Knowledge Graph Memory Server
by shaneholloman
This server provides a persistent memory implementation using a local knowledge graph, allowing Claude to remember information across chats. It's a fork of the original Memory Server, designed to avoid the ephemeral memory npx installation method.
Last updated: N/A
What is Knowledge Graph Memory Server?
The Knowledge Graph Memory Server is an implementation of persistent memory that leverages a local knowledge graph. It allows a language model like Claude to retain and recall information about users and interactions across multiple chat sessions.
How to use Knowledge Graph Memory Server?
To use the server, you need to configure it within your claude_desktop_config.json file. This involves specifying the command and arguments to start the server, including the optional --memory-path argument to customize the location of the memory file. You can also define a system prompt to guide the language model in utilizing the memory effectively.
Key features of Knowledge Graph Memory Server
Persistent memory using a local knowledge graph
Customizable memory path
API for creating, reading, updating, and deleting entities, relations, and observations
Tools for searching nodes and retrieving specific nodes
Integration with Claude Desktop
Use cases of Knowledge Graph Memory Server
Chat personalization by remembering user preferences and history
Building context-aware applications that adapt to user behavior
Creating a knowledge base for a language model to draw upon
Enabling long-term memory for AI agents
FAQ from Knowledge Graph Memory Server
What are entities?
What are entities?
Entities are the primary nodes in the knowledge graph, representing real-world objects or concepts. 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, representing one fact per observation.
How do I specify a custom memory path?
How do I specify a custom memory path?
You can specify a custom memory path using the --memory-path argument when starting the server. This allows you to control where the memory file is stored.
What is the license for this server?
What is the license for this server?
This MCP server is licensed under the MIT License, allowing you to use, modify, and distribute the software freely, subject to the terms and conditions of the license.