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
Olow304/memvid
Memvid is an innovative video-based AI memory library designed to store millions of text chunks within MP4 video files, enabling lightning-fast semantic search without the need for traditional databases. It compresses entire knowledge bases into compact video files by encoding text as QR codes embedded in video frames, leveraging modern video codecs to achieve 50 to 100 times smaller storage compared to conventional vector databases. This approach allows for sub-100 millisecond retrieval times by directly seeking video frames, decoding QR codes, and returning text results with no server round-trips, making it highly efficient and portable. The project is currently in its experimental v1 phase, with a promising v2 version planned that introduces a Living-Memory Engine to maintain and update knowledge across sessions, Capsule Contexts for shareable memory capsules with rules and expiry, Time-Travel Debugging to review or branch chat histories, Smart Recall for ultra-fast local caching, Codec Intelligence for automatic codec tuning, and user-friendly CLI and dashboard tools for management and cloud publishing. Memvid's design emphasizes zero infrastructure requirements, running purely on Python and MP4 files without the need for database clusters or complex operations. It supports offline-first usage, making it suitable for environments without internet access. The library also offers advanced features such as scale optimization for huge datasets, custom embedding models, parallel processing for large-scale chunk addition, and compatibility with various codecs including AV1 and H.265. Real-world applications include documentation assistants, PDF library semantic search, and interactive web UIs for knowledge querying. The project provides a simple API for encoding text chunks into video memory and chatting with the stored knowledge, along with CLI tools for document processing and codec management. Performance benchmarks highlight its ability to index 10,000 chunks per second, search one million chunks in under 100 milliseconds, and compress 100MB of text into just 1-2MB of video storage. Overall, Memvid represents a novel approach to AI memory storage and retrieval, combining video compression technology with semantic search to create a portable, efficient, and scalable memory solution for AI applications.
https://github.com/Olow304/memvid
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...
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...
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.