LABSCO SUMMARY

Memory you can look at, not just query.

The graph visualisation is the unusual part: most memory servers are a black box you can only interrogate one question at a time, and seeing the clusters tells you whether the thing is learning anything useful. Versioning on update is the other good decision - a corrected memory does not erase what it replaced.

What it is

A lightweight retrieval-augmented memory that runs on your machine. Notes, ideas and session context are embedded and kept between runs, with a visual graph view of how entries cluster.

What you get

Recording user data, ideas and context as memories
Retrieval by keyword or topic over everything stored, and a quick fetch of the most recent entries
Updating an entry by appending to it or modifying it, with older versions kept so there is a history
Importing a document straight into memory, and deleting entries you no longer want
An interactive graph visualisation showing how memories cluster and relate
Guidance delivered as resources, teaching the model when to recall past interactions and when not to

Requirements

The uv runtime, and a Google API key in GOOGLE_API_KEY - used only for the Gemini embedding endpoint, which the author notes is free to use. Clients launch it with uvx and the package name; VS Code has a one-click install link, and Cursor and Cline take the same JSON block. The first run pulls dependencies and takes about a minute before it becomes responsive.

Setup effort

One command plus a key — uvx -q memory-plus@latest, then supply credentials

See installation options

USE CASES

01

Keeping context across sessions

Record decisions and preferences as you work, and pull the recent entries at the start of the next run.

02

Getting a document into the agent's memory

Import the file directly rather than pasting its contents into the conversation.

03

Checking whether the memory is any good

Open the graph view and look at how entries cluster, instead of guessing from individual recalls.

04

Correcting something that changed

Update the entry rather than adding a contradicting one - the previous version is kept as history.

BEFORE YOU INSTALL

What to know first

Requires

uvx on PATH
GOOGLE_API_KEY in your environment

Where it runs

All 3 documented clients run the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

uvx -q memory-plus@latest

MCP Clients

VS Code

VS CODE · JSON

{
  "servers": {
    "memory-plus": {
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ]
    }
  }
}

This block passes no key. Set GOOGLE_API_KEY in your environment before starting VS Code, or add "env": {"GOOGLE_API_KEY": "<YOUR_API_KEY>"} just after the args array.

Cursor

CURSOR · JSON

{
  "mcpServers": {
    "memory-plus": {
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ],
      "env": {
        "GOOGLE_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Cline

CLINE · JSON

{
  "mcpServers": {
    "memory-plus": {
      "disabled": false,
      "timeout": 300,
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ],
      "env": {
        "GOOGLE_API_KEY": "<YOUR_API_KEY>"
      },
      "transportType": "stdio"
    }
  }
}

Memory-Plus