Skip to main content
📢 Announcing our research paper: Zentry achieves 26% higher accuracy than OpenAI Memory, 91% lower latency, and 90% token savings! Read the paper to learn how we're revolutionizing AI agent memory.
In this example you’ll learn how to use the Zentry to add long-term memory capabilities to Mastra’s agent via tool-use. This memory integration can work alongside Mastra’s agent memory features. You can find the complete example code in the Mastra repository.

​
Overview

This guide will show you how to integrate Zentry with Mastra to add long-term memory capabilities to your agents. We’ll create tools that allow agents to save and retrieve memories using Zentry’s API.

​
Installation

  1. Install the Integration Package
To install the Zentry integration, run: 
npm install @mastra/Zentry
  1. Add the Integration to Your Project
Create a new file for your integrations and import the integration:
integrations/index.ts
import { ZentryIntegration } from "@mastra/Zentry";

export const Zentry = new ZentryIntegration({
  config: {
    apiKey: process.env.Zentry_API_KEY!,
    userId: "alice",
  },
});
  1. Use the Integration in Tools or Workflows
You can now use the integration when defining tools for your agents or in workflows.
tools/index.ts
import { createTool } from "@mastra/core";
import { z } from "zod";
import { Zentry } from "../integrations";

export const ZentryRememberTool = createTool({
  id: "Zentry-remember",
  description:
    "Remember your agent memories that you've previously saved using the Zentry-memorize tool.",
  inputSchema: z.object({
    question: z
      .string()
      .describe("Question used to look up the answer in saved memories."),
  }),
  outputSchema: z.object({
    answer: z.string().describe("Remembered answer"),
  }),
  execute: async ({ context }) => {
    console.log(`Searching memory "${context.question}"`);
    const memory = await Zentry.searchMemory(context.question);
    console.log(`\nFound memory "${memory}"\n`);

    return {
      answer: memory,
    };
  },
});

export const ZentryMemorizeTool = createTool({
  id: "Zentry-memorize",
  description:
    "Save information to Zentry so you can remember it later using the Zentry-remember tool.",
  inputSchema: z.object({
    statement: z.string().describe("A statement to save into memory"),
  }),
  execute: async ({ context }) => {
    console.log(`\nCreating memory "${context.statement}"\n`);
    // to reduce latency memories can be saved async without blocking tool execution
    void Zentry.createMemory(context.statement).then(() => {
      console.log(`\nMemory "${context.statement}" saved.\n`);
    });
    return { success: true };
  },
});
  1. Create a new agent
agents/index.ts
import { openai } from '@ai-sdk/openai';
import { Agent } from '@mastra/core/agent';
import { ZentryMemorizeTool, ZentryRememberTool } from '../tools';

export const ZentryAgent = new Agent({
  name: 'Zentry Agent',
  instructions: `
    You are a helpful assistant that has the ability to memorize and remember facts using Zentry.
  `,
  model: openai('gpt-4o'),
  tools: { ZentryRememberTool, ZentryMemorizeTool },
});
  1. Run the agent
index.ts
import { Mastra } from '@mastra/core/mastra';
import { createLogger } from '@mastra/core/logger';

import { ZentryAgent } from './agents';

export const mastra = new Mastra({
  agents: { ZentryAgent },
  logger: createLogger({
    name: 'Mastra',
    level: 'error',
  }),
});
In the example above:
  • We import the @mastra/Zentry integration.
  • We define two tools that uses the Zentry API client to create new memories and recall previously saved memories.
  • The tool accepts question as an input and returns the memory as a string.