# Agent With Persistent Memory (/examples/memory/agent-with-memory)



Set `update_memory_on_run=True` to extract memories from user input during the run. Memory work starts alongside the main response and is awaited before successful completion. Consume a stream to completion before reading the resulting memories.

Use a disposable database: this example calls `db.clear_memories()`, which removes the entire memory table’s records, including those for other users.

```python title="agent_with_memory.py"
"""
Agent With Persistent Memory
============================

This example shows how to use persistent memory with an Agent.
After each run, user memories are created or updated.
"""

import asyncio
from uuid import uuid4

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
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 Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIChat(id="gpt-5.6-luna"),
    db=db,
    update_memory_on_run=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    db.clear_memories()

    session_id = str(uuid4())
    john_doe_id = "john_doe@example.com"

    asyncio.run(
        agent.aprint_response(
            "My name is John Doe and I like to hike in the mountains on weekends.",
            stream=True,
            user_id=john_doe_id,
            session_id=session_id,
        )
    )

    agent.print_response(
        "What are my hobbies?", stream=True, user_id=john_doe_id, session_id=session_id
    )

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

    agent.print_response(
        "Ok i dont like hiking anymore, i like to play soccer instead.",
        stream=True,
        user_id=john_doe_id,
        session_id=session_id,
    )

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

## 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 "psycopg[binary]" 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 PgVector">
      <CodeBlockTabs defaultValue="macOS / Linux">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="macOS / Linux">
            macOS / Linux
          </CodeBlockTabsTrigger>

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

        <CodeBlockTab value="macOS / Linux">
          ```bash
          docker run -d \
            -e POSTGRES_DB=ai \
            -e POSTGRES_USER=ai \
            -e POSTGRES_PASSWORD=ai \
            -e PGDATA=/var/lib/postgresql \
            -v pgvolume:/var/lib/postgresql \
            -p 5532:5432 \
            --name pgvector \
            agnohq/pgvector:18
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```powershell
          docker run -d `
            -e POSTGRES_DB=ai `
            -e POSTGRES_USER=ai `
            -e POSTGRES_PASSWORD=ai `
            -e PGDATA=/var/lib/postgresql `
            -v pgvolume:/var/lib/postgresql `
            -p 5532:5432 `
            --name pgvector `
            agnohq/pgvector:18
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

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

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

Full source: [cookbook/11\_memory/01\_agent\_with\_memory.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/11_memory/01_agent_with_memory.py)