A2UI: A Protocol for Agent-Driven Interfaces

Source: Hacker News

[Image: A2UI Logo]

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.

Status: Early Stage Public Preview
A2UI is currently v0.8 (Public Preview). The specification and implementations are functional but are still evolving. We are opening the project to foster collaboration, gather feedback, and solicit contributions (e.g., on client renderers). Expect changes.

At a Glance

• Version: v0.8
• License: Apache 2.0
• Created by: Google, with contributions from CopilotKit and the open‑source community
• Repository: Active development on GitHub

Problem solved: 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—a universal UI language.

Key Benefits

• Secure by Design – Declarative data format, not executable code. Agents can only use pre‑approved components from your catalog, preventing UI injection attacks.
• LLM‑Friendly – Flat, streaming JSON structure designed for easy generation. LLMs can build UIs incrementally without needing 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 a complete response.

Get Started in 5 Minutes

• Quickstart Guide – Run the restaurant‑finder demo and see A2UI in action with Gemini‑powered agents.
• Core Concepts – Understand surfaces, components, data binding, and the adjacency‑list model.
• Developer Guides – Integrate A2UI renderers into your app or build agents that generate UIs.
• Protocol Reference – Dive into the complete technical specification and message types.

How It Works

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 generates a custom form for landscaping needs.

Your browser does not support the video tag.

Custom Components: Interactive Charts & Maps

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

Your browser does not support the video tag.

A2UI Composer

CopilotKit provides a public A2UI Widget Builder you can try out.