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

# Persistent Session

> Persist agent sessions in Postgres with a fixed session_id so history carries across runs.

Persistent Session Example.

```python persistent_session.py theme={null}
"""
Persistent Session
=============================

Persistent Session Example.
"""

from agno.agent.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.openai import OpenAIResponses

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

db = PostgresDb(db_url=db_url, session_table="sessions")

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5-mini"),
    db=db,
    session_id="session_storage",
    add_history_to_context=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response("Tell me a new interesting fact about space")
```

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno "psycopg[binary]" openai sqlalchemy
```

**2. Export your OpenAI API key**

```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"
```

<Snippet file="run-pgvector-step.mdx" />

**3. Run the example**

Save the code above as `persistent_session.py`, then run:

```bash theme={null}
python persistent_session.py
```

Full source: [cookbook/02\_agents/05\_state\_and\_session/persistent\_session.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/02_agents/05_state_and_session/persistent_session.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.