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
Lyellr88/MARM-Systems
MARM Systems is a universal Model Context Protocol (MCP) server designed to transform AI into a persistent, memory-powered collaborator. It supports both HTTP and STDIO interfaces, enabling cross-platform AI memory, multi-agent coordination, and context sharing. Built on the MARM protocol, it provides structured reasoning that evolves with ongoing work, ensuring AI agents retain long-term recall, session continuity, and reliable conversation history. This system addresses the common problem of AI models forgetting context over time, repeating ideas, or drifting from requirements by offering a unified, persistent memory layer beneath any AI client. MARM MCP blends semantic search, structured session logs, reusable notebooks, and smart summaries, allowing AI agents to remember, reference, and build on prior work consistently across sessions and tools. The project offers advanced features such as semantic search by meaning using AI embeddings, auto-classification of content into categories like code, project, or book, and persistent cross-session memory that survives agent conversations. It supports multiple AI clients including Claude, Qwen, and Gemini, enabling them to share knowledge and learn from each other through a unified memory layer. The architecture includes 18 complete MCP tools, database optimization with SQLite using WAL mode and connection pooling, rate limiting for stability, and compliance with MCP standards for predictable performance. The server is containerized with Docker for easy deployment and includes health and readiness checks. MARM MCP is actively developed with plans for improvements in advanced memory indexing, cross-session recall, and performance optimizations based on real production data. It is recognized in the AI community and appears in Google's AI overview for AI memory protocol queries. Users report high value in industrial automation, DevOps, and complex infrastructure projects, praising its session management, persistent logging, and smart recall capabilities. Overall, MARM Systems provides a robust, scalable solution for persistent AI memory and multi-agent collaboration, making it an essential tool for enhancing AI workflows and maintaining context over time.
https://github.com/Lyellr88/MARM-Systems
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...