An open-source Next.js demo that recreates ChatGPT's Intelligent UI, streaming model answers as interactive maps, charts, forms and working tools built on OpenUI.
tambo-ai/tambo
Open-source React toolkit for building AI agents that render and update your own components as generative UI.
- Stars
- 11,197
- Forks
- 570
- Open issues
- 49
- Last commit
- 15 hours ago
What is it?
Tambo lets you register React components with Zod schemas. An LLM agent chooses which component fits a user's request, streams the props to it, and renders the result inside your app. Components can be one-off outputs such as charts and summaries, or interactable components that persist and update as the user refines a request, such as task boards or notes.
The SDK provides hooks like useTambo and useTamboThreadInput for messages, streaming state, and input handling. It also covers MCP server integration, local browser-side tools, additional context passing, auth tokens, and clickable suggestions. Bring your own API key for OpenAI, Anthropic, Gemini, Mistral, or any OpenAI-compatible provider.
The backend that manages conversation state and agent execution can be self-hosted via Docker. The hosted Tambo Cloud service is shutting down on October 31, 2026, and new signups are closed.
Key features
- 01Register React components with Zod schemas so the agent can choose and render them.
- 02Streams component props to the UI as the LLM generates them.
- 03Supports generative components for one-off results and interactable components that persist.
- 04Connects to MCP servers over HTTP, including tools, prompts, and sampling.
- 05Lets you define browser-side tools the agent can call, such as DOM actions or authenticated fetches.
- 06Works with OpenAI, Anthropic, Gemini, Mistral, and OpenAI-compatible providers.
Use cases
- Adding a chat assistant that shows charts or dashboards inside an existing React app.
- Building a task board or spreadsheet that users can modify through natural language.
- Connecting an in-app AI assistant to internal tools via MCP servers.
Quick start
- 1
Scaffold a new app with the Tambo CLI
npm create tambo-app my-tambo-app - 2
Enter the project folder
cd my-tambo-app - 3
Start the development server
npm run dev
Things to know
- Tambo Cloud is shutting down on October 31, 2026, and new signups are closed.
- Running it yourself requires following the self-hosting guide via Docker on your own infrastructure.
- You must bring your own LLM API key from a supported provider.
Topics
FAQ
- What is tambo?
- Open-source React toolkit for building AI agents that render and update your own components as generative UI. Tambo lets you register React components with Zod schemas. An LLM agent chooses which component fits a user's request, streams the props to it, and renders the result inside your app. Components can be one-off outputs such as charts and summaries, or interactable components that persist and update as the user refines a request, such as task boards or notes.
- Is tambo free to use? What license does it have?
- tambo is open source under the MIT license. Check the license terms before using it in commercial products.
- Is tambo still maintained?
- Actively maintained. The last commit to tambo was on Oct 21, 2026.
- What can I use tambo for?
- Adding a chat assistant that shows charts or dashboards inside an existing React app. Building a task board or spreadsheet that users can modify through natural language. Connecting an in-app AI assistant to internal tools via MCP servers.
- How do I install tambo?
- Scaffold a new app with the Tambo CLI: npm create tambo-app my-tambo-app Enter the project folder: cd my-tambo-app Start the development server: npm run dev
- Where can I get tambo?
- The source code and installation instructions are on GitHub: https://github.com/tambo-ai/tambo
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A TypeScript SDK for building agent-native apps with generative UI, shared state, and human-in-the-loop flows in React, Angular, Vue, and chat apps.
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.
An open source MCP server that connects AI agents, IDEs and apps to databases with prebuilt tools or custom tool definitions.
An automation platform for building agentic AI workflows in YAML that run across conversational channels, with tools, MCP, memory and RAG.
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.