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
hbg/mcp-paperswithcode
mcp-paperswithcode is a Python MCP server that fronts the Papers with Code API so an AI assistant can find, read and cross-reference machine learning research together with the code that accompanies it. Paper tools cover searching by abstract text, title or arXiv identifier, fetching a paper by its identifier, and reading a paper directly: given a PDF or HTML URL the server extracts the readable text so the model can work with the content rather than just the metadata. Around each paper the server exposes the relationships that make Papers with Code useful, listing the benchmark results reported for it, the tasks it addresses, the methods it discusses, the code repositories linked to it and the datasets it uses. A second group of tools works at the level of research areas, searching areas by name, returning metadata for one and listing the tasks that belong to it, which lets an assistant move from a broad topic down to concrete problems. Author tools search by full name, return metadata for an author identifier, list every paper attributed to an author identifier, and provide a convenience path that takes a name, resolves the first matching author and returns their papers. Conference tools list conferences with an optional name filter, fetch a single conference, list its proceedings, fetch one proceeding and list all papers published within it. Installation is documented through Smithery, which can wire the server into Claude Desktop automatically. The intended use is literature work: pulling together the papers on a topic, checking which implementations exist for a result, tracing an author or a conference track, and then reading the actual text of a selected paper without the user having to leave the assistant to open a browser.
https://github.com/hbg/mcp-paperswithcode
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...