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
assafelovic/gptr-mcp
GPT Researcher MCP Server is a specialized server implementing the Model Context Protocol (MCP) designed to enhance the capabilities of large language model (LLM) applications by enabling them to perform deep, validated, and comprehensive web research. Unlike standard web search tools that return raw and often irrelevant results, this server autonomously explores, filters, and validates numerous sources to provide only relevant, trusted, and up-to-date information. This results in higher quality information, optimized use of context windows, comprehensive research results, and improved reasoning capabilities for LLMs. The server supports multiple transport protocols including STDIO for local development, SSE for Docker and web clients, and streamable HTTP for advanced web deployments, automatically detecting the best transport mode based on the environment. It integrates seamlessly with applications like Claude Desktop and can be deployed using Docker for production environments. The server requires Python 3.11 or higher and API keys for OpenAI and Tavily services, but it also supports other web search engines compatible with GPTR retrievers. Key features include primary tools such as deep_research for thorough web research, quick_search for fast but less detailed searches, write_report for generating reports based on research, and utilities to retrieve research sources and context. The server is designed to improve the quality and reliability of information retrieved by LLMs, making it highly valuable for applications requiring accurate and comprehensive web-based research. Installation involves cloning the GPT Researcher repository, installing dependencies, setting environment variables for API keys, and running the server either directly via Python, through MCP CLI, or using Docker. The server also supports integration with automation tools like n8n, facilitating its use in complex workflows. Overall, GPT Researcher MCP Server is a powerful MCP-based tool that significantly enhances LLM research capabilities by providing deep, validated, and contextually optimized web research results.
https://github.com/assafelovic/gptr-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...