AgentWong_optimized-memory-mcp-server
If you are the rightful owner of AgentWong_optimized-memory-mcp-server 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.
The optimized-memory-mcp-server is a Python-based fork of a Memory MCP Server, utilizing SQLite for backend storage, designed to demonstrate AI workflows and prompt design.
The optimized-memory-mcp-server is a knowledge graph memory server that provides a basic implementation of persistent memory using a local knowledge graph. It allows for the storage and retrieval of information about users across different interactions. The server uses entities, relations, and observations to structure data, enabling the creation of a dynamic and interconnected knowledge graph. Entities are the primary nodes, each with a unique identifier, type, and list of observations. Relations define directed connections between entities, while observations are discrete pieces of information attached to entities. The server offers a comprehensive API with tools for creating, deleting, and managing entities, relations, and observations, as well as searching and reading the entire graph. This server is particularly useful for applications requiring memory persistence, such as chat personalization, where it can remember user information and preferences across sessions.
Features
- Persistent memory using a local knowledge graph
- Entity, relation, and observation management
- Comprehensive API for graph operations
- Search and retrieval of graph data
- Integration with Claude Desktop for chat personalization
