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
MemTensor/MemOS
MemOS (Memory Operating System) is a comprehensive solution designed to enhance the memory capabilities of Large Language Models (LLMs) and AI agents. It provides a unified API for managing persistent long-term memory, allowing agents to store, retrieve, and manage diverse information types, including text, images, tool traces, and personas. Instead of treating memory as a black-box embedding store, MemOS structures it as an inspectable and editable graph. Key features include multi-modal memory support, enabling the retrieval and reasoning of various data types within a single system, and multi-cube knowledge base management for isolating, sharing, and composing knowledge across different users, projects, and agents. The system utilizes an asynchronous ingestion mechanism via MemScheduler to ensure production stability and low latency under high concurrency. Furthermore, MemOS supports natural-language feedback and correction, allowing memories to be refined, supplemented, or replaced over time. MemOS offers substantial benefits, such as up to 35.24% token savings and a 43.70% increase in accuracy compared to OpenAI's memory systems. It provides both cloud service and self-hosted options, including local plugins for agents like Hermes and OpenClaw. Recent updates, such as MemOS 2.0 Stardust, have introduced advanced features like comprehensive KB support, memory feedback and deletion APIs, multi-modal memory for conversations and documents, and improved infrastructure with Redis Streams scheduling.
https://github.com/MemTensor/MemOS
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.
casibase/casibase
Casibase is an open-source enterprise AI knowledge base platform supporting the Model Context Protocol and multiple AI models with features like admin UI, user management, and Single Sign-On.