GCS for Team

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

Usage

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

gcs_for_team.py

"""
Run: `uv pip install openai newspaper4k lxml_html_clean agno` to install the dependencies
"""

import uuid
import google.auth
from typing import List

from agno.agent import Agent
from agno.db.gcs_json import GcsJsonDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.hackernews import HackerNewsTools
from pydantic import BaseModel

# 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}")

# Setup the JSON database
db = GcsJsonDb(
    bucket_name=unique_bucket_name,
    prefix="team/",
    project=project_id,
    credentials=credentials,
)

class Article(BaseModel):
    title: str
    summary: str
    reference_links: List[str]

hn_researcher = Agent(
    name="HackerNews Researcher",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Gets top stories from hackernews.",
    tools=[HackerNewsTools()],
)

web_searcher = Agent(
    name="Web Searcher",
    model=OpenAIResponses(id="gpt-5.2"),
    role="Searches the web for information on a topic",
    tools=[HackerNewsTools()],
    add_datetime_to_context=True,
)

hn_team = Team(
    name="HackerNews Team",
    model=OpenAIResponses(id="gpt-5.2"),
    members=[hn_researcher, web_searcher],
    db=db,
    instructions=[
        "First, search hackernews for what the user is asking about.",
        "Then, ask the web searcher to search for each story to get more information.",
        "Finally, provide a thoughtful and engaging summary.",
    ],
    output_schema=Article,
    markdown=True,
    show_members_responses=True,
)

hn_team.print_response("Write an article about the top 2 stories on hackernews")

Prerequisites

1. Google Cloud SDK Setup

   1. Install the Google Cloud SDK
   2. Run gcloud init to configure your account and project
2. GCS Permissions

   Ensure your account has sufficient permissions (e.g., Storage Admin) to create and manage GCS buckets:

   gcloud projects add-iam-policy-binding YOUR_PROJECT_ID \
       --member="user:[e-mail]" \
       --role="roles/storage.admin"
   
3. Authentication

   Use default credentials from your gcloud CLI session:

   gcloud auth application-default login
   

   Alternatively, if using a service account, set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account JSON file.

4. Python Dependencies

   Install the required Python packages:

   pip install google-auth google-cloud-storage openai ddgs
   

1. Setup with Docker

   For local testing without using real GCS, you can use fake-gcs-server.

   Create a docker-compose.yml file:

   version: '3.8'
   services:
     fake-gcs-server:
       image: fsouza/fake-gcs-server:latest
       ports:
         - "4443:4443"
       command: ["-scheme", "http", "-port", "4443", "-public-host", "localhost"]
       volumes:
         - ./fake-gcs-data:/data
   

   Start the fake GCS server:

   docker-compose up -d
   
2. Using Fake GCS with Docker

   Set the environment variable to direct API calls to the emulator:

   export STORAGE_EMULATOR_HOST="http://localhost:4443"
   python gcs_for_agent.py
   

   When using Fake GCS, authentication isn't enforced and the client will automatically detect the emulator endpoint.

Params

Parameter	Type	Default	Description
id	Optional[str]	-	The ID of the database instance. UUID by default.
bucket_name	str	-	Name of the GCS bucket where JSON files will be stored.
prefix	Optional[str]	-	Path prefix for organizing files in the bucket. Defaults to "agno/".
session_table	Optional[str]	-	Name of the JSON file to store sessions (without .json extension).
memory_table	Optional[str]	-	Name of the JSON file to store user memories.
metrics_table	Optional[str]	-	Name of the JSON file to store metrics.
eval_table	Optional[str]	-	Name of the JSON file to store evaluation runs.
knowledge_table	Optional[str]	-	Name of the JSON file to store knowledge content.
traces_table	Optional[str]	-	Name of the JSON file to store traces.
spans_table	Optional[str]	-	Name of the JSON file to store spans.
project	Optional[str]	-	GCP project ID. If None, uses default project.
credentials	Optional[Any]	-	GCP credentials. If None, uses default credentials.