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
zhsama/duckduckgo-mcp-server
duckduckgo-search MCP Server exposes web search through DuckDuckGo as a single well-specified tool. duckduckgo_search takes a required query of up to four hundred characters, an optional count between one and twenty defaulting to ten, and an optional safeSearch level of strict, moderate or off, defaulting to moderate. Results come back as formatted markdown rather than raw JSON, which is directly readable by a model without a parsing step. Rate limits are documented plainly — at most one request per second and fifteen thousand per month — and the server implements limiting and error handling rather than letting a talkative agent hit the ceiling and receive confusing failures. The practical appeal is that DuckDuckGo requires no API key or account, so this is one of the search servers that works as soon as it is added to a client configuration. It is TypeScript, built with pnpm 8 or newer on Node.js 18 or newer, and the README presents it partly as a demonstration of core MCP concepts, making it readable as an example as well as usable. Documentation is provided in English and Chinese. The audience is anyone who wants basic web search in an assistant without signing up for a commercial search API, accepting the monthly cap.
https://github.com/zhsama/duckduckgo-mcp-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...