Skip to main content
AG-UI, or Agent-User Interaction Protocol, is a protocol standarizing how AI agents connect to front-end applications.

​
Example usage

1

Install the backend dependencies

2

Run the backend

Now let’s run a AGUIApp exposing an Agno Agent. You can use the previous code!
3

Run the frontend

You can use Dojo, an advanced and customizable option to use as frontend for AG-UI agents.
  1. Clone the project: git clone https://github.com/ag-ui-protocol/ag-ui.git
  2. Follow the instructions here to learn how to install the needed dependencies and run the project.
  3. Remember to install the dependencies in /ag-ui/typescript-sdk with pnpm install, and to build the Agno package in /integrations/agno with pnpm run build.
  4. You can now run your Dojo! It will show our Agno agent as one of the available options.
4

Chat with your Agno Agent

Done! If you are running Dojo as your front-end, you can now go to http://localhost:3000 in your browser and chat with your Agno Agent.
AG-UI Dojo screenshot You can see more examples in our AG-UI integration examples section.

​
Core Components

  • AGUIApp: Wraps Agno agents/teams for in a FastAPI app.
  • serve: Serves the FastAPI AG-UI app using Uvicorn.
AGUIApp uses helper functions for routing.

​
AGUIApp Class

Main entry point for Agno AG-UI apps.

​
Initialization Parameters

Provide agent or team, not both.

​
Key Method

​
Endpoints

Endpoints are available at the specified prefix (default /v1).

​
1. POST /agui

This is the main entrypoint to interact with your Agno Agent or Team. It expects a RunAgentInput object (from the ag-ui-protocol package) as defined by the protocol. You can read more about it in their docs.

​
Serving the Application (serve)

Serves the FastAPI app using Uvicorn.

​
Parameters

You can check some usage examples in our AG-UI integration examples section. You can also check the CopilotKit docs on working with Agno, to learn more on how to build the UI side.