AG-UI and A2UI
Despite the naming similarities, AG-UI and A2UI serve very different and complementary roles in the agentic application stack.
AG-UI is the Agent–User Interaction protocol which connects your user-facing application to any agentic backend.
A2UI is a Declarative Generative UI spec, originated by Google, which agents can use to return UI widgets as part of their responses.
CopilotKit and AG-UI both fully support A2UI, as CopilotKit is a launch partner with Google of the official A2UI release.
This page explains how AG-UI and A2UI work together to enable powerful agent-user interactions.
The A2UI Composer - powered by CopilotKit
Generative UI Specifications
Generative UI Specs allow agentic chats to communicate in UIs, not only in text.
There are static, declarative, and open-ended generative UI specs on the market.
AG-UI supports them all
Types of Generative UI
Static
UI is chosen from a fixed set of hand‑built components.
Open-Ended
Arbitrary UI (HTML, iframes, free‑form content) is passed between agent and frontend.
Declarative
A structured UI specification (cards, lists, forms, widgets) is used between agent and frontend.
Several recently released specs have enabled agents to return generative UI, increasing the power and flexibility of the Agent↔User conversation.
A2UI, MCP-UI, and Open-JSON-UI are all Generative UI specifications. Generative UIs allow agents to respond to users not only with text but also with dynamic UI components.
CopilotKit and AG-UI both fully support A2UI, as CopilotKit is a launch partner with Google of the official A2UI release.
You can learn more about the different types of Generative UI and their specifications on our Generative UI page
Specification
Origin /
Maintainer
Purpose
A2UI
A declarative, LLM-friendly Generative UI spec. JSONL-based and streaming, designed for platform-agnostic rendering.
Open-JSON-UI
OpenAI
An open standardization of OpenAI's internal declarative Generative UI schema.
A2UI
Microsoft + Shopify
A fully open, iframe-based Generative UI standard extending MCP for user-facing experiences.
AG-UI: The Agent-User Interaction Protocol
AG-UI is a General Purpose Bi-Directional Agentic Frontend <> Agentic Backend Connection
AG-UI is not a generative UI specification — it is the Agent-User Interaction protocol that provides the bi-directional runtime connection between your user-facing application and any agentic backend.
AG-UI natively supports all of the above generative UI specs (including A2UI) and allows developers to define their own custom generative UI standards as well.
AG-UI Protocol
- •Provides the runtime connection between agentic backend and user-facing app
- •Handles bi-directional communication and state synchronization
- •Focuses on how agents and applications communicate
How They Work Together
AG-UI and generative UI specifications are complementary technologies that work together seamlessly
Agents generate UI using a generative UI spec like A2UI, describing the components they want to create.
AG-UI transports that specification from the agent to the application over the bi-directional runtime connection..
The application renders the UI components according to the spec, creating the dynamic interface.
User interactions flow back through AG-UI to the agent, enabling real-time collaboration.
This combination gives developers the flexibility to choose their preferred generative UI format while providing a robust, standardized way to connect agents with user-facing applications.
Ready to Get Started?
Explore the protocol specification and start building agentic applications with CopilotKit and AG-UI.
