Firestore for Workflows

Store workflow sessions in Firestore with FirestoreDb.

Agno supports using Firestore as a storage backend for Workflows using the FirestoreDb class.

Usage

Start in a virtual environment and set the model key before running the example.

Set OpenAI Key

Set your OPENAI_API_KEY as an environment variable. You can get one from OpenAI.

export OPENAI_API_KEY=sk-***

You need to provide either project_id or db_client to the FirestoreDb class. Configure Application Default Credentials (gcloud auth application-default login locally, or GOOGLE_APPLICATION_CREDENTIALS for a service account). The project must already have a Firestore database and your identity must have data access. The client does not provision the project or database.

Install dependencies:

uv pip install agno openai google-cloud-firestore ddgs
firestore_for_workflow.py
from agno.agent import Agent
from agno.db.firestore import FirestoreDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.websearch import WebSearchTools
from agno.workflow.step import Step
from agno.workflow.workflow import Workflow

PROJECT_ID = "agno-os-test"  # Use your project ID here

# Setup the Firestore database
db = FirestoreDb(project_id=PROJECT_ID)

# Define agents
hackernews_agent = Agent(
    name="HackerNews Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[HackerNewsTools()],
    role="Extract key insights and content from HackerNews posts",
)
web_agent = Agent(
    name="Web Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[WebSearchTools()],
    role="Search the web for the latest news and trends",
)

# Define research team for complex analysis
research_team = Team(
    name="Research Team",
    members=[hackernews_agent, web_agent],
    instructions="Research tech topics from HackerNews and the web",
)

content_planner = Agent(
    name="Content Planner",
    model=OpenAIResponses(id="gpt-5.2"),
    instructions=[
        "Plan a content schedule over 4 weeks for the provided topic and research content",
        "Ensure that I have posts for 3 posts per week",
    ],
)

# Define steps
research_step = Step(
    name="Research Step",
    team=research_team,
)

content_planning_step = Step(
    name="Content Planning Step",
    agent=content_planner,
)

# Create and use workflow
if __name__ == "__main__":
    content_creation_workflow = Workflow(
        name="Content Creation Workflow",
        description="Automated content creation from blog posts to social media",
        db=db,
        steps=[research_step, content_planning_step],
    )
    content_creation_workflow.print_response(
        input="AI trends in 2024",
        markdown=True,
    )

Params

ParameterTypeDefaultDescription
idOptional[str]-Database ID. Derived deterministically from project or client when omitted.
db_clientOptional[Client]-The Firestore client to use.
project_idOptional[str]-The GCP project ID for Firestore.
session_collectionOptional[str]-Name of the collection to store sessions.
runs_collectionOptional[str]NoneStorage name for individual runs. Defaults to agno_runs, or <session_collection>_runs when a custom session name is supplied.
memory_collectionOptional[str]-Name of the collection to store memories.
metrics_collectionOptional[str]-Name of the collection to store metrics.
eval_collectionOptional[str]-Name of the collection to store evaluation runs.
knowledge_collectionOptional[str]-Name of the collection to store knowledge documents.
traces_collectionOptional[str]-Name of the collection to store traces.
spans_collectionOptional[str]-Name of the collection to store spans.

Run the Example

Save the code as firestore_for_workflow.py, complete the prerequisites above, then run:

python firestore_for_workflow.py