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
cyanheads/obsidian-mcp-server
Obsidian MCP Server is a secure and efficient Model Context Protocol (MCP) server designed to enable large language models (LLMs) and AI agents to interact seamlessly with Obsidian vaults. This project acts as a bridge between applications that understand MCP and the Obsidian knowledge base, allowing advanced AI assistants, IDE extensions, or custom scripts to read, write, search, and manage notes and files within an Obsidian vault programmatically. The server leverages the Obsidian Local REST API plugin to communicate with the vault, providing a standardized and secure interface for vault operations. The server is built on a modular architecture using the cyanheads/mcp-ts-template, which offers robust error handling, logging, configuration management, input validation, and type safety. It supports a variety of tools that expose key vault functionalities as MCP tools, including reading notes in markdown or JSON formats, updating notes with append, prepend, or overwrite operations, performing search and replace within notes, global vault search with filters, listing notes and directories, managing YAML frontmatter and tags, and deleting notes safely with case-insensitive path fallback. Additional features include a vault cache service that caches vault content in memory to improve performance and provide fallback capabilities, especially for global search operations. The server also supports flexible targeting of files by path, active note, or periodic notes, and includes safety features to prevent accidental data loss. It offers structured logging with sensitive data redaction, centralized error processing, environment variable configuration with validation, and HTTP transport options with session management, CORS, and authentication strategies like JWT and OAuth 2.1. Overall, Obsidian MCP Server empowers AI agents and development tools to integrate deeply with Obsidian vaults, enabling automation, enhanced AI workflows, and the creation of custom tools that leverage the rich knowledge stored in Obsidian. It is production-ready, open-source under the Apache 2.0 license, and actively maintained with a focus on security and extensibility.
https://github.com/cyanheads/obsidian-mcp-server
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...