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
jacksteamdev/obsidian-mcp-tools
MCP Tools for Obsidian is a plugin and local server designed to enable secure AI integrations with Obsidian vaults through the Model Context Protocol (MCP). This open protocol standardizes how AI applications can interact with external data sources and tools while ensuring security and user control. The project consists of two main components: an Obsidian plugin that adds MCP capabilities to the user's vault, and a local MCP server that manages communication between the vault and AI applications such as Claude Desktop. The MCP server acts as a secure intermediary, allowing AI assistants to read notes, execute templates, and perform semantic searches within the vault, but only with explicit user permission and through a secure API. This design prevents direct access to vault files by AI applications, enhancing privacy and security. The plugin supports features like vault access, semantic search based on meaning and context, and template integration with dynamic parameters, all requiring an MCP-compatible client. Installation involves adding the plugin from Obsidian's Community Plugins, enabling it, and then installing the MCP server via the plugin settings. The server binary is downloaded and configured automatically, including setting up Claude Desktop and necessary permissions. The project emphasizes security with signed binaries, reproducible builds, encrypted communication, and secure API key storage. Users can verify the integrity of the server binaries using GitHub CLI and SLSA provenance attestations. The project is structured as a monorepo with separate packages for the server, plugin, and shared utilities, using Bun and TypeScript for development. It also integrates with other Obsidian plugins like Local REST API, Templater, and Smart Connections for enhanced functionality. The repository includes detailed documentation on installation, configuration, troubleshooting, security, development, and contribution guidelines. Overall, MCP Tools for Obsidian provides a robust and secure framework for integrating AI capabilities into Obsidian vaults, leveraging the Model Context Protocol to maintain user control and privacy while enabling powerful AI-driven features.
https://github.com/jacksteamdev/obsidian-mcp-tools
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...