AI News

Google's open-source cross-platform protocol A2UI 1.0 launches, adopted by ByteDance and other companies

English text is being prepared.Updated Nov 12 15:15

AI summary

Google has officially released the open protocol for generative UI, A2UI 1.0, the first stable version of the protocol. Developers can use it with the open-source web, Android, and iOS renderer SDKs as well as the Python, TypeScript, and Dart agent SDKs. Version 1.0 adds bidirectional function calling and expands support for accessibility and additional metadata. Companies such as Atlassian, Alation, Bloomberg, and ByteDance have begun developing with it, and A2UI content can also appear in AI assistants such as Claude and Gemini that support MCP applications.

Why read this

AI score 67

The original text lists the bidirectional function calling and multi-platform renderers newly added in 1.0, so readers can judge how to integrate agent-generated UI output.

Topics

Tags

Body · AI translation

Let AI Reply Directly to Users with UI Interfaces: Google Open-Sources Cross-Platform Protocol A2UI Version 1.0, ByteDance Already Using It

English text is being prepared.

English text is being prepared.

Today, Google officially released A2UI version 1.0, the first stable version of the protocol. Developers can now use it together with open-source web, Android, and iOS renderer SDKs as well as agent SDKs for Python, TypeScript, and Dart. Companies such as Atlassian, Alation, Bloomberg, and ByteDance have already begun developing with it.

Google explains that in A2UI, the agent is responsible for describing the content to be displayed, and each app can draw the UI using its own native components. Whether users access the agent within a company's own app or through a third-party AI assistant hosting an MCP app (such as Gemini or Claude), they get the same low latency, high trust, and full native fidelity.

▲ The same request answered via text and A2UI, then shown with the same view on a laptop as well

English text is being prepared.

The open-source renderers can draw A2UI screens on the web using React, Angular, and Lit; render with Flutter on mobile, web, and desktop; and use 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.

Source

English text is being prepared.