ollama at zero token cost.
- Which AI models can I use with OpenUI?
- It is model-agnostic via LiteLLM, supporting OpenAI GPT-4o/4.1, Anthropic Claude 3.5/3.7, Google Gemini, Groq, Cohere, and Mistral. You can also run local models like Llama or Qwen using Ollama to avoid per-token costs.
- Can I export the generated UI to different frameworks?
- Yes. After generating an initial HTML/Tailwind preview, you can convert the same component into React, Svelte, Vue, or Web Components directly within the app without leaving the interface.
- Is OpenUI suitable for non-technical users?
- It is best for frontend developers and design-engineering teams. Non-technical users seeking a managed no-code SaaS should skip it, as serious use is expected via Docker or source install where you control models and data.
- What are the main use cases for OpenUI?
- It is ideal for AI-assisted UI prototyping, generating React scaffolds, converting HTML to Svelte or Vue, exploring dashboard layouts, and teaching prompt-driven development. It serves as a fast sketchpad for component ideas before integrating into real codebases.