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
54yyyu/zotero-mcp
Zotero MCP is a powerful integration tool that connects your Zotero research library with AI assistants like Claude and others through the Model Context Protocol (MCP). This project enables users to interact with their research materials in a highly efficient and intelligent manner by leveraging AI capabilities. Users can discuss academic papers, obtain summaries, analyze citations, and extract annotations from PDFs seamlessly. The tool supports complex search functionalities allowing users to find papers, articles, and books by various criteria such as title, author, content, tags, and collections. It provides access to detailed metadata, full-text content when available, attachments, notes, and child items within the Zotero library. Zotero MCP offers flexible access methods including a local mode that works offline without requiring an API key, and a web API mode for cloud-based library access, making it suitable for both individual researchers and collaborative environments. The project supports advanced PDF annotation extraction, including direct processing of PDF files to extract annotations and image annotations, enhancing the research workflow by integrating with Zotero's native annotation system. It also recommends using the Better BibTeX plugin for enhanced annotation features. Installation is straightforward with options for automatic setup via Smithery, manual installation via uv or pip, and detailed configuration instructions for integration with Claude Desktop and Cherry Studio AI assistants. The project requires Python 3.10+ and Zotero 7+ for full functionality. Zotero MCP includes a variety of tools for searching, retrieving content, managing annotations and notes, and exporting citations in formats like BibTeX. Overall, Zotero MCP significantly enhances the usability of Zotero libraries by enabling AI-driven interactions and advanced data extraction, making it an invaluable tool for researchers who want to leverage AI to manage and analyze their academic resources more effectively.
https://github.com/54yyyu/zotero-mcp
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...