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
nloui/paperless-mcp
nloui/paperless-mcp is a JavaScript MCP server that exposes a Paperless-NGX document archive to MCP clients, so an assistant can search and organise scanned documents. Document tools cover list_documents with pagination, get_document by ID, search_documents for full-text queries, download_document with an option to fetch the original file rather than the archived version, and post_document, which uploads base64 file content together with a filename and optional title, creation date, correspondent, document type, storage path, tags, archive serial number and custom fields. bulk_edit_documents applies one operation to a list of document IDs and supports setting the correspondent, document type or storage path, adding, removing or batch-modifying tags, deleting, reprocessing, setting permissions, merging several documents into one, splitting a document by page ranges, rotating pages by 90, 180 or 270 degrees, and deleting specific pages. Metadata tools list and create tags with a colour, a match pattern and a matching algorithm chosen from any, all, exact, regular expression or fuzzy, and the same listing and creation pattern is provided for correspondents and for document types. Installation is through the npm package paperless-mcp, registered in a Claude Desktop or Cline settings file as an npx command whose arguments are the Paperless-NGX base URL and an API token generated from the user profile page in Paperless. The server runs over stdio by default and also offers a Streamable HTTP mode. It is built on the litemcp TypeScript framework with zod for schema validation and maps onto documented endpoints of the Paperless-NGX REST API. Error messages distinguish a wrong URL or token, an unreachable server, a failed operation and invalid parameters. It suits people who self-host Paperless-NGX and want to query and tidy their document archive conversationally.
https://github.com/nloui/paperless-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...