A2UI (Agent-to-User Interface) is an open-source protocol and set of libraries developed by Google to enable AI agents to generate rich, interactive user interfaces instead of relying solely on text-based responses. The project introduces a declarative JSON format that allows agents to describe the structure, components, and behavior of a user interface, which is then rendered by the client using its own native components. This approach separates UI intent from UI implementation, making it possible for the same agent-generated interface to be rendered across different platforms such as web, mobile, and desktop applications. A key design principle of A2UI is security, as it avoids executing arbitrary code generated by models and instead restricts output to structured data that maps to a predefined catalog of trusted UI components. The system also supports incremental updates, allowing agents to progressively modify the interface as a conversation evolves.

Features

  • Declarative JSON format for agent-generated UI
  • Cross-platform rendering across web, mobile, and desktop
  • Security-first design with no executable code from agents
  • Incremental UI updates for dynamic interactions
  • Framework-agnostic integration with multiple UI stacks
  • Support for custom component catalogs and extensibility

Project Samples

Project Activity

See All Activity >

Categories

Agentic AI

License

Apache License V2.0

Follow A2UI

A2UI Web Site

Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform Icon
Gemini 3 and 200+ AI Models on One Platform

Access Google's best plus Claude, Llama, and Gemma. Fine-tune and deploy from one console.

Build, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of A2UI!

Additional Project Details

Programming Language

TypeScript

Related Categories

TypeScript Agentic AI Tool

Registered

2026-04-20