IT之家 News on November 12: A2UI is an open protocol for generative UI announced by Google at the end of 2025, allowing agents to reply not only with user text but also directly with UI interface content.
Today, Google officially released the A2UI 1.0 version, the first stable version of the protocol. Developers can now use it together with the open-source web,Android and iOS renderer SDKs as well as agent SDKs for Python, TypeScript and Dart.Companies including Atlassian, Alation, Bloomberg and ByteDance have already begun developing with it。
Google explained that in A2UI,the agent is responsible for describing the content to be displayed, and each app can draw the UI with its own native components. Whether the user connects to an agent in the company's own app or through a third-party AI assistant hosting MCP apps (such as Gemini or Claude), they get the same low latency, high trust and full native fidelity.
IT之家 learned from Google's official blog that the A2UI 1.0 version added bidirectional function calling, as well as extended support for accessibility and additional metadata.
The open-source renderers can draw A2UI screens on the web with React, Angular and Lit; render with Flutter on mobile, web and desktop; as well as SwiftUI on the iOS platform and Jetpack Compose on the Android platform.
The web and Flutter renderers also run inside MCP apps, so A2UI content can appear in AI assistants that support MCP apps, such as Claude and Gemini.