> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Team State Events

> Demonstrates AG-UI state synchronization with a Team using enable_agentic_state.

Demonstrates AG-UI state synchronization with a Team using enable\_agentic\_state. The team coordinates multiple agents while maintaining shared session state.

```python team_state_events.py theme={null}
"""
Team State Events
=================

Demonstrates AG-UI state synchronization with a Team using enable_agentic_state.
The team coordinates multiple agents while maintaining shared session state.
"""

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

recipe_creator = Agent(
    name="recipe_creator",
    role="Recipe Creator",
    model=OpenAIResponses(id="gpt-5.5"),
    instructions="You create recipes with ingredients and instructions. Focus on the cooking process.",
    markdown=True,
)

nutrition_advisor = Agent(
    name="nutrition_advisor",
    role="Nutrition Advisor",
    model=OpenAIResponses(id="gpt-5.5"),
    instructions="You advise on dietary preferences and nutritional aspects of recipes.",
    markdown=True,
)

recipe_team = Team(
    name="RecipeTeam",
    members=[recipe_creator, nutrition_advisor],
    session_state={
        "recipe": {
            "title": "",
            "skill_level": "Intermediate",
            "cooking_time": "45 min",
            "special_preferences": [],
            "ingredients": [],
            "instructions": [],
        }
    },
    add_session_state_to_context=True,
    enable_agentic_state=True,
    instructions="""You are a recipe team that helps users create and modify recipes.

The current recipe state is shown in <session_state>. Use it to understand what exists.

Use update_session_state to modify the recipe. The recipe structure is:
- title: Recipe name
- skill_level: "Beginner", "Intermediate", or "Advanced"
- cooking_time: "5 min", "15 min", "30 min", "45 min", or "60+ min"
- special_preferences: List of dietary preferences like "High Protein", "Low Carb", "Spicy", "Budget-Friendly", "One-Pot Meal", "Vegetarian", "Vegan"
- ingredients: List of {name, amount, icon} objects. Use emoji icons like 🥕 🧅 🥚 🌾 🧈 🥛
- instructions: List of cooking step strings

Coordinate between the recipe creator (ingredients, instructions) and nutrition advisor (dietary preferences).
When updating, preserve existing fields and only change what's needed.""",
    show_members_responses=True,
    markdown=True,
)

agent_os = AgentOS(
    teams=[recipe_team],
    interfaces=[AGUI(team=recipe_team, prefix="/shared_state")],
)
app = agent_os.get_app()


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

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[agui,os]" fastmcp openai starlette
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:JWT_VERIFICATION_KEY="your_jwt_verification_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `team_state_events.py`, then run:

    ```bash theme={null}
    python team_state_events.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/interfaces/agui/team\_state\_events.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/interfaces/agui/team_state_events.py)