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
andrea9293/mcp-documentation-server
The MCP Documentation Server is a TypeScript-based server designed to implement the Model Context Protocol (MCP) for local-first document management and semantic search using embeddings. It serves as a bridge to close the AI knowledge gap by providing advanced document intelligence features. The server supports document management, AI-powered semantic search, file uploads, smart chunking, multilingual support, and requires zero setup, making it ideal for new frameworks, API documentation, and internal guides. A standout feature is its integration with Google Gemini AI, which enhances document analysis and contextual understanding. This allows users to ask complex questions and receive intelligent summaries, explanations, and insights from their documents. The server optimizes performance with on-disk persistence, an in-memory index, and caching mechanisms such as an LRU embedding cache to speed up repeated queries. It supports parallel chunking and batch processing for efficient ingestion of large documents and streaming file reading to handle large files without high memory usage. The MCP Documentation Server exposes a collection of MCP tools for document lifecycle management and search, including adding, listing, retrieving, and deleting documents, processing file uploads, and performing both traditional semantic and AI-powered searches. It supports context window retrieval to provide richer context for large language models (LLMs). The server stores all data locally without requiring an external database, ensuring data privacy and ease of use. Configuration is flexible through environment variables, allowing customization of embedding models, enabling or disabling indexing, cache size, parallel processing, streaming options, and more. The server is designed to be user-friendly with a simple setup process and clear usage examples for document operations and AI-powered search. Overall, the MCP Documentation Server is a powerful tool for managing and searching documents with advanced AI capabilities, optimized for performance and ease of integration within the MCP ecosystem.
https://github.com/andrea9293/mcp-documentation-server
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...