Verified project record
thesysdev/openui
thesysdev/openui is a full-stack, renderer-agnostic Generative UI framework built around a compact, streaming-first language called OpenUI Lang that uses up to 67% fewer tokens than JSON. It provides official React support, built-in component libraries, and progressive rendering so large language models can emit interactive UI incrementally as tokens arrive.
Project overview
By using a streaming-first language that uses up to 67% fewer tokens than JSON, the framework directly addresses the latency and cost challenges of generating structured, interactive UI from large language models.
- Project type
- AI Agent · Infrastructure
- Use cases
- Knowledge Q&A · Coding & Development
- Deployment
- Refer to project documentation
- License
- MIT
Best for
- Developers and AI engineers who need to render structured, interactive UI from large language model output with low latency and lower token consumption.
- Creators building applications in React, Vue 3, or Svelte 5 who want framework-specific bindings and built-in component libraries for generative UI.
Key capabilities
- A compact, streaming-first language for model-generated UI designed to emit UI incrementally as tokens arrive.
- Parses and renders model output progressively in React as tokens arrive.
- Generates model instructions directly from the components you allow.
- Provides charts, forms, tables, layouts, and more, ready to use or extend.
- React Email component definitions plus prompt options for model-generated emails.
- Provides Vue 3 and Svelte 5 bindings for defining model-renderable components and rendering streamed OpenUI Lang.
- Core parser, prompt-generation, runtime-evaluation, and type layer with no React, Vue, or Svelte dependency.
- Ships an Agent Skill so AI coding assistants can help you scaffold, build, and debug Generative UI apps using OpenUI Lang.
Limitations and risks
- Using the framework requires connecting a large language model, which may incur costs depending on your chosen API provider.
- Setting up and using the framework requires development work, including defining or integrating component libraries and connecting an LLM API.
Getting started
- Run npx @openuidev/cli@latest create --name genui-chat-app to scaffold a new project. Then enter the directory with cd genui-chat-app, add your key via echo "OPENAI_API_KEY=sk-your-key-here" > .env, and start the development server with npm run dev.
- Generation requires an external LLM API such as the OpenAI API. The model must be capable of generating OpenUI Lang based on the component library prompts you provide.
Evidence and sources
- README: OpenUI is a full-stack, renderer-agnostic Generative UI framework built around a compact, streaming-first language. It offers official React support with built-in component librar…
- README: OpenUI Lang is designed for model-generated UI that needs to be both structured and streamable.
- README: - **Token efficiency** - Up to 67% fewer tokens than equivalent JSON (see [benchmarks](./benchmarks)).
- README: - **OpenUI Lang** - A compact language for structured UI generation designed for streaming output. - **Built-in component libraries** - Charts, forms, tables, layouts, and more, r…
- README: | [`@openuidev/react-headless`](./packages/react-headless) | Bring-your-own React chat UI | Headless chat state, streaming adapters, and message format converters |
AI 搜索
把需求说清楚,让项目选择更有依据
告诉我们你要解决什么、运行在哪里、哪些条件不能妥协。雷达会从已核验项目中给出主推荐、备选和采用前检查。
目标你最终想完成什么
环境本地、云端或现有技术栈
硬条件部署、界面、语言与 License
从一个真实需求开始点击只会填入搜索框,你可以继续修改
今日榜单
0