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
ggozad/haiku.rag
Haiku SQLite RAG is a Retrieval-Augmented Generation (RAG) library designed to operate solely on SQLite without requiring external vector databases. It leverages sqlite-vec for embedding storage and combines semantic vector search with full-text search using Reciprocal Rank Fusion to enhance search accuracy and relevance. The library supports multiple embedding providers, including open-source options like Ollama and commercial providers such as OpenAI and VoyageAI, as well as multiple question-answering providers like Ollama, OpenAI, and Anthropic. Haiku.rag offers a hybrid search capability that integrates vector and full-text search methods, enabling efficient and precise retrieval of information from documents. The project supports over 40 file formats, including PDF, DOCX, HTML, Markdown, audio files, and URLs, making it versatile for various document types. It features file monitoring for automatic indexing when run as a server, facilitating real-time updates to the document database. Haiku.rag also includes built-in question-answering agents that allow users to query their documents directly. The system can be exposed as tools for AI assistants through an MCP (Model Context Protocol) server, enabling seamless integration with AI platforms like Claude Desktop. Users can interact with haiku.rag via a command-line interface or a Python API, providing flexibility in usage. The Python API supports asynchronous operations for adding documents, searching, and asking questions. The project is well-documented with comprehensive guides on installation, configuration, CLI commands, and API usage. Overall, haiku.rag is a powerful, self-contained RAG solution that simplifies document management, search, and question answering by leveraging SQLite and advanced embedding techniques without external dependencies.
https://github.com/ggozad/haiku.rag
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...