Skip to main content

​
Overview

AsyncMongoStorage provides an asynchronous MongoDB-based storage backend. Supports both Motor (legacy) and PyMongo async (recommended) clients. Ideal for document-based applications, flexible schemas, and horizontally scalable deployments.

​
Basic Usage

import asyncio
from upsonic import Agent, Task
from upsonic.storage.memory import Memory
from upsonic.storage.mongo import AsyncMongoStorage

async def main():
    storage = AsyncMongoStorage(
        db_url="mongodb://localhost:27017",
        db_name="agent_memory"
    )

    memory = Memory(
        storage=storage,
        session_id="session_001",
        user_id="user_123",
        full_session_memory=True,
        summary_memory=True,
        user_analysis_memory=True,
        model="openai/gpt-4o"
    )

    agent = Agent("openai/gpt-4o", memory=memory)

    result1 = await agent.ado(Task("My name is Alice"))
    result2 = await agent.ado(Task("What's my name?"))
    print(result2)  # "Your name is Alice"

asyncio.run(main())

​
Parameters

ParameterTypeDefaultDescription
db_urlstrNoneMongoDB connection URL
db_namestr"upsonic"Database name to use
db_clientAsyncIOMotorClient or AsyncMongoClientNonePre-configured async MongoDB client
session_collectionstrNoneCustom name for the session collection
user_memory_collectionstrNoneCustom name for the user memory collection
idstrNoneUnique identifier for this storage instance
When both Motor and PyMongo async are available, PyMongo async is preferred. Install using pip install -U 'pymongo>=4.9' (recommended) or pip install -U motor (legacy).

​
Requirements

# Recommended
pip install 'pymongo>=4.9'

# Or legacy Motor
pip install motor