Concepts Components Blog Roadmap
Get Started
The Standard Protocol for Agentic UI

Don't Just Chat.
Speak UI.

A2UI is the missing layer between LLMs and your frontend.
Turn "text bubbles" into rich, native, interactive applications.

Trusted by Developers building the Next Gen of Apps

The "Handshake" for Generative UI

A2UI (Agent-to-User Interface) isn't a library component—it's a protocol. It solves the biggest problem in AI today: How do intelligent agents safely control visual interfaces?

Instead of writing dangerous HTML, A2UI agents negotiate intent via structured JSON. Your app says "I can render a Chart," and the Agent says "Here is the data."

🧱

JSON, Not Code

Safe by design. The Agent sends a schema, your Codebase renders the view. No injections.

⚡️

Native Performance

Zero visual lag. Renders as native React/Vue/Flutter components, indistinguishable from handwritten code.

🔄

Full Control

You define the design system. The Agent just uses the "Lego bricks" you provide.

Powering Next-Gen
Agentic Experiences

✈️

Travel Agents

Don't just chat about flights. Show real-time availability, seat maps, and booking flows directly in the conversation.

🛍️

Conversational Commerce

Turn browsing into buying. Display product carousels, size guides, and checkout buttons without leaving the chat.

📊

Data Analyst

Visualise SQL queries instantly. Render interactive line charts, pivot tables, and heatmaps from raw data.

How A2UI Works

1

Define

Create a component registry in your codebase mapping JSON types to React/Vue components.

2

Prompt

Instruct your LLM (GPT-4, Gemini) to output JSON matching your schema.

3

Render

The `<AIOutput />` component parses the stream and renders native UI instantly.

Protocol Flow

A2UI End-to-End Data Flow

Agent generated UIs crossing trust boundaries safely using declarative schemas.

The Problem: Agents need to speak UI

Text-only interactions are slow and inefficient for complex tasks. Instead of a clunky back-and-forth about availability, A2UI allows agents to instantly render a bespoke booking interface.

Comparison: Text Chat vs A2UI Reserve Table
Text Chat A2UI Interface

A2UI in Action

Watch an agent generate a complete landscape architect application interface from a single photo upload.

Trusted by Industry Leaders

"

A2UI was a great fit for Flutter's GenUI SDK because it ensures that every user, on every platform, gets a high quality native feeling experience.

V
Vijay Menon
Engineering Director, Dart & Flutter
"

It gives us the flexibility to let the AI drive the user experience in novel ways... Its declarative nature and focus on security allow us to experiment quickly and safely.

D
Dimitri Glazkov
Principal Engineer, Google Opal Team
"

A2UI changes that with a 'native-first' approach: Agents send a description of UI components, not code. Your app maps these to its own trusted design system, maintaining perfect brand consistency and security.

M
Minko Gechev
Product Lead, Angular @ Google

Frequently Asked Questions

Is A2UI safe to use?
Yes. Unlike solutions that generate and execute raw HTML or JavaScript (which pose severe XSS risks), A2UI is purely data-driven. The LLM produces JSON, and your client application strictly controls which components can be rendered.
Does it work with next.js / Vercel AI SDK?
Absolutely. A2UI is a protocol, not a framework lock-in. You can use it alongside the Vercel AI SDK, LangChain, or any other agent orchestration tool. We provide adapters for easy integration.
Is it totally free?
Yes. A2UI is an open-source standard (Apache 2.0). You can use it in personal and commercial projects without restriction. Check out the GitHub repository.