MastraStorage

MastraStorage provides a unified interface for managing

• Workflow Tracking, allowing users to suspend and resume workflow runs.
• Memory, threads and messages per resourceId in your application
• Traces - OpenTelemetry traces from all components of Mastra
• Evaluation Datasets - as evaluations are run, the scores and reasons are stored in datasets.

Mastra provides different storage providers, but you can treat them as interchangeable. Eg, you could use libsql in development but postgres in production, and your code will work the same both ways.

Data Schema

Memory

Messages

Stores conversation messages and their metadata. Each message belongs to a thread and contains the actual content along with metadata about the sender role and message type.

Threads

Groups related messages together and associates them with a resource. Contains metadata about the conversation.

Workflows

Preserves workflow execution states and enables resuming workflows:

Evaluation Datasets

Stores evaluation results from running metrics against agent outputs:

Traces

Captures OpenTelemetry traces for monitoring and debugging:

Configuration

Mastra can be configured with a default storage option:

import { Mastra } from '@mastra/core/mastra';
import { DefaultStorage } from '@mastra/core/storage/libsql';
 
const mastra = new Mastra({
  storage: new DefaultStorage({
    config: {
      url: "file:storage.db",
    }
  }),
});

Other Storage Providers

If you want to use other storage, check out the following providers:

• LibSQL Storage
• PostgreSQL Storage
• Upstash Storage