> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Short-term memory with MongoDB Atlas

> Persist agent short-term memory with MongoDBSaver and MongoDB Atlas.

[Short-term memory](/oss/python/langchain/short-term-memory) lets your agent remember previous interactions within a single thread or conversation. This guide shows how to use [MongoDB Atlas](https://www.mongodb.com/docs/atlas/) as the persistent checkpointer backend.

MongoDB stores conversation state as documents in a collection, so threads can resume across process restarts and deployments.

<Tip>
  Need to remember information **across** conversations? Use [long-term memory with MongoDB Atlas](/oss/python/integrations/memory/mongodb-long-term-memory) to store and recall data across different threads and sessions.
</Tip>

## Setup

### Installation

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install -U langgraph-checkpoint-mongodb pymongo
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add langgraph-checkpoint-mongodb pymongo
  ```
</CodeGroup>

### Credentials

Set your Atlas connection string:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import getpass
import os

if not os.environ.get("MONGODB_ATLAS_URI"):
    os.environ["MONGODB_ATLAS_URI"] = getpass.getpass("Enter your MongoDB Atlas URI: ")
```

If you want automated tracing of your model calls, set your [LangSmith](/langsmith/home) API key:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
if not os.environ.get("LANGSMITH_API_KEY"):
    os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"
```

## Usage

Create a `MongoDBSaver` with `from_conn_string` and pass it to `create_agent`. The context manager creates the required collections and indexes when it opens. You do not call a separate `setup()` method (unlike the Postgres checkpointer).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import os

from langchain.agents import create_agent
from langgraph.checkpoint.mongodb import MongoDBSaver

def get_user_info() -> str:
    """Look up information about the current user."""
    return "No user profile on file."

MONGODB_ATLAS_URI = os.environ["MONGODB_ATLAS_URI"]

with MongoDBSaver.from_conn_string(MONGODB_ATLAS_URI) as checkpointer:
    agent = create_agent(
        "anthropic:claude-sonnet-4-6",
        tools=[get_user_info],
        checkpointer=checkpointer,
    )

    thread_config = {"configurable": {"thread_id": "1"}}
    response = agent.invoke(
        {"messages": [{"role": "user", "content": "Hi! My name is Bob."}]},
        thread_config,
    )["messages"][-1].content

    print(response)

    response = agent.invoke(
        {"messages": [{"role": "user", "content": "What's my name?"}]},
        thread_config,
    )["messages"][-1].content

    print(response)
```

`MongoDBSaver` also exposes async methods such as `aget` and `aput` for use in async graphs. There is no separate `AsyncMongoDBSaver` class.

## Next steps

* Customize agent state, trim or summarize history, and access memory from tools in the [short-term memory](/oss/python/langchain/short-term-memory) guide. Pass the same `MongoDBSaver` as `checkpointer`.
* See the [checkpointer integrations](/oss/python/integrations/checkpointers) list for other backends.
* For cross-thread persistence, see [long-term memory with MongoDB Atlas](/oss/python/integrations/memory/mongodb-long-term-memory).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/memory/mongodb-short-term-memory.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>