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
dmayboroda/minima
Minima is an open-source on-premises Retrieval-Augmented Generation (RAG) system designed to enable secure and private querying of local documents through conversational AI. It supports integration with ChatGPT and the Model Context Protocol (MCP), allowing users to leverage powerful language models while maintaining data privacy by keeping all document indexing and processing local. The system operates through configurable containers and supports three main modes: fully isolated on-premises operation with all neural networks running locally, integration with ChatGPT for querying local documents using custom GPTs, and integration with Anthropic Claude for similar querying capabilities. Minima supports a variety of document types including PDFs, Excel files, Word documents, text files, markdown, and CSVs, which it indexes recursively from a specified root folder. It uses Sentence Transformer models for embedding and supports reranker models from BAAI to improve query relevance. The system can be deployed using Docker containers with environment variables to configure paths, models, and authentication details. For MCP integration, Minima can be used with the Anthropic Desktop app and also supports usage with GitHub Copilot through a specific configuration. The project provides detailed instructions for setup, including environment variable configuration, container deployment commands, and integration steps for different modes. It also offers a local Electron app for fully local usage. Minima emphasizes data security by enabling on-premises operation without reliance on external cloud services, making it suitable for users who require private and secure access to their local document repositories via conversational AI. The project is licensed under the Mozilla Public License v2.0 and includes badges for security assessment, highlighting its focus on secure deployment.
https://github.com/dmayboroda/minima
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...