claude-memory-mcp
If you are the rightful owner of claude-memory-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server implementation providing persistent memory capabilities for Large Language Models, designed for integration with the Claude desktop application.
The Claude Memory MCP Server is a sophisticated implementation designed to enhance the memory capabilities of Large Language Models, specifically tailored for the Claude desktop application. It employs a tiered memory architecture to manage short-term, long-term, and archival memories, allowing for seamless memory retention and recall across sessions. The server supports various memory types, including conversations, knowledge, entities, and reflections, and utilizes semantic search to retrieve memories based on similarity. With automatic memory management, the server intelligently captures and consolidates memories without requiring explicit commands, ensuring that important information is retained while less relevant data is forgotten. The server is fully compatible with the Model Context Protocol and can be easily deployed using Docker containers, making it a versatile and efficient solution for enhancing LLM memory capabilities.
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
- Automatic Memory Management: Intelligent memory capture without explicit commands
- Claude Integration: Ready-to-use integration with Claude desktop application
