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
reading-plus-ai/mcp-server-deep-research
MCP Server for Deep Research is a specialized tool designed to facilitate comprehensive and structured research on complex topics by transforming research questions into detailed, well-cited reports. The tool operates through a multi-step workflow that begins with question elaboration, where the initial research question is expanded and clarified, key terms and concepts are identified, and the scope and parameters of the research are defined. Following this, the tool generates focused subquestions that cover different aspects of the main topic, ensuring a thorough and systematic approach to research. The server integrates web search capabilities, specifically leveraging Claude's built-in web search, to perform targeted searches for each subquestion. This allows the tool to identify relevant and authoritative sources, gathering diverse perspectives on the topic. The content analysis phase evaluates the quality and relevance of the gathered information, synthesizes findings from multiple sources, and ensures proper citation of all references. Finally, the tool generates comprehensive research reports that are well-structured and balanced, presenting evidence-based conclusions with appropriate formatting for clarity and readability. The project includes a tailored prompt named "deep-research" designed for comprehensive research tasks, supporting the structured approach of the server. The MCP Server for Deep Research is intended to be used with Claude Desktop, with setup instructions provided for macOS. It supports development and customization through configuration files and offers commands for building, publishing, and syncing dependencies. The project is open to contributions and is licensed under the MIT License. Overall, this project is a powerful assistant for deep research, automating the process of question refinement, information gathering, analysis, and report generation, making it highly relevant to the Model Context Protocol (MCP) ecosystem.
https://github.com/reading-plus-ai/mcp-server-deep-research
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...