wandb/openui

OpenUI let's you describe UI using your imagination, then see it rendered live.

What it solves

Building user interface (UI) components manually is often a slow and tedious process. OpenUI simplifies this by allowing users to describe the interface they want in plain language and see it rendered instantly, speeding up the prototyping and design phase of application development.

How it works

OpenUI uses Large Language Models (LLMs) to translate natural language descriptions into UI code. It integrates with various model providers via LiteLLM, supporting OpenAI, Groq, Gemini, Anthropic, and local models via Ollama. Users can describe a UI, request iterative changes, and convert the generated HTML into different frameworks like React, Svelte, or Web Components.

Who it’s for

Developers and designers who want to quickly prototype UI components using AI, as well as teams looking for an open-source alternative to tools like v0.

Highlights

  • Live Rendering: See UI components rendered in real-time based on text descriptions.
  • Multi-Framework Support: Convert generated HTML to React, Svelte, and Web Components.
  • Broad Model Compatibility: Works with a variety of LLMs including proprietary APIs and local models via Ollama.
  • Iterative Design: Ability to ask for specific changes to the rendered UI to refine the design.

Related

  • Project
    thesysdev/openui

    OpenUI is a framework‑agnostic, streaming‑first UI library that lets LLMs generate UI components using a compact language (OpenUI Lang). It provides parsers, prompt generators, and runtime bindings for React, Vue, Svelte, Angular, plus a CLI for scaffolding apps. The language reduces token usage by ~50 % versus JSON, enabling progressive rendering of model‑generated interfaces.

  • Project
    AGenUI/AGenUI

    AGenUI is a production-grade SDK that implements Google's A2UI v0.9 protocol to render LLM-generated interactive UI in real time on iOS, Android, and HarmonyOS. A shared C++ core handles parsing, layout, and diffing while native renderers draw the components, giving 22 built-in UI components, custom component registration, Function Call support, a self-contained JSON catalog schema for constraining LLM output, an agent skill for turning natural language into UI protocol messages, and a local Studio workbench for prototyping.

  • Project
    assistant-ui/assistant-ui

    assistant‑ui is a TypeScript/React library that provides composable, production‑ready chat UI components for AI assistants. It works with many LLM backends via typed runtimes, handles streaming, markdown, tool‑call rendering, and offers a CLI to scaffold or inject the UI into Next.js projects. MIT‑licensed and backed by Y Combinator.

  • Project
    vercel-labs/json-render

    json-render is a generative UI framework that lets AI create interfaces from prompts while staying safe and predictable. It works by constraining AI output to a catalog of defined components and actions, which are then rendered across many platforms.