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
8enSmith/mcp-open-library
MCP Open Library is a Model Context Protocol server that puts the public Open Library catalogue behind a set of MCP tools, so an assistant can look up bibliographic data without scraping the site. It exposes seven read-only tools: search_books searches across query, title, author, subject, place, person, publisher and ISBN fields with sorting; get_book_by_title looks a book up by its title; get_authors_by_name searches authors by name; get_author_info returns detailed data for an Open Library author key; get_author_photo returns the photo URL for an author OLID; get_book_cover returns a cover image URL from an ISBN, OCLC, LCCN, OLID or internal id; and get_book_by_id retrieves book details from those same identifiers. Rather than passing back the raw Open Library payloads, the server returns JSON projections of them. Search results are paged: every search tool returns at most limit results, defaulting to 10 and capped at 50, together with num_found for the total number of matches, and offset walks through the results up to 1000. The two cover tools check that an image actually exists and report when it does not instead of returning a URL that resolves to a blank placeholder. Each tool carries the readOnlyHint and openWorldHint annotations, which a client may use to skip the confirmation prompt it shows for tools that can change state, although the specification leaves that policy to the client. Errors such as an unreachable API or a rejected argument come back as tool results flagged isError so the assistant can correct its next call. It runs over stdio through npx with no build step, is published to the official MCP Registry as io.github.8enSmith/mcp-open-library, and can also be installed through Smithery or built from source with Node and npm.
https://github.com/8enSmith/mcp-open-library
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...