> ## 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.

# Google Cloud Storage for Agent

Agno supports using Google Cloud Storage (GCS) as a storage backend for Agents using the `GcsJsonDb` class. This storage backend stores session data as JSON blobs in a GCS bucket.

## Usage

Configure your agent with GCS storage to enable cloud-based session persistence.

```python gcs_for_agent.py theme={null}
import uuid
import google.auth
from agno.agent import Agent
from agno.db.base import SessionType
from agno.db.gcs_json import GcsJsonDb
from agno.tools.hackernews import HackerNewsTools

# Obtain the default credentials and project id from your gcloud CLI session.
credentials, project_id = google.auth.default()

# Generate a unique bucket name using a base name and a UUID4 suffix.
base_bucket_name = "example-gcs-bucket"
unique_bucket_name = f"{base_bucket_name}-{uuid.uuid4().hex[:12]}"
print(f"Using bucket: {unique_bucket_name}")

# Initialize GCSJsonDb with explicit credentials, unique bucket name, and project.
db = GcsJsonDb(
    bucket_name=unique_bucket_name,
    prefix="agent/",
    project=project_id,
    credentials=credentials,
)

# Initialize the Agno agent with the new storage backend and HackerNews tools.
agent1 = Agent(
    db=db,
    tools=[HackerNewsTools()],
    add_history_to_context=True,
    debug_mode=False,
)

# Execute sample queries.
agent1.print_response("How many people live in Canada?")
agent1.print_response("What is their national anthem called?")

# Create a new agent and make sure it pursues the conversation
agent2 = Agent(
    db=db,
    session_id=agent1.session_id,
    tools=[HackerNewsTools()],
    add_history_to_context=True,
    debug_mode=False,
)

agent2.print_response("What's the name of the country we discussed?")
agent2.print_response("What is that country's national sport?")
```

## Prerequisites

<Snippet file="gcs-auth-storage.mdx" />

## Params

<Snippet file="db-gcs-params.mdx" />