DocsReferenceMemoryMemory Class

Memory Class Reference

The Memory class provides a robust system for managing conversation history and thread-based message storage in Mastra. It enables persistent storage of conversations, semantic search capabilities, and efficient message retrieval. By default, it uses LibSQL for storage and vector search, and FastEmbed for embeddings.

Basic Usage

import { Memory } from "@mastra/memory";
import { Agent } from "@mastra/core/agent";
 
const agent = new Agent({
  memory: new Memory(),
  ...otherOptions,
});

Custom Configuration

import { Memory } from "@mastra/memory";
import { LibSQLStore } from "@mastra/core/storage/libsql";
import { LibSQLVector } from "@mastra/core/vector/libsql";
import { Agent } from "@mastra/core/agent";
 
const memory = new Memory({
  // Optional storage configuration - libsql will be used by default
  storage: new LibSQLStore({
    url: "file:memory.db",
  }),
 
  // Optional vector database for semantic search - libsql will be used by default
  vector: new LibSQLVector({
    url: "file:vector.db",
  }),
 
  // Memory configuration options
  options: {
    // Number of recent messages to include
    lastMessages: 20,
 
    // Semantic search configuration
    semanticRecall: {
      topK: 3, // Number of similar messages to retrieve
      messageRange: {
        // Messages to include around each result
        before: 2,
        after: 1,
      },
    },
 
    // Working memory configuration
    workingMemory: {
      enabled: true,
      template: "<user><first_name></first_name><last_name></last_name></user>",
    },
  },
});
 
const agent = new Agent({
  memory,
  ...otherOptions,
});

Parameters

storage?:

MastraStorage
Storage implementation for persisting memory data

vector?:

MastraVector
Vector store for semantic search capabilities

embedder?:

EmbeddingModel
Embedder instance for vector embeddings. Uses FastEmbed (bge-small-en-v1.5) by default

options?:

MemoryConfig
General memory configuration options

options

lastMessages?:

number | false
= 40
Number of most recent messages to retrieve. Set to false to disable.

semanticRecall?:

boolean | SemanticRecallConfig
= false (true if vector store provided)
Enable semantic search in message history. Automatically enabled when vector store is provided.

topK?:

number
= 2
Number of similar messages to retrieve when using semantic search

messageRange?:

number | { before: number; after: number }
= 2
Range of messages to include around semantic search results

workingMemory?:

{ enabled: boolean; template?: string; use?: 'text-stream' | 'tool-call' }
= { enabled: false, template: '<user><first_name></first_name><last_name></last_name>...</user>', use: 'text-stream' }
Configuration for working memory feature that allows persistent storage of user information across conversations. The 'use' setting determines how working memory updates are handled - either through text stream tags or tool calls.

threads?:

{ generateTitle?: boolean }
= { generateTitle: true }
Settings related to memory thread creation. `generateTitle` will cause the thread.title to be generated from an llm summary of the users first message.

Working Memory

The working memory feature allows agents to maintain persistent information across conversations. When enabled, the Memory class will automatically manage XML-based working memory updates through either text stream tags or tool calls.

There are two modes for handling working memory updates:

  1. text-stream (default): The agent includes working memory updates directly in its responses using XML-like tags (<working_memory>...</working_memory>). These tags are automatically processed and stripped from the visible output.

  2. tool-call: The agent uses a dedicated tool to update working memory. This mode should be used when working with toDataStream() as text-stream mode is not compatible with data streaming. Additionally, this mode provides more explicit control over memory updates and may be preferred when working with agents that are better at using tools than managing text tags.

Example configuration:

const memory = new Memory({
  options: {
    workingMemory: {
      enabled: true,
      template: "<user><first_name></first_name><last_name></last_name></user>",
      use: "tool-call", // or 'text-stream'
    },
  },
});

If no template is provided, the Memory class uses a default template that includes fields for user details, preferences, goals, and other contextual information. See the Agent Memory Guide for detailed usage examples and best practices.

embedder

By default, Memory uses FastEmbed with the bge-small-en-v1.5 model, which provides a good balance of performance and model size (~130MB). You only need to specify an embedder if you want to use a different model or provider.