> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Memory Search

> Retrieve user memories by update time or select related memories with a model.

`MemoryManager.search_user_memories()` retrieves memories by update time or asks a model to select memories related to a query.

## Code

```python memory-search.py theme={null}
from agno.db.postgres import PostgresDb
from agno.memory import MemoryManager, UserMemory
from agno.models.openai import OpenAIResponses
from rich.pretty import pprint

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

memory_db = PostgresDb(db_url=db_url)

memory = MemoryManager(model=OpenAIResponses(id="gpt-5.2"), db=memory_db)

john_doe_id = "john_doe@example.com"
memory.add_user_memory(
    memory=UserMemory(memory="The user enjoys hiking in the mountains on weekends"),
    user_id=john_doe_id,
)
memory.add_user_memory(
    memory=UserMemory(
        memory="The user enjoys reading science fiction novels before bed"
    ),
    user_id=john_doe_id,
)
print("John Doe's memories:")
pprint(memory.get_user_memories(user_id=john_doe_id))

memories = memory.search_user_memories(
    user_id=john_doe_id, limit=1, retrieval_method="last_n"
)
print("\nJohn Doe's last_n memories:")
pprint(memories)

memories = memory.search_user_memories(
    user_id=john_doe_id, limit=1, retrieval_method="first_n"
)
print("\nJohn Doe's first_n memories:")
pprint(memories)

memories = memory.search_user_memories(
    user_id=john_doe_id,
    query="What does the user like to do on weekends?",
    retrieval_method="agentic",
)
print("\nJohn Doe's memories related to the query (agentic):")
pprint(memories)
```

## Retrieval Methods

| Method    | Result                                                      |
| --------- | ----------------------------------------------------------- |
| `last_n`  | Most recently updated memories                              |
| `first_n` | Least recently updated memories                             |
| `agentic` | Memories a model selects as related to the required `query` |

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export OPENAI_API_KEY=xxx
    ```
  </Step>

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

  <Step title="Run example">
    ```bash theme={null}
    python memory-search.py
    ```
  </Step>
</Steps>