Skip to main content

Memory.query()

the .query() method retrieves messages from a specific thread, with support for pagination, filtering options, and semantic search.

Usage Example​

await memory?.query({ threadId: "user-123" });

Parameters​

threadId:

string
The unique identifier of the thread to retrieve messages from

resourceId?:

string
Optional ID of the resource that owns the thread. If provided, validates thread ownership

selectBy?:

object
Options for filtering and selecting messages

threadConfig?:

MemoryConfig
Configuration options for message retrieval and semantic search

format?:

'v1' | 'v2'
Message format to return. Defaults to 'v2' for current format, 'v1' for backwards compatibility

selectBy parameters​

vectorSearchString?:

string
Search string for finding semantically similar messages. Requires semantic recall to be enabled in threadConfig.

last?:

number | false
Number of most recent messages to retrieve. Set to false to disable limit. Note: threadConfig.lastMessages (default: 10) will override this if smaller.

include?:

{ id: string; threadId?: string; withPreviousMessages?: number; withNextMessages?: number }[]
Array of specific message IDs to include with optional context messages. Each item has an `id` (required), optional `threadId` (defaults to main threadId), `withPreviousMessages` (number of messages before, defaults to 2 for vector search, 0 otherwise), and `withNextMessages` (number of messages after, defaults to 2 for vector search, 0 otherwise).

threadConfig parameters​

lastMessages?:

number | false
= 10
Number of most recent messages to retrieve. Set to false to disable.

semanticRecall?:

boolean | { topK: number; messageRange: number | { before: number; after: number }; scope?: 'thread' | 'resource' }
= false
Enable semantic search in message history. Can be a boolean or an object with configuration options. When enabled, requires both vector store and embedder to be configured.

workingMemory?:

WorkingMemory
= { enabled: false, template: '# User Information\n- **First Name**:\n- **Last Name**:\n...' }
Configuration for working memory feature. Can be `{ enabled: boolean; template?: string; schema?: ZodObject<any> | JSONSchema7; scope?: 'thread' | 'resource' }` or `{ enabled: boolean }` to disable.

threads?:

{ generateTitle?: boolean | { model: DynamicArgument<MastraLanguageModel>; instructions?: DynamicArgument<string> } }
= { generateTitle: false }
Settings related to memory thread creation. `generateTitle` controls automatic thread title generation from the user's first message. Can be a boolean or an object with custom model and instructions.

Returns​

messages:

CoreMessage[]
Array of retrieved messages in their core format

uiMessages:

UIMessageWithMetadata[]
Array of messages formatted for UI display, including proper threading of tool calls and results

Extended usage example​

src/test-memory.ts
import { mastra } from "./mastra";

const agent = mastra.getAgent("agent");
const memory = await agent.getMemory();

const { messages, uiMessages } = await memory!.query({
  threadId: "thread-123",
  selectBy: {
    last: 50,
    vectorSearchString: "What messages are there?",
    include: [
      {
        id: "msg-123",
      },
      {
        id: "msg-456",
        withPreviousMessages: 3,
        withNextMessages: 1,
      },
    ],
  },
  threadConfig: {
    semanticRecall: true,
  },
});

console.log(messages);
console.log(uiMessages);