MongoDB for Team

Store team sessions and run history in MongoDB with MongoDb.

MongoDb stores a Team's sessions and run history in MongoDB.

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-***

Provide either db_url or db_client. The default database name is agno; set db_name to use another database. The following example uses db_url.

Install the agno, pymongo, openai, and ddgs packages:

uv pip install agno pymongo openai ddgs

Run MongoDB

Install Docker Desktop, then start MongoDB on port 27017:

docker run -d \
  --name local-mongo \
  -p 27017:27017 \
  -e MONGO_INITDB_ROOT_USERNAME=mongoadmin \
  -e MONGO_INITDB_ROOT_PASSWORD=secret \
  mongo
mongodb_for_team.py
from typing import List

from agno.agent import Agent
from agno.db.mongo import MongoDb
from agno.models.openai import OpenAIResponses
from agno.team import Team
from agno.tools.hackernews import HackerNewsTools
from agno.tools.websearch import WebSearchTools
from pydantic import BaseModel

db_url = "mongodb://mongoadmin:secret@localhost:27017"
db = MongoDb(db_url=db_url)

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=[WebSearchTools()],
    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")

Parameters

ParameterTypeDefaultDescription
idOptional[str]-Database ID. Derived deterministically from connection/client and database name when omitted.
db_clientOptional[MongoClient]-The MongoDB client to use.
db_nameOptional[str]-The name of the database to use.
db_urlOptional[str]-The database URL to connect to.
session_collectionOptional[str]-Name of the collection to store sessions.
runs_collectionOptional[str]-Name of the collection to store individual runs.
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.
schedules_collectionOptional[str]-Name of the collection to store cron schedules.
schedule_runs_collectionOptional[str]-Name of the collection to store schedule run history.
learnings_collectionOptional[str]-Name of the collection to store learnings.

Run the Example

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

python mongodb_for_team.py