Streaming Working Memory

This example demonstrates how to create an agent that maintains a working memory for relevant conversational details like the users name, location, or preferences.

Setup

First, set up the memory system with working memory enabled. Memory uses LibSQL storage by default, but you can use any other storage provider if needed:

import { Memory } from "@mastra/memory";
 
const memory = new Memory({
  options: {
    workingMemory: {
      enabled: true,
    },
  },
});

Add the memory instance to an agent

import { openai } from "@ai-sdk/openai";
 
const todoAgent = new Agent({
  name: "Memory agent",
  instructions: "You are a helpful AI assistant.",
  model: openai("gpt-4o-mini"),
  memory,
});

Usage Example

Now that working memory is set up you can interact with the agent and it will remember key details about interactions.

First start a conversation and give the agent relevant information like your name.

import { randomUUID } from "crypto";
 
const threadId = randomUUID();
const resourceId = "SOME_USER_ID";
 
const response = await todoAgent.stream("Hello, my name is Jane", {
  threadId,
  resourceId,
});
 
// process response stream
for await (const chunk of response.textStream) {
  process.stdout.write(chunk);
}

Handling response data

The response stream will contain xml-like <working_memory>$data</working_memory> tagged data. Mastra picks up these tags and automatically updates working memory with the data returned by the LLM.

To prevent showing this data to users you can import the maskStreamTags util and pass the stream response through it.

import { maskStreamTags } from "@mastra/core/utils";
 
for await (const chunk of maskStreamTags(
  response.textStream, // pass the text stream
  "working_memory", // and the name of the working memory tag
)) {
  process.stdout.write(chunk);
}

Summary

This example demonstrates:

1. Setting up a memory system with working memory enabled
2. Using maskStreamTags to hide memory updates from users
3. The agent will maintain relevant user info between interactions, even when the original messages containing that info are no longer in context.

Advanced use cases

For examples on controlling which information is relevant for working memory, or showing loading states while working memory is being saved, see our advanced working memory example.

To learn more about agent memory, including other memory types and storage options, check out the Memory documentation page.