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
Rudra-ravi/wikipedia-mcp
Wikipedia MCP Server is a Python MCP server that retrieves Wikipedia content on demand so a language model can ground its answers in article text instead of memory. It exposes search over article titles with diagnostics, retrieval of full article content, concise summaries, extraction of individual sections, discovery of the links inside an article, and listing of topics related to a given article. Language handling is a particular focus: a --language or -l flag selects any Wikipedia edition, a --country flag accepts intuitive country names or codes such as US, China or TW and maps them to the right edition, and language variants are supported, including simplified and traditional Chinese as zh-hans, zh-tw and similar, and Serbian Latin and Cyrillic scripts. A --list-countries flag prints everything supported. Responses can be cached with --enable-cache, and a Wikipedia personal access token can be supplied through --access-token or the WIKIPEDIA_ACCESS_TOKEN environment variable to avoid rate limiting. Transports cover stdio for desktop clients plus http and streamable-http, with the legacy sse transport kept for compatibility; host, port and path are configurable, which the README pairs with Docker and Kubernetes examples that bind to 0.0.0.0. For exposed network transports the server can require authentication, either a static bearer token via --auth-mode static or JWT validation against a JWKS URI with --auth-mode jwt. Installation is available through pipx, which the project recommends for Claude Desktop because it puts the command on PATH, through PyPI, from source, or automatically via Smithery. The tool schemas are documented as compatible with Google ADK agents and other frameworks that enforce strict function calling schemas.
https://github.com/Rudra-ravi/wikipedia-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...