# Knowledge Graph

An implementation of the MCP server based on txtai, providing semantic search, knowledge graph, and AI text processing functions.

A Deno-based MCP server template that supports publishing through JSR.io and optional Deno Deploy hosting, including knowledge graph functionality implemented with the Deno KV database.

A knowledge graph memory server based on Neo4j, providing efficient storage and retrieval capabilities for AI interactions

An implementation of a persistent memory server based on knowledge graphs, allowing Claude to remember user information across different chats. It provides functions for creating, querying, updating, and deleting entities, relationships, and observations, and supports local JSON storage.

Flexible GraphRAG is a flexible platform that supports multi - data source document processing, automatic knowledge graph construction, hybrid search (full - text, vector, graph), and AI Q&A. It includes a FastAPI backend, an MCP server, and various front - end interfaces.

The AI Memory Protocol is a versioned, graph - based persistent memory system designed for AI programming agents, implemented using Sphinx - Needs, supporting the creation, search, update of memories, and integration with AI clients through the MCP protocol.

ATLAS is an intelligent task and knowledge management system built on TypeScript and Neo4j, designed for LLM agents, providing a three - layer management architecture for projects, tasks, and knowledge.

An implementation of a knowledge graph management MCP server based on Neo4j, providing standard interfaces for the storage and retrieval of graph databases.

An MCP server that connects AI agents with Apache Jena, providing SPARQL query functionality

NeoCoder is an AI programming assistance system based on the Neo4j knowledge graph. It enables the interaction between AI assistants and the knowledge graph through an MCP server, providing standardized coding workflows, dynamic instruction manuals, and project memory functions. The system supports multiple operation modes (incarnations), including basic programming, scientific research, decision - making analysis, complex system modeling, knowledge graph management, and code analysis. It stores workflow templates and execution records in Neo4j to ensure the traceability and standardization of the coding process.

Project Synapse is a revolutionary MCP server that transforms text into an interconnected knowledge network through semantic analysis and knowledge graph technology and autonomously generates insights. It combines Montague semantics and the Zettelkasten method to achieve the cognitive collaboration ability of AI.

This project adds custom memory paths and timestamp functions to the MCP team's Memory server, supporting the construction of a knowledge graph through LLM to manage interaction memory.

MCP Server Knowledge Graph Memory Project

A persistent memory server based on knowledge graphs that supports remembering user information across sessions and accumulating experience through an error - learning system. It provides functions for entity - relationship management, observation record storage, and error - solution management, and can be integrated into the Cursor MCP client.

An MCP memory server based on the Qdrant vector database, providing knowledge graph and semantic search capabilities.

The knowledge graph memory server is a persistent memory system based on a local knowledge graph that supports remembering user information across chat sessions.

An implementation of the MCP server based on txtai, providing semantic search, knowledge graph, and AI text processing functions, supporting local knowledge base construction and standardized interface access.

The Knowledge Graph Memory Server implements a persistent memory function and supports cross - session storage of user information

The Graphiti MCP Server is a multi - project knowledge graph server extension based on the official getzep/graphiti. It supports multi - server single - database configuration, provides a developer - friendly CLI tool, and can build temporary knowledge graphs for each project for AI agents to query through the model context protocol.

A Python memory MCP server based on a knowledge graph, using SQLite as the backend to achieve persistent memory storage and management across conversations.

A flexible resource management system that supports managing multiple types of resources (papers, web pages, books, etc.) and integrating with knowledge graphs, providing functions such as unified identification, structured notes, and status tracking.

SourceSage is an efficient MCP server designed for LLMs, used to remember key aspects of codebases, such as logic, style, and standards, and supports dynamic updates and fast retrieval.

A memory server implementing the Model Context Protocol (MCP), providing persistent memory storage and retrieval functions based on a knowledge graph for large language models.

A fully functional LightRAG MCP server that provides 22 complete tools, covering four major functional modules: document management, query operations, knowledge graphs, and system management, achieving 100% compatible integration with the LightRAG API.

Repo GraphRAG MCP Server is a service based on the MCP protocol that uses LightRAG and Tree - sitter to build a knowledge graph from code and text documents and provides functions such as question - answering and implementation planning.

The Neo4j MCP project connects LLMs with external systems through a standardized protocol to enable natural - language operation of Neo4j databases, knowledge graph storage, and Aura cloud service management.

An MCP server for the AI Memory Engine Cognee, supporting the construction of knowledge graphs from text and searching.

The MCP context manager is a solution for achieving cross - session persistent AI context through a knowledge graph, supporting multi - domain intelligent management.

An AI memory storage server based on knowledge graphs, providing persistent memory functions across interactions for AI models.

A knowledge graph service supporting both FastAPI and FastMCP protocols, providing core operation functions of the Qdrant vector database.