> ## 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.

# User Memory: Agentic Mode

> AGENTIC mode gives the agent explicit tools to save and update memories.

AGENTIC mode gives the agent explicit tools to save and update memories. The agent decides when to store information - you can see the tool calls.

```python user_memory_agentic.py theme={null}
"""
User Memory: Agentic Mode
=========================
User Memory captures unstructured observations about users:
- Work context and role
- Communication style preferences
- Patterns and interests
- Any memorable facts

AGENTIC mode gives the agent explicit tools to save and update memories.
The agent decides when to store information - you can see the tool calls.

Compare with: 2a_user_memory_always.py for automatic extraction.
See also: 1b_user_profile_agentic.py for structured profile fields.
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import LearningMachine, LearningMode, UserMemoryConfig
from agno.models.openai import OpenAIResponses

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

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

# AGENTIC mode: Agent gets memory tools and decides when to use them.
# You'll see tool calls like "update_user_memory" in responses.
agent = Agent(
    model=OpenAIResponses(id="gpt-5.5"),
    db=db,
    learning=LearningMachine(
        user_memory=UserMemoryConfig(
            mode=LearningMode.AGENTIC,
        ),
    ),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    user_id = "bob@example.com"

    # Session 1: Agent explicitly saves memories
    print("\n" + "=" * 60)
    print("SESSION 1: Share information (watch for tool calls)")
    print("=" * 60 + "\n")

    agent.print_response(
        "I'm a backend engineer at Stripe. "
        "I specialize in distributed systems and prefer Rust over Go.",
        user_id=user_id,
        session_id="session_1",
        stream=True,
    )
    agent.learning_machine.user_memory_store.print(user_id=user_id)

    # Session 2: Agent uses stored memories
    print("\n" + "=" * 60)
    print("SESSION 2: Memories recalled in new session")
    print("=" * 60 + "\n")

    agent.print_response(
        "What programming language would you recommend for my next project?",
        user_id=user_id,
        session_id="session_2",
        stream=True,
    )
    agent.learning_machine.user_memory_store.print(user_id=user_id)
```

## 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 `user_memory_agentic.py`, then run:

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

Full source: [cookbook/08\_learning/01\_basics/2b\_user\_memory\_agentic.py](https://github.com/agno-agi/agno/blob/main/cookbook/08_learning/01_basics/2b_user_memory_agentic.py)