Claude Memory MCP Server

An MCP (Model Context Protocol) server implementation that provides persistent memory capabilities for Large Language Models, specifically designed to integrate with the Claude desktop application.

Overview

This project implements optimal memory techniques based on comprehensive research of current approaches in the field. It provides a standardized way for Claude to maintain persistent memory across conversations and sessions.

Features

**Tiered Memory Architecture**: Short-term, long-term, and archival memory tiers

**Multiple Memory Types**: Support for conversations, knowledge, entities, and reflections

**Semantic Search**: Retrieve memories based on semantic similarity

**Memory Consolidation**: Automatic consolidation of short-term memories into long-term memory

**Memory Management**: Importance-based memory retention and forgetting

**Claude Integration**: Ready-to-use integration with Claude desktop application

**MCP Protocol Support**: Compatible with the Model Context Protocol

Architecture

The MCP server follows a functional domain-based architecture with the following components:

Functional Domains

**Episodic Domain**: Manages session-based interactions and contextual memory

**Semantic Domain**: Handles knowledge organization and retrieval

**Temporal Domain**: Controls time-aware processing of memories

**Persistence Domain**: Manages storage optimization and retrieval

Installation

Prerequisites

Python 3.8 or higher

pip package manager

Installation Steps

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

Install dependencies: ``` pip install -e . ```

Run the setup script: ``` chmod +x setup.sh ./setup.sh ```

Claude Desktop Integration

To integrate with the Claude desktop application, add the following to your Claude configuration file:

Memory File Structure

The memory system uses a JSON-based file structure with the following components:

Usage

Starting the Server

Available Tools

`store_memory`: Store new information in memory

`retrieve_memory`: Retrieve relevant memories based on query

`list_memories`: List available memories with filtering options

`update_memory`: Update existing memory entries

`delete_memory`: Remove specific memories

`memory_stats`: Get statistics about the memory store

Development

Project Structure

Running Tests

Research Background

This implementation is based on comprehensive research of current LLM persistent memory techniques:

**OS-Inspired Memory Management**: Tiered memory architecture similar to MemGPT

**Biological-Inspired Episodic Memory**: Context-sensitive memory retrieval

**Vector Embeddings**: Semantic search inspired by vector database approaches

**Self-Reflection**: Memory consolidation through periodic review

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

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

Acknowledgements

Based on research of optimal memory techniques for LLMs

Implements the Model Context Protocol for integration with Claude

Claude Memory