Skip to main content

Basic Working Memory

Use working memory to help agents remember key facts, track user details, and maintain context across conversations.

Working memory works with both streamed responses using .stream() and generated responses using .generate(), and requires a storage provider such as PostgreSQL, LibSQL, or Redis to persist data between sessions.

This example shows how to enable working memory in an agent and interact with it across multiple messages in the same thread.

Prerequisites​

This example uses the openai model. Make sure to add OPENAI_API_KEY to your .env file.

OPENAI_API_KEY=<your-api-key>

And install the following package:

npm install @mastra/libsql

Adding memory to an agent​

To add LibSQL memory to an agent, use the Memory class and pass a storage instance using LibSQLStore. The url can point to a remote location or local file.

Working memory configuration​

Enable working memory by setting workingMemory.enabled to true. This allows the agent to remember information from earlier conversations and persist structured data between sessions.

Threads group related messages into distinct conversations. When generateTitle is enabled, each thread is automatically named based on its content.

import { Memory } from "@mastra/memory";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";
import { LibSQLStore } from "@mastra/libsql";

export const workingMemoryAgent = new Agent({
  name: "working-memory-agent",
  instructions:
    "You are an AI agent with the ability to automatically recall memories from previous interactions.",
  model: openai("gpt-4o"),
  memory: new Memory({
    storage: new LibSQLStore({
      url: "file:working-memory.db",
    }),
    options: {
      workingMemory: {
        enabled: true,
      },
      threads: {
        generateTitle: true,
      },
    },
  }),
});

Usage examples​

This example shows how to interact with an agent that has working memory enabled. The agent remembers information shared across multiple interactions within the same thread.

Streaming a response using .stream()​

This example sends two messages to the agent within the same thread. The response is streamed and includes information remembered from the first.

import "dotenv/config";

import { mastra } from "./mastra";

const threadId = "123";
const resourceId = "user-456";

const agent = mastra.getAgent("workingMemoryAgent");

await agent.stream("My name is Mastra", {
  memory: {
    thread: threadId,
    resource: resourceId,
  },
});

const stream = await agent.stream("What do you know about me?", {
  memory: {
    thread: threadId,
    resource: resourceId,
  },
});

for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

Generating a response using .generate()​

This example sends two messages to the agent within the same thread. The response is returned as a single message and includes information remembered from the first.

import "dotenv/config";

import { mastra } from "./mastra";

const threadId = "123";
const resourceId = "user-456";

const agent = mastra.getAgent("workingMemoryAgent");

await agent.generate("My name is Mastra", {
  memory: {
    thread: threadId,
    resource: resourceId,
  },
});

const response = await agent.generate("What do you know about me?", {
  memory: {
    thread: threadId,
    resource: resourceId,
  },
});

console.log(response.text);

Example output​

The output demonstrates the agent has used its memory to recall information.

I know that your first name is Mastra.
If there's anything else you'd like to share or update, feel free to let me know!

Example storage object​

Working memory stores data in .json format, which would look similar to the below:

{
  // ...
  "toolInvocations": [
    {
      // ...
      "args": {
        "memory": "# User Information\n- **First Name**: Mastra\n-"
      }
    }
  ]
}