optimized-memory-mcp-server
by AgentWong
This is a fork of a Python Memory MCP Server that uses SQLite for a backend. It implements a basic persistent memory using a local knowledge graph, allowing Claude to remember information across chats.
Last updated: N/A
What is optimized-memory-mcp-server?
A Python Memory MCP Server that implements a persistent memory system using a local knowledge graph with SQLite as the backend. It's designed to allow Claude to retain information about users across multiple chat sessions.
How to use optimized-memory-mcp-server?
The server provides an API with tools for creating entities and relations, adding/deleting observations, reading the graph, and searching nodes. It can be integrated with Claude Desktop using Docker or NPX, as shown in the provided configuration examples. A system prompt example is provided to guide Claude in using the memory effectively.
Key features of optimized-memory-mcp-server
Persistent memory using a knowledge graph
SQLite backend for data storage
API for managing entities, relations, and observations
Integration with Claude Desktop
Tools for searching and retrieving information from the graph
Use cases of optimized-memory-mcp-server
Chat personalization by remembering user preferences
Building user profiles based on interactions
Tracking relationships between entities
Storing and retrieving facts about users and events
FAQ from optimized-memory-mcp-server
What are entities?
What are entities?
Entities are the primary nodes in the knowledge graph, representing people, organizations, or events. Each entity has a unique name, an entity type, and a list of observations.
What are relations?
What are relations?
Relations define directed connections between entities, describing how they interact or relate to each other. They are always stored in active voice.
What are observations?
What are observations?
Observations are discrete pieces of information about an entity, stored as strings and attached to specific entities. They should be atomic (one fact per observation).
How do I integrate this with Claude Desktop?
How do I integrate this with Claude Desktop?
You can integrate the server with Claude Desktop by adding the appropriate configuration to your claude_desktop_config.json file, using either Docker or NPX as shown in the README.
How do I build the Docker image?
How do I build the Docker image?
You can build the Docker image using the command docker build -t mcp/memory -f src/memory/Dockerfile .