Claude Memory

Provides persistent memory capabilities for Claude to remember details across conversations and sessions.

python

0

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "towan912-claude-memory-mcp-cf": {
      "command": "python",
      "args": [
        "-m",
        "memory_mcp"
      ],
      "env": {
        "MEMORY_FILE_PATH": "YOUR_MEMORY_PATH"
      }
    }
  }
}

You can enable Claude to remember details across conversations by running a Memory MCP Server that stores and retrieves memories using a persistent store. This MCP integrates with Claude to provide automatic memory capture, semantic search, and memory consolidation, so you can rely on consistent context across sessions without manually saving information.

How to use

Use the Memory MCP Server with your MCP client to store, recall, and manage memories for Claude. The server operates locally and can be run as a separate process or container. You interact with it through standard MCP client calls exposed by the server, and Claude will automatically remember important details you share, recall preferences, and retrieve relevant memories when needed.

How to install

Prerequisites: ensure you have Python installed and available on your system. You will also need pip to install dependencies.

Option 1: Using Docker (Recommended)

# Clone the repository
git clone https://github.com/WhenMoon-afk/claude-memory-mcp.git
cd claude-memory-mcp

# Start with Docker Compose
docker-compose up -d

Configure Claude Desktop to use the containerized MCP server (see Docker Usage Guide for details).

Option 2: Standard Installation

Prerequisites:

Python 3.8-3.12
pip

Installation:

# Clone the repository
git clone https://github.com/WhenMoon-afk/claude-memory-mcp.git
cd claude-memory-mcp

# Install dependencies
pip install -r requirements.txt

# Run setup script
chmod +x setup.sh
./setup.sh

Claude Desktop Integration:

{
  "mcpServers": {
    "memory": {
      "command": "python",
      "args": ["-m", "memory_mcp"],
      "env": {
        "MEMORY_FILE_PATH": "/path/to/your/memory.json"
      }
    }
  }
}

Additional configuration and notes

The Memory MCP Server supports automatic memory capture, semantic search, and automatic memory consolidation to keep short-term memories flowing into long-term storage. - You can tune memory retention and forgetting behavior through environment configuration and system prompts to fit your privacy and usage preferences.

Memory-related prompts and recall are designed to be seamless. You can ask Claude what it remembers or what it knows about your preferences to verify the memory dynamics.

Troubleshooting

If you encounter issues, try the following steps:

Check the compatibility and requirements for your Python version (3.8–3.12).
For NumPy issues, install a compatible version with: pip install "numpy>=1.20.0,<2.0.0".
For easier deployment, consider using Docker to avoid local environment conflicts.

Available tools

store_memory

Store a memory item into the memory store for later recall across conversations.

retrieve_memory

Retrieve memories that match a given query or context.

semantic_search

Search memories using semantic similarity to surface relevant past information.

memory_consolidation

Consolidate short-term memories into long-term storage to persist across sessions.

automatic_memory

Automatically capture important details from conversations without explicit commands.