# Memory Manager (/examples/agents/memory-and-learning/memory-manager)



```python title="memory_manager.py"
"""
Memory Manager
=============================

Use a MemoryManager to give agents persistent memory across sessions.
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.memory.manager import MemoryManager
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
db = SqliteDb(db_file="tmp/memory_demo.db")

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    db=db,
    # Enable agentic memory so the agent can store and retrieve memories
    enable_agentic_memory=True,
    # Provide a MemoryManager for structured memory operations
    memory_manager=MemoryManager(
        db=db,
        model=OpenAIResponses(id="gpt-5-mini"),
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # First interaction: tell the agent something to remember
    agent.print_response(
        "My name is Alice and I prefer Python over JavaScript.",
        stream=True,
    )

    print("\n--- Second interaction ---\n")

    # Second interaction: the agent should recall the preference
    agent.print_response(
        "What programming language do I prefer?",
        stream=True,
    )
```

## Demonstrate recall across sessions [#demonstrate-recall-across-sessions]

The source is a single-user demonstration: without `user_id`, memory uses the shared `default` user, and the two calls reuse one generated session. Memory still works in that configuration.

To demonstrate cross-session recall, replace both calls in the saved script with the following. Keep the same SQLite path and user ID across runs; separate users need separate IDs. With agentic memory, the model must choose to save the preference.

```python
agent.print_response(
    "Remember that my name is Alice and I prefer Python over JavaScript.",
    user_id="alice",
    session_id="alice-first-visit",
    stream=True,
)
agent.print_response(
    "What programming language do I prefer?",
    user_id="alice",
    session_id="alice-second-visit",
    stream=True,
)
```

## Run the Example [#run-the-example]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U agno openai sqlalchemy
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

        <CodeBlockTabsTrigger value="Windows">
          Windows
        </CodeBlockTabsTrigger>
      </CodeBlockTabsList>

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

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

    ```bash
    python memory_manager.py
    ```
  </Step>
</Steps>

Full source: [cookbook/02\_agents/06\_memory\_and\_learning/memory\_manager.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/02_agents/06_memory_and_learning/memory_manager.py)