An open source MCP server that connects AI agents, IDEs and apps to databases with prebuilt tools or custom tool definitions.
thesysdev/openui
A framework-agnostic Generative UI toolkit built around OpenUI Lang, a compact streaming language that lets LLMs produce renderable UI from your own component library.
- 스타
- 12,028
- 포크
- 820
- 열린 이슈
- 169
- 마지막 커밋
- 3시간 전
어떤 프로젝트인가요?
OpenUI is a Generative UI framework for letting language models produce interface elements instead of plain text. Its core is OpenUI Lang, a compact streaming-first language. Developers define the components a model may use, the toolkit generates a system prompt from that library, and the streamed model output is parsed and rendered progressively as tokens arrive.
The framework-agnostic core is paired with runtimes for React, Vue, Svelte, and Angular. The React packages also include prebuilt chat layouts and two built-in component libraries covering charts, forms, tables, and layouts. Additional packages target LangChain and LangGraph agents, the A2UI protocol, email generation with React Email, and a browser bundle for CDN or iframe embeds.
The project reports that OpenUI Lang uses up to 67% fewer tokens than equivalent JSON, with a benchmark suite included in the repository. A CLI scaffolds a working chat app with a single command.
핵심 기능
- 01Streaming renderer that displays model-generated UI progressively as tokens arrive.
- 02Prompt generation directly from the component library you allow the model to use.
- 03Runtimes for React, Vue, Svelte, and Angular on a framework-agnostic core.
- 04Prebuilt React chat layouts and built-in charts, forms, tables, and layout components.
- 05LangChain and LangGraph integration that streams OpenUI through AG-UI.
- 06Zod-based typed component contracts for props and structure.
활용 사례
- Building an AI assistant or copilot that answers with interactive charts, forms, or tables.
- Restricting model output to a vetted set of components in a production product.
- Adding generated UI to a LangGraph agent backend with a React frontend.
- Embedding generated interfaces in an iframe or static page via the browser bundle.
토픽
자주 묻는 질문
- openui은(는) 무엇인가요?
- A framework-agnostic Generative UI toolkit built around OpenUI Lang, a compact streaming language that lets LLMs produce renderable UI from your own component library. OpenUI is a Generative UI framework for letting language models produce interface elements instead of plain text. Its core is OpenUI Lang, a compact streaming-first language. Developers define the components a model may use, the toolkit generates a system prompt from that library, and the streamed model output is parsed and rendered progressively as tokens arrive.
- openui은(는) 무료로 사용할 수 있나요? 라이선스는 무엇인가요?
- openui은(는) MIT 라이선스의 오픈소스입니다. 상업용 제품에 사용하기 전에 라이선스 조건을 확인하세요.
- openui은(는) 아직 유지보수되고 있나요?
- 활발히 유지보수 중. openui의 마지막 커밋은 2026년 10월 19일입니다.
- openui은(는) 어디에 사용할 수 있나요?
- Building an AI assistant or copilot that answers with interactive charts, forms, or tables. Restricting model output to a vetted set of components in a production product. Adding generated UI to a LangGraph agent backend with a React frontend. Embedding generated interfaces in an iframe or static page via the browser bundle.
- openui은(는) 어디서 받을 수 있나요?
- 소스 코드와 설치 방법은 GitHub에 있습니다: https://github.com/thesysdev/openui
요약은 프로젝트 README를 바탕으로 AI가 작성했습니다. GitHub 통계는 매일 갱신됩니다.
관련 프로젝트
Self-hosted AI coworker platform where each agent gets its own browser, files and tools, with every action gated by policy and logged.
A modular Agentic RAG tutorial and project built with LangGraph, featuring hierarchical indexing, conversation memory, and query clarification.
Cross-platform team chat where AI agents are first-class teammates alongside humans, running on Cumora's cloud or your own machine.
An open-source chat interface where AI answers can be interactive, rendering explanations, comparisons, charts, and working tools built with CopilotKit and AG-UI.
A local MCP server that routes prompts from Cursor, VS Code, Windsurf or Claude Desktop to ChatGPT, Claude, Gemini, Perplexity, BYOK APIs or local Ollama models.