Async MongoDB for Agent

AsyncMongoDb stores an Agent's sessions and run history asynchronously in MongoDB. Use async Agent methods such as arun() and aprint_response().

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. This example uses db_url.

Install the pymongo (4.9 or later), openai, and ddgs packages:

uv pip install agno "pymongo>=4.9" openai ddgs

motor clients are also supported, but motor is deprecated. Use PyMongo's async client instead.

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

async_mongodb_for_agent.py

import asyncio

from agno.agent import Agent
from agno.db.mongo import AsyncMongoDb
from agno.tools.websearch import WebSearchTools

db_url = "mongodb://mongoadmin:secret@localhost:27017"

db = AsyncMongoDb(db_url=db_url)

agent = Agent(
    db=db,
    tools=[WebSearchTools()],
    add_history_to_context=True,
)


async def main():
    try:
        await agent.aprint_response("How many people live in Canada?")
        await agent.aprint_response("What is their national anthem called?")
    finally:
        await db.close()


if __name__ == "__main__":
    asyncio.run(main())

Parameters

Parameter	Type	Default	Description
`id`	`Optional[str]`	-	Database ID. Derived deterministically from connection/client and database name when omitted.
`db_client`	`Optional[Union[AsyncIOMotorClient, AsyncMongoClient]]`	-	The MongoDB async client to use. Supports Motor and PyMongo async clients.
`db_name`	`Optional[str]`	-	The name of the database to use.
`db_url`	`Optional[str]`	-	The database URL to connect to.
`session_collection`	`Optional[str]`	-	Name of the collection to store sessions.
`runs_collection`	`Optional[str]`	-	Name of the collection to store session runs.
`memory_collection`	`Optional[str]`	-	Name of the collection to store memories.
`metrics_collection`	`Optional[str]`	-	Name of the collection to store metrics.
`eval_collection`	`Optional[str]`	-	Name of the collection to store evaluation runs.
`knowledge_collection`	`Optional[str]`	-	Name of the collection to store knowledge documents.
`traces_collection`	`Optional[str]`	-	Name of the collection to store traces.
`spans_collection`	`Optional[str]`	-	Name of the collection to store spans.
`learnings_collection`	`Optional[str]`	-	Name of the collection to store learnings.
`schedules_collection`	`Optional[str]`	-	Name of the collection to store cron schedules.
`schedule_runs_collection`	`Optional[str]`	-	Name of the collection to store schedule run history.

Run the Example

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

python async_mongodb_for_agent.py