> ## 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/javascript/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/javascript/integrations/memory/mongodb-long-term-memory) to store and recall data across different threads and sessions.
</Tip>

## Setup

### Installation

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @langchain/langgraph-checkpoint-mongodb mongodb
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/langgraph-checkpoint-mongodb mongodb
  ```

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

### Credentials

Set your Atlas connection string:

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export MONGODB_ATLAS_URI="your-atlas-connection-string"
```

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

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export LANGSMITH_API_KEY="your-api-key"
export LANGSMITH_TRACING="true"
```

## Usage

Create a `MongoClient`, construct `MongoDBSaver`, and call `setup()` once so indexes exist. There is no `MongoDBSaver.fromConnString` helper.

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { createAgent, tool } from "langchain";
import { MongoDBSaver } from "@langchain/langgraph-checkpoint-mongodb";
import { MongoClient } from "mongodb";
import * as z from "zod";

const getUserInfo = tool(() => "No user profile on file.", {
  name: "get_user_info",
  description: "Look up information about the current user.",
  schema: z.object({}),
});

const MONGODB_ATLAS_URI = process.env.MONGODB_ATLAS_URI;
if (!MONGODB_ATLAS_URI) {
  throw new Error("MONGODB_ATLAS_URI is required");
}

const client = new MongoClient(MONGODB_ATLAS_URI);
const checkpointer = new MongoDBSaver({ client });
await checkpointer.setup();

const agent = createAgent({
  model: "anthropic:claude-sonnet-4-6",
  tools: [getUserInfo],
  checkpointer,
});

const threadConfig = { configurable: { thread_id: "1" } };
let result = await agent.invoke(
  { messages: [{ role: "user", content: "Hi! My name is Bob." }] },
  threadConfig,
);
console.log(result.messages.at(-1)?.content);

result = await agent.invoke(
  { messages: [{ role: "user", content: "What's my name?" }] },
  threadConfig,
);
console.log(result.messages.at(-1)?.content);

await client.close();
```

## Next steps

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

***

<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/javascript/integrations/memory/mongodb-short-term-memory.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>