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
StevenStavrakis/obsidian-mcp
obsidian-mcp is a Model Context Protocol (MCP) server designed to enable AI assistants to interact seamlessly with Obsidian vaults. This project provides a comprehensive set of tools that allow AI to read, create, edit, and manage notes and tags within an Obsidian vault, facilitating enhanced note-taking and organization workflows. The server supports operations such as reading and searching notes, creating new notes and directories, editing and moving existing notes, deleting notes, and managing tags by adding, removing, or renaming them. It also supports searching the entire vault content and listing available vaults, which is particularly useful for users managing multiple vaults. The project requires Node.js 20 or higher and an existing Obsidian vault to function. Installation can be done manually by configuring the Claude Desktop client to connect to the obsidian-mcp server or via the Smithery CLI tool, although manual installation is recommended for reliability. The server runs with read and write access to the vault, so users are strongly advised to back up their vaults before use to prevent data loss. Developers can clone the repository, install dependencies, and build the project to customize or extend its functionality. The project includes detailed documentation on creating new tools and examples of using the available tools, making it accessible for further development and integration. Security considerations are emphasized, advising users to restrict server access to intended vault directories and to review tool actions carefully. Troubleshooting guidance is provided for common issues such as configuration errors, permission problems, and tool execution failures. Overall, obsidian-mcp bridges AI capabilities with Obsidian's powerful note-taking environment, enabling automated and intelligent management of notes and tags through the MCP framework.
https://github.com/StevenStavrakis/obsidian-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...