AG-UI

Expose agents via the AG-UI protocol for frontend integration.

The AG-UI interface exposes any Agno agent or team via the AG-UI protocol, enabling real-time streaming to compatible frontends like Dojo and CopilotKit.

Quick Start

agui_agent.py

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.os.app import AgentOS
from agno.os.interfaces.agui import AGUI

agent = Agent(name="Assistant", model=OpenAIResponses(id="gpt-5.4"))

agent_os = AgentOS(
    agents=[agent],
    interfaces=[AGUI(agent=agent)],
)
app = agent_os.get_app()

if __name__ == "__main__":
    agent_os.serve(app="agui_agent:app", reload=True, port=9001)

uv pip install 'agno[agui]'
python agui_agent.py

How It Works

Concept	Behavior
Protocol	AG-UI standard for agent-to-frontend communication
Streaming	Real-time token streaming with tool call visibility
Custom Events	Stream structured data (charts, profiles) to frontend
Frontends	Works with Dojo, CopilotKit, or any AG-UI client

Setup

No external configuration required. Run the agent and connect your frontend to the /agui endpoint.

Endpoint: http://localhost:9001/agui

Next Steps

Full Guide

Sessions, reasoning, structured output, and troubleshooting.

Setup Guide

Run the backend and connect a Dojo frontend step by step.

Reference

Parameters, endpoints, and the Agno to AG-UI event map.

Examples

Tools, reasoning, structured output, teams, and more.