Tambo is a React-oriented AI orchestration framework that enables integration of “generative UI” components—that is, components that can be dynamically rendered or updated in response to AI decisions or prompts. It acts as the bridge between an AI assistant and the React front end, letting your AI agent not only send text responses, but also generate interactive UI elements (forms, charts, dashboards, etc.). The library includes tools to scaffold a Tambo app, manage state, and integrate with its backend protocol (Model Context Protocol, or MCP). Developers use Tambo to shift UI logic toward the AI model: instead of hardcoding UI flows, the AI can decide what component to show next. Tambo also supports streaming updates (i.e. progressively rendering UI) and embedding interactions between LLM outputs and front-end state.
Features
- Define custom UI components with props schemas (e.g. using Zod) and register them so the LLM can render them dynamically inside chat threads
- Templates / scaffolding via commands like npx tambo create-app to get starter projects
- Streaming responses (streamResponse: true) to allow gradual output from assistant threads
- Support for “tools” (functions) that AI can invoke, with schema-defined args and returns
- React SDK (frontend) to wrap app in a provider, message thread input hooks, component rendering in the UI etc.
- Showcases / examples and documentation for how to build with generative UI, and component library (UI library) to leverage existing components