> ## 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.

# Agent with Storage

> Persist a Groq agent's chat history to Postgres and reuse it across runs.

Set `db` and `add_history_to_context=True` so the agent recalls earlier messages in the same session.

## Code

```python db.py theme={null}
from agno.agent import Agent
from agno.db.postgres import PostgresDb
from agno.models.groq import Groq
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=Groq(id="openai/gpt-oss-120b"),
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
)
agent.print_response("How many people live in Canada?")
agent.print_response("What is their national anthem called?")
```

## Usage

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

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U ddgs psycopg sqlalchemy groq agno
    ```
  </Step>

  <Step title="Run PgVector">
    ```bash theme={null}
    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
    ```
  </Step>

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

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

## Developer Resources

* [Agent storage](/features/storage)
* [WebSearchTools](/tools/toolkits/search/websearch)