Memoer (Persistent Memory Storage)

Memoer (Persistent Memory Storage)

geli2001

Provides persistent memory storage for AI assistants using SQLite, allowing them to create, retrieve, update and delete memories with filtering by app, category, and other criteria.

Provides persistent memory storage for assistants to create and retrieve memories with filtering options by app name, category, and result limits through a SQLite database with automatic setup.

9491 views2Local (stdio)

What it does

  • Store persistent memories in SQLite database
  • Retrieve memories with filtering options
  • Update and delete existing memories
  • Organize memories by user, app, and category
  • Search memories semantically with Qdrant integration

Best for

AI assistants needing long-term memoryChatbots that remember user preferencesApplications requiring persistent context storage
Automatic SQLite database setupTypeScript-first designSemantic search capabilities

About Memoer (Persistent Memory Storage)

Memoer (Persistent Memory Storage) is a community-built MCP server published by geli2001 that provides AI assistants with tools and capabilities via the Model Context Protocol. Memoer offers unlimited free cloud storage and data management with persistent memory via SQLite for assistants—secure, It is categorized under ai ml.

How to install

You can install Memoer (Persistent Memory Storage) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

License

Memoer (Persistent Memory Storage) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

@memoer-mcp

A minimal, pluggable memory management library for Node.js, inspired by OpenMemory. Supports local SQLite storage, semantic search (Qdrant), and OpenAI embeddings. No web server, no frontend—just a programmatic API.

Features

  • Add, list, update, delete memories
  • Semantic search (Qdrant)
  • User, app, and category support
  • Local SQLite (via Prisma)
  • TypeScript-first

Getting Started

  1. Install dependencies:

    npm install
    
  2. Initialize the database:

    npx prisma migrate dev --name init
    
  3. Configure the MCP: Create or update your MCP configuration file (e.g., mcp_config.json) as follows:

    {
      "memoer-mcp": {
        "command": "npx",
        "args": ["memoer-mcp@latest"],
        "env": {
          "DATABASE_URL": "file:/Users/{your_username}/{any_folder_path}/memoer.db" //macOS example
        }
      }
    }
    
  4. Use the library in your project:

    import { MemoerMCP } from "@memoer-mcp";
    
    const memoer = new MemoerMCP();
    
    // Example: Adding a memory
    await memoer.addMemory({
      title: "My First Memory",
      content: "This is the content of my first memory.",
      category: "Personal"
    });
    
    // Example: Listing memories
    const memories = await memoer.listMemories();
    console.log(memories);
    

Development

  • Edit the Prisma schema in prisma/schema.prisma
  • Run npx prisma generate after changes
  • Source code in src/

This library is now fully functional and ready for use in your projects!


### MCP Configuration Example

In your `mcp_config.json`, you can configure the `memoer-mcp` command as follows:

```json
{
  "memoer-mcp": {
    "command": "npx",
    "args": ["memoer-mcp@latest"],
    "env": {
      "DATABASE_URL": "file:/Users/{your_username}/{any_folder_path}/memoer.db" //macOS example
    }
  }
}

Explanation of Configuration

  • command: This specifies the command to run, which in this case is npx to execute the memoer-mcp package.
  • args: This is an array of arguments passed to the command. Here, it specifies the package to run.
  • env: This section allows you to set environment variables needed for your application. The DATABASE_URL points to your SQLite database file.

Usage

With this setup, you can now run memoer-mcp from your command line or integrate it into your application as shown in the examples. This configuration allows you to manage memories effectively using the memoer-mcp library.

If you have any further questions or need additional examples, feel free to ask!

License

This project is licensed under the MIT License - see the LICENSE file for details.

Alternatives

Related Skills

Browse all skills