> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Save Agent to Database

> Demonstrates creating an agent and saving it to the database.

```python save_agent.py theme={null}
"""
Save Agent to Database
======================

Demonstrates creating an agent and saving it to the database.
"""

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIChat

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------
db = PostgresDb(db_url="postgresql+psycopg://ai:ai@localhost:5532/ai")

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    id="agno-agent",
    model=OpenAIChat(id="gpt-5-mini"),
    name="Agno Agent",
    db=db,
)

# ---------------------------------------------------------------------------
# Run Agent Save Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # agent.print_response("How many people live in Canada?")

    # Save the agent to the database
    version = agent.save()
    print(f"Saved agent as version {version}")

    # By default, saving a agent will create a new version of the agent

    # Delete the agent from the database (soft delete by default)
    # agent.delete()

    # Hard delete (permanently removes from database)
    # agent.delete(hard_delete=True)
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai psycopg-binary sqlalchemy
    ```
  </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>

  <Snippet file="run-pgvector-step.mdx" />

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

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

Full source: [cookbook/93\_components/save\_agent.py](https://github.com/agno-agi/agno/blob/main/cookbook/93_components/save_agent.py)