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
entanglr/zettelkasten-mcp
Zettelkasten MCP Server is a Model Context Protocol server that implements the Zettelkasten knowledge management method, so that Claude and other MCP-compatible clients can create, link, explore and synthesize atomic notes. It follows the three principles of the method: atomicity, where each note holds exactly one idea and carries a unique timestamp-based identifier; connectivity, where notes are linked bidirectionally into a graph; and emergence, where patterns appear as the network grows. Notes come in five kinds - fleeting, literature, permanent, structure and hub - and links carry semantic types with automatic inverses, including reference, extends and extended_by, refines and refined_by, contradicts and contradicted_by, questions and questioned_by, supports and supported_by, and a generic related relation. Beyond linking, the server supports tagging and search by content, tag or link, which allows both vertical exploration inside a topic and horizontal exploration across domains. Storage is deliberately split in two layers. Markdown files with YAML frontmatter are the source of truth: they stay readable, can be edited in any text editor, put under version control and backed up as ordinary files. A SQLite database sits alongside them as an index that speeds up querying and graph traversal; it can be deleted at any time and rebuilt from the Markdown files, and the zk_rebuild_index tool refreshes it after notes are edited outside the server. The server runs synchronously and is started with python -m zettelkasten_mcp.main, optionally with explicit notes directory and database path arguments, or wired into Claude Desktop through an mcpServers entry with the ZETTELKASTEN_NOTES_DIR and ZETTELKASTEN_DATABASE_PATH environment variables. The repository also ships a docs directory with recommended system prompts, chat prompts for knowledge creation, exploration and synthesis, and background material on the method and its link types.
https://github.com/entanglr/zettelkasten-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...