Ag Ui
Basic
Expose an OpenAI agent through the AG-UI protocol.
Code
from agno.agent.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.os import AgentOS
from agno.os.interfaces.agui import AGUI
chat_agent = Agent(
name="Assistant",
model=OpenAIResponses(id="gpt-5.4"),
instructions="You are a helpful AI assistant.",
add_datetime_to_context=True,
markdown=True,
)
agent_os = AgentOS(
agents=[chat_agent],
interfaces=[AGUI(agent=chat_agent)],
)
app = agent_os.get_app()
if __name__ == "__main__":
agent_os.serve(app="basic:app", reload=True, port=9001)Usage
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activateSet Environment Variables
export OPENAI_API_KEY=your_openai_api_keyInstall dependencies
uv pip install -U "agno[os,agui]" openaiRun Example
python basic.pyKey Features
- AG-UI endpoint: Connect the agent to an AG-UI-compatible frontend
- Streaming events: Stream agent responses to the frontend
- Markdown support: Return Markdown-formatted responses
- Datetime context: Include the current date and time in the agent context
- Open protocol: Use AG-UI events and message formats
Setup Frontend
Create an AG-UI application:
npx create-ag-ui-app@latest