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

# Add Dependencies to Agent Run

This example demonstrates how to inject dependencies into agent runs, allowing the agent to access dynamic context like user profiles and current time information for personalized responses.

## Code

```python add_dependencies_on_run.py theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat


def get_user_profile(user_id: str = "john_doe") -> dict:
    """Get user profile information that can be referenced in responses.

    Args:
        user_id: The user ID to get profile for
    Returns:
        Dictionary containing user profile information
    """
    profiles = {
        "john_doe": {
            "name": "John Doe",
            "preferences": {
                "communication_style": "professional",
                "topics_of_interest": ["AI/ML", "Software Engineering", "Finance"],
                "experience_level": "senior",
            },
            "location": "San Francisco, CA",
            "role": "Senior Software Engineer",
        }
    }

    return profiles.get(user_id, {"name": "Unknown User"})


def get_current_context() -> dict:
    """Get current contextual information like time, weather, etc."""
    from datetime import datetime

    return {
        "current_time": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
        "timezone": "PST",
        "day_of_week": datetime.now().strftime("%A"),
    }


agent = Agent(
    model=OpenAIChat(id="gpt-5-mini"),
    markdown=True,
)

# Example usage - sync
response = agent.run(
    "Please provide me with a personalized summary of today's priorities based on my profile and interests.",
    dependencies={
        "user_profile": get_user_profile,
        "current_context": get_current_context,
    },
    add_dependencies_to_context=True,
    debug_mode=True,
)

print(response.content)

# ------------------------------------------------------------
# ASYNC EXAMPLE
# ------------------------------------------------------------
# async def test_async():
#     async_response = await agent.arun(
#         "Based on my profile, what should I focus on this week? Include specific recommendations.",
#         dependencies={
#             "user_profile": get_user_profile,
#             "current_context": get_current_context
#         },
#         add_dependencies_to_context=True,
#         debug_mode=True,
#     )

#     print("\n=== Async Run Response ===")
#     print(async_response.content)

# # Run the async test
# import asyncio
# asyncio.run(test_async())

# ------------------------------------------------------------
# Print response EXAMPLE
# ------------------------------------------------------------
# agent.print_response(
#     "Please provide me with a personalized summary of today's priorities based on my profile and interests.",
#     dependencies={
#         "user_profile": get_user_profile,
#         "current_context": get_current_context,
#     },
#     add_dependencies_to_context=True,
#     debug_mode=True,
# )
```

## Usage

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

  <Step title="Install libraries">
    ```bash theme={null}
    pip install -U agno openai
    ```
  </Step>

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

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

  <Step title="Create a Python file">
    Create a Python file and add the above code.

    ```bash theme={null}
    touch add_dependencies_on_run.py
    ```
  </Step>

  <Step title="Run Agent">
    <CodeGroup>
      ```bash Mac theme={null}
      python add_dependencies_on_run.py
      ```

      ```bash Windows theme={null}
      python add_dependencies_on_run.py
      ```
    </CodeGroup>
  </Step>

  <Step title="Find All Cookbooks">
    Explore all the available cookbooks in the Agno repository. Click the link below to view the code on GitHub:

    <Link href="https://github.com/agno-agi/agno/tree/main/cookbook/agents/dependencies" target="_blank">
      Agno Cookbooks on GitHub
    </Link>
  </Step>
</Steps>