Mastra + Memanto

Add persistent memory to any Mastra agent with three ready-made tools, shipped as part of the @moorcheh-ai/memanto TypeScript SDK.

Prerequisites

Node.js 20+
uv (ships uvx) — the Memanto client spawns a local Memanto server via uvx on first use unless you pass baseUrl
Memanto / Moorcheh credentials — Moorcheh API key (cloud) or an on-prem backend (no Moorcheh API key). Set MOORCHEH_API_KEY or pass apiKey to new Memanto({ ... })
Agent model credentials — the quick start uses openai/gpt-4o for tool orchestration. Configure your OpenAI API key for Mastra (typically OPENAI_API_KEY).
@mastra/core and zod installed in your app (optional peer dependencies of @moorcheh-ai/memanto)

Install

npm install @moorcheh-ai/memanto @mastra/core zod

@mastra/core and zod are optional peer dependencies of @moorcheh-ai/memanto — install them yourself in the host app. Importing @moorcheh-ai/memanto/mastra without them installed will fail at module load with a standard Node resolution error.

Quick Start

import { Agent } from "@mastra/core/agent";
import { Memanto } from "@moorcheh-ai/memanto";
import { createMemantoMastraTools } from "@moorcheh-ai/memanto/mastra";

const memanto = new Memanto({
  agentId: "my-agent",
  apiKey: process.env.MOORCHEH_API_KEY, // omit when using on-prem; see On-Prem below
});

const agent = new Agent({
  id: "assistant",
  name: "Assistant",
  instructions:
    "You have long-term memory. Persist durable facts with rememberMemory " +
    "and look them up with recallMemory / answerMemory before answering.",
  model: "openai/gpt-4o", // requires OPENAI_API_KEY — swap for your provider if needed
  tools: createMemantoMastraTools(memanto),
});

createMemantoMastraTools returns an object with three Mastra tools — pass it straight into an agent’s tools map. Each tool’s description is written for the model to decide when to call it (e.g. recallMemory: “Call this before answering whenever the user refers to information from earlier or from a previous session”).

Available Tools

Tool	Backed by	Description
`recallMemory`	Recall	Semantic search over stored memories. `query` (required), `limit` (1-50), `type` (optional array of memory types to filter by).
`rememberMemory`	Remember	Persist a durable fact/preference/decision/instruction. `content` (required), `type` (optional — server auto-classifies if omitted), `title`, `tags`.
`answerMemory`	Generate AI Answer	RAG-synthesized answer over stored memories. `question` (required), `limit` (1-100).

answerMemory calls Memanto’s Generate AI Answer API (memanto.answer() → Moorcheh answer.generate). Memanto retrieves relevant memories and synthesizes a grounded response using Memanto’s configured LLM — not the model you pass to your Mastra Agent. Your agent model only decides when to call the tool and how to use the result. recallMemory and rememberMemory do not invoke an LLM.

Options

createMemantoMastraTools(memanto, {
  include: ["recallMemory", "answerMemory"], // expose a subset — omit for all three
  defaultLimit: 10,                           // default limit for recall/answer when the model doesn't specify one
});

Memory Types

type fields are constrained to Memanto’s 13 supported types via a shared MEMORY_TYPES export:

import { MEMORY_TYPES } from "@moorcheh-ai/memanto/mastra";
// ["fact", "preference", "goal", "decision", "artifact", "learning", "event",
//  "instruction", "relationship", "context", "observation", "commitment", "error"]

See the Memory Types Reference for what each type means.

On-Prem

The integration talks to Memanto through the Memanto client, so it works identically against an on-prem backend — no code changes, just configure the backend once with the CLI. See On-Prem Overview and the TypeScript SDK Reference.

Next Steps

TypeScript SDK Reference for the full Memanto client API
Vercel AI SDK Integration for the equivalent AI SDK tools
OpenAI Integration for the equivalent OpenAI runTools() tools
Memory Types Reference

​Mastra + Memanto

​Prerequisites

​Install

​Quick Start

​Available Tools

​Options

​Memory Types

​On-Prem

​Next Steps