A Protocol for Agent-Driven Interfaces

A2UI enables AI agents to generate rich, interactive user interfaces that render natively across web, mobile, and desktop—without executing arbitrary code.

Specification Versions

Version	Status	Description
v0.8	Stable	Current production release. Surfaces, components, data binding, adjacency list model.
v0.9	Draft	Adds createSurface, client-side functions, custom catalogs, and the extension specification. Evolution guide →

A2UI is Apache 2.0 licensed, created by Google with contributions from CopilotKit and the open source community, and is in active development on GitHub.

A2UI solves the following problem: how can AI agents safely send rich UIs across trust boundaries?

Instead of text-only responses or risky code execution, A2UI lets agents send declarative component descriptions that clients render using their own native widgets. It's like having agents speak a universal UI language.

This repository contains: - A2UI specifications (v0.8 stable, v0.9 draft). - Implementations for renderers (Angular, Flutter, Lit, Markdown, etc.) on the client side. - Transports like A2A which communicate A2UI messages between agents and clients.

• Secure by Design

  ---

  Declarative data format, not executable code. Agents can only use pre-approved components from your catalog—no UI injection attacks.

• LLM-Friendly

  ---

  Flat, streaming JSON structure designed for easy generation. LLMs can build UIs incrementally without perfect JSON in one shot.

• Framework-Agnostic

  ---

  One agent response works everywhere. Render the same UI on Angular, Flutter, React, or native mobile with your own styled components.

• Progressive Rendering

  ---

  Stream UI updates as they're generated. Users see the interface building in real-time instead of waiting for complete responses.

Get Started in 5 Minutes

• Quickstart Guide

  ---

  Run the restaurant finder demo and see A2UI in action with Gemini-powered agents.

  Get started

• Core Concepts

  ---

  Understand surfaces, components, data binding, and the adjacency list model.

  Learn concepts

• Developer Guides

  ---

  Integrate A2UI renderers into your app or build agents that generate UIs.

  Start building

• Protocol Specifications

  ---

  Dive into the complete technical specs: v0.8 (stable) · v0.9 (draft)

  Read the v0.8 spec

How It Works

The typical interaction flow consists of these steps:

1. User sends a message to an AI agent
2. Agent generates A2UI messages describing the UI (structure + data)
3. Messages stream to the client application
4. Client renders using native components (Angular, Flutter, React, etc.)
5. User interacts with the UI, sending actions back to the agent
6. Agent responds with updated A2UI messages

A2UI in Action

Landscape Architect Demo

Watch an agent generate all of the interfaces for a landscape architect application. The user uploads a photo; the agent uses Gemini to understand it and generate a custom form for landscaping needs.

Custom Components: Interactive Charts & Maps

Watch an agent chose to respond with a chart component to answer a numerical summary question. Then the agent chooses a Google Map component to answer a location question. Both are custom components offered by the client.

A2UI Composer

CopilotKit has a public A2UI Widget Builder to try out as well.