trackmcp
Back to directory
Yuchen20

Memory-Plus

View on GitHub

๐Ÿง  ๐‘ด๐’†๐’Ž๐’๐’“๐’š-๐‘ท๐’๐’–๐’” is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessionsโ€”perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.

41 stars PythonAI & Machine Learning Updated Oct 17, 2025
agenthackathonmcpmcp-servermemorymemory-storemodel-context-protocol

Documentation

memory_plus
pretty image
License: MIT
visitors
PyPI version
PyPI Downloads

Memory-Plus

A lightweight, local Retrieval-Augmented Generation (RAG) memory store for MCP agents. Memory-Plus lets your agent record, retrieve, update, and visualize persistent "memories"โ€”notes, ideas, and session contextโ€”across runs.

> ๐Ÿ† First Place at the Infosys Cambridge AI Centre Hackathon!

Key Features

  • Record Memories๏ผšSave user data, ideas, and important context.
  • Retrieve Memories๏ผšSearch by keywords or topics over past entries.
  • Recent Memories๏ผšFetch the last *N* items quickly.
  • Update Memories๏ผšAppend or modify existing entries seamlessly.
  • Visualize Memories๏ผšInteractive graph clusters revealing relationships.
  • File Import (*since v0.1.2*)๏ผšIngest documents directly into memory.
  • Delete Memories (*since v0.1.2*)๏ผšRemove unwanted entries.
  • Memory for Memories (*since v0.1.4*)๏ผšNow we use `resources` to teach your AI exactly when (and when not) to recall past interactions.
  • Memory Versioning (*since v0.1.4*)๏ผšWhen memories are updated, we keep the old versions to provide a full history.

alt text

Installation

1. Prerequisites

Google API Key

Obtain from Google AI Studio and set as `GOOGLE_API_KEY` in your environment.

> Note that we will only use the `Gemini Embedding API` with this API key, so it is Entirely Free for you to use!

Setup Google API Key Example

bash
# macOS/Linux
  export GOOGLE_API_KEY=""

  # Windows (PowerShell)
  setx GOOGLE_API_KEY ""

UV Runtime

Required to serve the MCP plugin.

Install UV Runtime

bash
pip install uv

Or install via shell scripts:

bash
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

VS Code One-Click Setup

Click the badge below to automatically install and configure Memory-Plus in VS Code:

One Click Install in VS Code

This will add the following to your `settings.json`:

json
{
    "mcpServers": {
      //...,  your other MCP servers
      "memory-plus": {
        "command": "uvx",
        "args": [
          "-q",
          "memory-plus@latest"
        ],
      }
    }
  }

For `cursor`, go to `file -> Preferences -> Cursor Settings -> MCP` and add the above config.

If you didn't add the `GOOGLE_API_KEY` to your secrets / environment variables, you can add it with:

json
"env": {
        "GOOGLE_API_KEY": ""
      }

just after the `args` array with in the `memory-plus` dictionary.

For `Cline` add the following to your `cline_mcp_settings.json`:

json
{
  "mcpServers": {
    //...,  your other MCP servers
    "memory-plus": {
      "disabled": false,
      "timeout": 300,
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ],
      "env": {
        "GOOGLE_API_KEY": "${{ secrets.GOOGLE_API_KEY }}"
      },
      "transportType": "stdio"
    }
  }
}

For other IDEs it should be mostly similar to the above.

Local Testing and Development

Using MCP Inspector, you can test the memory-plus server locally.

bash
git clone https://github.com/Yuchen20/Memory-Plus.git
cd Memory-Plus
npx @modelcontextprotocol/inspector fastmcp run run .\\memory_plus\\mcp.py

Or If you prefer using this MCP in an actual Chat Session. There is a template chatbot in `agent.py`.

bash
# Clone the repository
git clone https://github.com/Yuchen20/Memory-Plus.git
cd Memory-Plus

# Install dependencies
pip install uv
uv pip install fast-agent-mcp
uv run fast-agent setup

setup the `fastagent.config.yaml` and `fastagent.secrets.yaml` with your own API keys.

bash
# Run the agent
uv run agent_memory.py

RoadMap

  • [x] Memory Update
  • [x] Improved prompt engineering for memory recording
  • [x] Better Visualization of Memory Graph
  • [x] File Import
  • [ ] Remote backup!
  • [ ] Web UI for Memory Management

> If you have any feature requests, please feel free to add them by adding a new issue or by adding a new entry in the Feature Request

License

This project is licensed under the Apache License 2.0. See LICENSE for details.

FAQ

1. Why is memory-plus not working?

  • Memory-plus has a few dependencies that can be slow to download the first time. It typically takes around 1 minute to fetch everything needed.
  • Once dependencies are installed, subsequent usage will be much faster.
  • If you experience other issues, please feel free to open a new issue on the repository.

2. How do I use memory-plus in a real chat session?

  • Simply add the MCP JSON file to your MCP setup.
  • Once added, memory-plus will automatically activate when needed.

Frequently asked questions

What is Memory-Plus?

Memory-Plus is ๐Ÿง  ๐‘ด๐’†๐’Ž๐’๐’“๐’š-๐‘ท๐’๐’–๐’” is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessionsโ€”perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually remember them.

How do I install Memory-Plus?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is Memory-Plus open source?

Yes โ€” it is hosted on GitHub at https://github.com/Yuchen20/Memory-Plus and has 41 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP