tambo

Hi HN — cofounder Michael here. We've been building Tambo for about a year, and just released our 1.0. We make are making it easier to register React components with Zod schemas, a build an agent picks the right one and renders the right props. We handle many of the complications with building generative user interfaces like: managing state between the user, the agent, and react component, rendering partial props, and we handle auth between your user, and MCP. We also support adding MCP servers and most of the spec. We are 100% open-source and currently have 8k+ GitHub stars, thousands of developers, and over half-millions messages processed by our hosted service. If you're building AI agents with generative UI, we'd like to hear from you.

It's a React app using NextJS, and behind the scenes it uses Tambo to respond to messages and automatically control the tabs component! https://github.com/tambo-ai/tambo

Hey HN — we’ve been building tambo-ai over the last year: an open-source framework for adding high-quality, AI-powered chat experiences inside your own React apps. With OpenAI’s ChatKit launching yesterday (https://github.com/openai/chatkit-js), we wanted to share an open, model-agnostic alternative that supports the same core features, but works with any model, any backend, and your existing UI components. Features: - Drop-in chat interface with streaming, threads, and message management - Deep UI customization: render your own React components in chat - Tool/workflow integration with visualization of agent actions - Interactive widgets (forms, tables, charts) inside chat - Attachment and file handling - Model-agnostic adapters for OpenAI, Anthropic, or local models - Full MCP support Why: ChatKit is a beautiful, batteries-included SDK —

UI library site: https://ui.tambo.co/ You can check out our generative graph, form, and map. We also have a set of components for “framing” the AI assistant. But you can also roll your own or render them outside of the chat experience. In our repository, we have a list of additional components we plan to build. Upcoming Components: https://github.com/tambo-ai/tambo/issues?q=sort:updated-desc... Let us know what you think. — Michael

Hi HN-- Tambo is a React SDK that lets your app render and control UI components based on natural language input. We are hooked on Cursor and want all our apps (Stripe, Vercel, GitHub) to have the same experience. I should be able to type `update env key` and get a UI to add it. Tambo lets an AI assistant render or update the state of registered React components. It can fetch context via MCP (Model Context Protocol) or client-side fetches (similar to OpenAI tool calls). The SDK handles streaming messages and prop updates, maintains thread history, and passes context across turns. It’s BYOM (Bring Your Own Model) and works with Next.js, Remix, Vite, and React Native. If you’re building a “Cursor for X” (spreadsheets, video, design, etc.), check it out. Yesterday, we went 100% open source. Docs: https://docs.tambo.co GitHub: https://tambo.c

Hey! We're working on a React SDK + API to make it simple to build apps with natural language interfaces, where AI can interact with the components on screen on behalf of the user. The basic setup is: Register your react components, tools, and MCP servers, and a way for users to send messages to Tambo, and let Tambo respond with text or components, calling tools when needed. Use it to build chat apps, copilots, or completely custom AI UX. The goal is to provide simple interfaces for common AI app features so we don't have to build them from scratch. Things like: - thread storage/management - streaming props into generated components - MCP and custom tool integration - passing component state to AI plus some pre-built UI components to get started. Would love feedback or contributions!

Hi HN — I’m Michael. We created tambo-ai after hitting the same wall: LLMs are great at generating text, but awkward at driving interactive UI with state. Tambo is a React package that lets AI generate components that: * Persist state via context + hooks * Stream responses * Preserve history * Suggest next actions * Component library You import components directly — no black boxes. Everything’s inspectable and customizable. This is our first release. We’d love feedback on the dev experience, architecture, or anything that’s unclear. * Site: [https://tambo.co](https://tambo.co) * GitHub: [https://github.com/tambo-ai/tambo](https://github.com/tambo-ai/tambo) * UI Library: [https://ui.tambo.co](https://ui.tambo.co) — Michael