# Knowledge graph

xgmem is a TypeScript-based MCP memory server that provides project-specific and knowledge graph-driven memory storage for tools like Claude and LLM agents, supporting cross-project knowledge sharing and persistent storage.

MCP Memory is a memory server designed for data-intensive applications, enabling session memory management and multi-source information retrieval through the efficient HippoRAG knowledge graph.

MCP Klaudium is an enhanced memory server with dynamic compression, context management, and thought process integration capabilities. It realizes entity - relationship storage and retrieval based on a knowledge graph and supports temporal awareness and memory importance evaluation.

A knowledge graph server based on Neo4j, integrating AI models and the MCP protocol, supporting dynamic knowledge management and semantic search.

MemoryMesh is a knowledge graph server designed for AI models, focusing on text RPGs and interactive narratives, helping AI maintain structured memory across conversations.

Ummon is a code analysis tool that enhances the understanding of codebases by building a code knowledge graph. It supports multi-language code analysis, an advanced query system, and intelligent recommendation functions.

RDF Explorer is a server based on the MCP protocol, providing knowledge graph exploration and analysis functions in local file or SPARQL endpoint modes, supporting natural language queries and SPARQL query conversion.

Cognee is an open - source project that provides memory functions for AI agents. It builds a dynamic knowledge graph through a modular ECL pipeline, supports multiple data sources and formats, reduces hallucinations, and lowers costs.

MemCP is an extensible memory MCP server designed for AI programming agents. It is extended based on Zep AI's Graphiti project, supports building, maintaining, and querying temporal knowledge graphs, and provides entity extraction, persistent storage, and support for multiple transport protocols.

The MCP Chat Analysis Server is a service based on the Model Context Protocol (MCP), providing semantic analysis functions for chat conversations, including vector embedding search, knowledge graph construction, and conversation pattern analysis.

An MCP server providing a SPARQL endpoint query tool

A Python - based service application that provides functions for getting metadata from SharePoint and retrieving entities from the Neo4j knowledge graph through semantic similarity search.

The Neo4j MCP Server is a knowledge graph storage service that supports environment variable configuration and is compatible with the Model Context Protocol.

The Graphiti MCP Server is a server based on multi - project knowledge graphs, supporting the rapid construction and management of temporary knowledge graphs for AI agents to query through the model context protocol. This project extends the official getzep/graphiti MCP Server, adds support for multiple servers and a single database, and provides a CLI tool with an optimized developer experience.

MCP Memory is a persistent memory system based on Elasticsearch, providing long - term memory storage capabilities for AI conversations and solving the problem of context loss in traditional AI conversations.

MCPKG is a knowledge graph system implemented in Go language, providing storage, management, and query functions for structured information through the Model Context Protocol (MCP), and supporting semantic triple operations and persistent storage.

A service implementing the Model Context Protocol (MCP) for managing Claude's memory and knowledge graph, supporting local development and testing.

The MCP Neo4j Knowledge Graph Memory Server is an enhanced memory storage system based on the Neo4j graph database, providing high-performance knowledge graph storage and retrieval capabilities for AI assistants.

Stardog MCP Server is a server that implements the MCP protocol for interacting with the Stardog database API, providing automation and interaction capabilities for developers and tools.

A project to import the Precision Medicine Knowledge Graph (PrimeKG) into the Neo4j database for biomedical data analysis and exploration.

MCP service integrating knowledge graph and vector database based on SQLite