About docs-server
docs-server is an MCP server published by git+assistant-ui in the Developer Tools category: mCP server for assistant-ui documentation and examples.
Install
npx @assistant-ui/mcp-docs-serverclaude mcp add assistant-ui -- npx -y @assistant-ui/mcp-docs-servernpx -y @assistant-ui/mcp-docs-serverThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about docs-server
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
4 checks have not been run yet.
README
The UX of ChatGPT in your React app 💬🚀
assistant-ui is an open source TypeScript/React library to build production-grade AI chat experiences fast.
- Handles streaming, auto-scrolling, accessibility, and real-time updates for you
- Fully composable primitives inspired by shadcn/ui and cmdk — customize every pixel
- Works with your stack: AI SDK, LangGraph, Mastra, or any custom backend
- Broad model support out of the box (OpenAI, Anthropic, Mistral, Perplexity, AWS Bedrock, Azure, Google Gemini, Hugging Face, Fireworks, Cohere, Replicate, Ollama) with easy extension to custom APIs
Why assistant-ui
- Fast to production: battle-tested primitives, built-in streaming and attachments
- Designed for customization: composable pieces instead of a monolithic widget
- Great DX: sensible defaults, keyboard shortcuts, a11y, and strong TypeScript
- Enterprise-ready: optional chat history and analytics via Assistant Cloud
Getting Started
Run one of the following in your terminal:
npx assistant-ui create # new project
npx assistant-ui init # add to existing project
Features
-
Build: composable primitives to create any chat UX (message list, input, thread, toolbar) and a polished shadcn/ui theme you can fully customize.
-
Ship: production-ready UX out of the box — streaming, auto-scroll, retries, attachments, markdown, code highlighting, and voice input (dictation) — plus keyboard shortcuts and accessibility by default.
-
Generate: render tool calls and JSON as components, collect human approvals inline, and enable safe frontend actions.
-
Integrate: works with AI SDK, LangGraph, Mastra, or custom backends; broad provider support; optional chat history and analytics via Assistant Cloud (single env var).
Backends
-
Assistant Cloud: managed chat persistence and analytics. Deploy with the Cloud Starter template; bring any model/provider.
-
AI SDK: integration with Vercel AI SDK; connect to any supported provider.
-
LangGraph: integration with LangGraph and LangGraph Cloud; connect via LangChain providers.
-
Mastra: integration with Mastra agents/workflows/RAG; model routing via Vercel AI SDK; optional Mastra Cloud.
-
Custom: use assistant-ui on top of your own backend/streaming protocol.
Customization
assistant-ui takes a Radix-style approach: instead of a single monolithic chat component, you compose primitives and bring your own styles. We provide a great starter config; you control everything else.

Sample customization to make a Perplexity lookalike:

Traction
assistant-ui is the most popular UI library for building AI chat.
Hundreds of companies and projects use assistant-ui to build in-app AI assistants, including , , , , , , , , , , and more.

Demos
Community & Support
Backed by Y Combinator. Building something with assistant-ui? We’d love to hear from you.
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.
