> ## 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.

# Custom Memory Manager Configuration

> Configure a MemoryManager separately from the Agent and apply custom memory capture instructions.

```python custom_memory_manager.py theme={null}
"""
Custom Memory Manager Configuration
===================================

This example shows how to configure a MemoryManager separately from the Agent
and apply custom memory capture instructions.
"""

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.memory import MemoryManager
from agno.models.openai import OpenAIChat
from rich.pretty import pprint

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

# ---------------------------------------------------------------------------
# Create Memory Manager
# ---------------------------------------------------------------------------
memory_manager = MemoryManager(
    model=OpenAIChat(id="gpt-4o"),
    additional_instructions="""
    IMPORTANT: Don't store any memories about the user's name. Just say "The User" instead of referencing the user's name.
    """,
    db=db,
)

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    db=db,
    memory_manager=memory_manager,
    update_memory_on_run=True,
    user_id="john_doe@example.com",
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    john_doe_id = "john_doe@example.com"

    agent.print_response(
        "My name is John Doe and I like to swim and play soccer.", stream=True
    )

    agent.print_response("I dont like to swim", stream=True)

    memories = agent.get_user_memories(user_id=john_doe_id)
    print("John Doe's memories:")
    pprint(memories)
```

## 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 `custom_memory_manager.py`, then run:

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

Full source: [cookbook/11\_memory/04\_custom\_memory\_manager.py](https://github.com/agno-agi/agno/blob/main/cookbook/11_memory/04_custom_memory_manager.py)