> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-docs-scavio-google-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Team Learning: Entity Memory

> Teams can track entities (people, projects, companies) across conversations using the EntityMemory store.

```python team_entity_memory.py theme={null}
"""
Team Learning: Entity Memory
=============================
Teams can track entities (people, projects, companies) across conversations
using the EntityMemory store.

Entity memory captures:
- Facts about entities
- Events involving entities
- Relationships between entities

This is useful for teams that deal with complex multi-entity contexts
like project management, CRM, or research coordination.
"""

from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.learn import (
    EntityMemoryConfig,
    LearningMachine,
    LearningMode,
    UserProfileConfig,
)
from agno.models.openai import OpenAIResponses
from agno.team import Team

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


# ---------------------------------------------------------------------------
# Create Members
# ---------------------------------------------------------------------------
project_manager = Agent(
    name="Project Manager",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Track project status, milestones, and team assignments.",
)

technical_lead = Agent(
    name="Technical Lead",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Provide technical guidance and architecture decisions.",
)


# ---------------------------------------------------------------------------
# Create Team
# ---------------------------------------------------------------------------
team = Team(
    name="Engineering Leadership",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[project_manager, technical_lead],
    db=db,
    learning=LearningMachine(
        user_profile=UserProfileConfig(
            mode=LearningMode.ALWAYS,
        ),
        entity_memory=EntityMemoryConfig(
            mode=LearningMode.ALWAYS,
        ),
    ),
    markdown=True,
    show_members_responses=True,
)


# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    user_id = "carol@example.com"

    # Session 1: Introduce project context
    print("\n" + "=" * 60)
    print("SESSION 1: Introduce project and team context")
    print("=" * 60 + "\n")

    team.print_response(
        "I'm Carol, engineering director. We have three key projects: "
        "Project Atlas (backend rewrite, led by Dave), "
        "Project Beacon (mobile app, led by Eve), and "
        "Project Compass (data pipeline, led by Frank). "
        "Atlas is behind schedule, Beacon launches next month, "
        "and Compass needs more engineers. What should I prioritize?",
        user_id=user_id,
        session_id="session_1",
        stream=True,
    )

    lm = team.learning_machine
    print("\n--- Entities Tracked ---")
    entities = lm.entity_memory_store.search(query="project", user_id=user_id)
    for entity in entities:
        lm.entity_memory_store.print(
            entity_id=entity.entity_id, entity_type=entity.entity_type, user_id=user_id
        )

    # Session 2: Update and query entities
    print("\n" + "=" * 60)
    print("SESSION 2: Update on projects")
    print("=" * 60 + "\n")

    team.print_response(
        "Good news: Dave got Atlas back on track by cutting scope. "
        "But Eve is now on medical leave - who should take over Beacon?",
        user_id=user_id,
        session_id="session_2",
        stream=True,
    )

    print("\n--- Updated Entities ---")
    entities = lm.entity_memory_store.search(query="project", user_id=user_id)
    for entity in entities:
        lm.entity_memory_store.print(
            entity_id=entity.entity_id, entity_type=entity.entity_type, 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 "psycopg[binary]" openai 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 `team_entity_memory.py`, then run:

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

Full source: [cookbook/03\_teams/12\_learning/03\_team\_entity\_memory.py](https://github.com/agno-agi/agno/blob/main/cookbook/03_teams/12_learning/03_team_entity_memory.py)