Awesome MCPKnowledge & Memory

shaneholloman/mcp-knowledge-graph

⭐ 888 JavaScript repository created 2024-12-09

The mcp-knowledge-graph project is an MCP (Model Context Protocol) server designed to provide persistent memory for AI models by utilizing a local knowledge graph. This server enables AI models to retain user information across multiple interactions, enhancing the continuity and personalization of conversations. It is compatible with any AI platform that supports MCP or function calling capabilities, such as Claude, GPT, and Llama. The core concept of the project revolves around a knowledge graph composed of entities, relations, and observations. Entities represent primary nodes in the graph and have unique identifiers, types (like person, organization, event), and associated observations which are atomic facts about the entity. Relations define directed connections between entities, describing how they interact or relate in active voice. Observations are discrete pieces of information attached to entities and can be added or removed independently. The server exposes a comprehensive API with tools to create, read, update, and delete entities, relations, and observations. It supports operations like creating multiple entities or relations, adding or deleting observations, reading the entire graph, searching nodes by query, and retrieving specific nodes. This API design allows flexible and dynamic management of the knowledge graph memory. The project is a fork of the original Memory Server but improves on persistent memory by avoiding ephemeral memory installation methods and allowing a customizable memory file path. It integrates seamlessly with MCP-compatible AI platforms by exposing standard tools through the MCP interface. Usage instructions include configuration examples for Claude Desktop and other AI platforms, emphasizing the ability to specify a custom memory path. The project also provides guidance on system prompts to optimize memory usage during AI interactions, focusing on user identification, memory retrieval, gathering, and updating. Overall, mcp-knowledge-graph is a robust and flexible solution for persistent AI memory using knowledge graphs, enhancing AI's ability to remember and personalize user interactions across sessions.

https://github.com/shaneholloman/mcp-knowledge-graph

ai-integrationai-interactionai-memoryai-modelsai-platform-compatibilityapichat-personalizationclaudeclaude-aientitiesfunction-callinggptknowledge-graphllamalocal-developmentlocal-knowledge-graphmcpmemory-pathmemory-servermodel-context-protocolobservationspersistent-memoryrelationstypescriptuser-information-retention

Also in Knowledge & Memory

MemPalace/mempalace

MemPalace is an open-source, local-first AI memory system that stores and retrieves conversation history verbatim using semantic search, supporting pluggable backends like ChromaDB and integrating ...

siyuan-note/siyuan

SiYuan is a privacy-first, self-hosted personal knowledge management system featuring block-level referencing, Markdown WYSIWYG editing, and support for the Model Context Protocol (MCP).

topoteretes/cognee

Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.

vectorize-io/hindsight

Hindsight is an agent memory system designed to create smarter, learning AI agents by moving beyond simple conversation history recall to encompass a biomimetic storage architecture for long-term m...

screenpipe/screenpipe

Screenpipe is a local-first, AI-powered memory tool that records computer activity (screen, audio, accessibility tree) to provide a searchable, automated context for personal AI agents and users, i...

Olow304/memvid

Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.

EverMind-AI/EverOS

EverOS is an open-source Python framework for self-evolving, portable, long-term memory for AI agents, supporting multimodal ingestion and local-first persistence with Markdown as the source of truth.

MemTensor/MemOS

MemOS is a Memory Operating System for LLMs and AI agents that unifies long-term memory management, offering a single API for structured, multi-modal memory with enterprise-grade optimizations, sig...