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 ...
Awesome MCP › Knowledge & Memory
awslabs/graphrag-toolkit
The graphrag-toolkit is a Python-based toolkit designed to facilitate the development of graph-enhanced Generative AI applications. It provides a suite of tools that leverage knowledge graphs to improve question answering and other AI-driven tasks. A key feature of the toolkit is BYOKG-RAG (Bring Your Own Knowledge Graph - Retrieval Augmented Generation), which enables users to integrate their own knowledge graphs and perform complex question answering over them. This approach combines the strengths of Large Language Models (LLMs) with structured knowledge graphs, enhancing the accuracy and depth of responses. Another significant component of the graphrag-toolkit is the MCP (Model Context Protocol) server. This server supports dynamic tool generation and tool description creation in multi-tenant environments, allowing different tenants to have customized tools tailored to their specific graph data and use cases. This makes the toolkit highly adaptable for various organizational needs. The toolkit also includes the lexical-graph framework, which automates the construction of hierarchical lexical graphs from unstructured data. This framework supports the composition of question-answering strategies that query these graphs, further enriching the AI's ability to understand and respond to user queries based on complex graph structures. Overall, the graphrag-toolkit is a comprehensive solution for developers looking to build advanced AI applications that integrate generative models with graph-based knowledge representations. It supports sophisticated question answering, dynamic tool generation, and multi-tenant deployment, making it suitable for enterprise-level applications that require customized and scalable AI solutions. The project is open source under the Apache-2.0 License and includes detailed installation instructions and security guidelines. It is actively maintained with recent releases enhancing its capabilities, such as the separation of the BYOKG-RAG package and the introduction of the MCP server.
https://github.com/awslabs/graphrag-toolkit
Also in Knowledge & Memory
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...