Memory Plus

v1.0.0β€’Knowledge & Memoryβ€’stable

🧠 π‘΄π’†π’Žπ’π’“π’š-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent 'memories' across sessionsβ€”perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copi

agenthackathonmcpmcp-servermemory
Share:
58
Stars
0
Downloads
0
Weekly
0/5

What is Memory Plus?

Memory Plus is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🧠 π‘΄π’†π’Žπ’π’“π’š-𝑷𝒍𝒖𝒔 is a lightweight, local rag memory store for mcp agents. easily record, retrieve, update, delete, and visualize persistent 'memories' across sessionsβ€”perfect for developers wo...

🧠 π‘΄π’†π’Žπ’π’“π’š-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent 'memories' across sessionsβ€”perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copi

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🧠 π‘΄π’†π’Žπ’π’“π’š-𝑷𝒍𝒖𝒔 is a lightweight, local RAG memory store for M

Use Cases

Lightweight local RAG memory for agents
Persistent memories across sessions
Yuchen20

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 16, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y memory-plus

Manual Installation

npx -y memory-plus

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Memory Plus

Memory Plus is a lightweight local RAG (Retrieval-Augmented Generation) memory store for MCP agents that lets AI assistants record, retrieve, update, and delete persistent memories across sessions using Google's Gemini Embedding API for semantic similarity. It stores all memories locally as files (no cloud database required) and includes an interactive graph visualisation for exploring the memory network. Developers using Windsurf, Cursor, Claude Code, or Copilot use it to give their AI coding assistants persistent project knowledge that survives context resets.

Prerequisites

  • Python 3.10 or later and uv installed (recommended) or pip
  • A Google AI Studio API key for the Gemini Embedding API (free tier available at aistudio.google.com/apikey)
  • An MCP-compatible client such as Claude Code, Cursor, or Windsurf
  • The GOOGLE_API_KEY environment variable set to your API key
1

Obtain a Google AI Studio API key

Visit aistudio.google.com/apikey, sign in with a Google account, and generate a new API key. Copy itβ€”it is used by Memory Plus for embedding generation.

2

Install uv (recommended runner)

uv provides dependency-isolated execution via uvx. Install it with the official installer or via pip.

curl -LsSf https://astral.sh/uv/install.sh | sh
3

Open your MCP client configuration

For Claude Code edit ~/.claude/settings.json or the project-level .mcp.json. For Cursor open its MCP settings file (usually .cursor/mcp.json).

4

Add the Memory Plus server entry

Add the mcpServers block with your GOOGLE_API_KEY. Using uvx ensures the latest version of memory-plus is used without a manual install step.

{
  "mcpServers": {
    "memory-plus": {
      "command": "uvx",
      "args": ["-q", "memory-plus@latest"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key"
      }
    }
  }
}
5

Restart your MCP client

Reload Claude Code or Cursor to start the Memory Plus server. uvx will download the package on first run.

6

Store your first memory

Ask your AI assistant to record a memory. From this point on, the agent can recall relevant memories automatically at the start of new sessions.

Memory Plus Examples

Client configuration

MCP config for Claude Code using uvx. Replace the GOOGLE_API_KEY value with your actual key from Google AI Studio.

{
  "mcpServers": {
    "memory-plus": {
      "command": "uvx",
      "args": ["-q", "memory-plus@latest"],
      "env": {
        "GOOGLE_API_KEY": "your-google-api-key"
      }
    }
  }
}

Prompts to try

Example requests that exercise the memory record, retrieve, search, update, and visualise capabilities.

- "Remember that we use PostgreSQL 15 with the pgvector extension for this project"
- "What do you remember about the database setup for this project?"
- "Search your memories for anything related to authentication or JWT tokens"
- "Show me the most recent memories you have stored"
- "Update your memory about the API rate limits to reflect the new 1000 req/min limit"
- "Delete all memories tagged with the 'temporary' keyword"
- "Open the memory graph visualisation so I can see how my memories are connected"

Troubleshooting Memory Plus

API key error: GOOGLE_API_KEY is invalid or missing

Ensure the GOOGLE_API_KEY env var is set in your MCP config and that the key is active at aistudio.google.com/apikey. The free tier includes sufficient quota for typical memory operations.

uvx command not found

uv is not installed or not in your PATH. Install it with: curl -LsSf https://astral.sh/uv/install.sh | sh (macOS/Linux). After installation, restart your terminal or run 'source ~/.zshrc'. Alternatively install via pip: pip install uv.

Memories are not persisted between sessions

Memory Plus stores data in a local directory. Ensure the process has write access to its working directory. If you run different MCP clients under different user accounts, each will have a separate memory store. Check the logs for any file permission errors.

Frequently Asked Questions about Memory Plus

What is Memory Plus?

Memory Plus is a Model Context Protocol (MCP) server that 🧠 π‘΄π’†π’Žπ’π’“π’š-𝑷𝒍𝒖𝒔 is a lightweight, local rag memory store for mcp agents. easily record, retrieve, update, delete, and visualize persistent 'memories' across sessionsβ€”perfect for developers working with multiple ai coders (like windsurf, cursor, or copi It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Memory Plus?

Install via npm with the command: npx -y memory-plus. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Memory Plus?

Memory Plus works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Memory Plus free to use?

Yes, Memory Plus is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "memory-plus": { "command": "npx", "args": ["-y", "memory-plus"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide β†’

Ready to use Memory Plus?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides