Knowledge Retrieval and the RAG Framework

M3-Agent is a multimodal intelligent body framework developed by the ByteDance SEED team. Its core feature is a long-term memory capability, capable of building and continuously updating its memory by processing real-time video (watching) and audio (listening) inputs, just like humans. This memory system does not just record...

LightRAG is an open-source Python framework developed by a team from the School of Data Science at the University of Hong Kong to simplify and accelerate the process of building Retrieval Augmented Generation (RAG) applications. It does this by combining knowledge graphs with traditional vector retrieval techniques to provide more accurate and contextualized Large Language Models (LLMs)...

RAG-Anything is a fully integrated multimodal document processing RAG system built on LightRAG. Most of the traditional question and answer systems (RAG) can only process plain text content, but the documents we come into contact with on a daily basis, such as PDFs, Word documents or presentations, often contain text, images, tables...

Medical-RAG 是一个专为中文医疗领域设计的问答智能体项目. 它基于检索增强生成（RAG）技术，通过结合外部知识库来提升大型语言模型（LLM）在医疗建议上的准确性和安全性. 该项目的核心是利用高性能向量数据库 Mi...

DiffMem is a lightweight memory backend designed for AI intelligences and conversational systems. It innovatively uses Git as the core of the memory store, saving AI memories as human-readable Markdown files. Git's commit history is used to track the evolution of memories over time, while the system uses in-memory...

AUM is an AI intelligence engine designed for enterprises, officially called the "Enterprise Brain". It runs entirely locally on the user's own server or computer, with no need for an internet connection, to ensure absolute privacy and security of business data. Users can let AUM process and analyze the company's data through a dialog...

ComoRAG is a Retrieval Augmented Generation (RAG) system designed to address long documents and multi-document narrative comprehension. Traditional RAG methods often encounter difficulties when dealing with long stories or novels due to the complexity of the plot and the evolving character relationships. This is due to the fact that most of them use stateless, single-check ...

WeKnora (Vinara) is a Tencent open source enterprise-class document understanding and retrieval Q&A framework. It is mainly used to deal with complex structure , content diverse document scenarios . WeKnora is the core of the Retrieval Augmented Generation (RAG) technology , the technology will be retrieved from the document context snippets with a large language model conjunction ...

memU is an open source memory framework designed for AI companions. While current big language models suffer from short memories and fail to establish long-term connections with users, memU acts like an intelligent "memory folder" for AI, allowing AI to remember users' identities, preferences, and past conversations,...

GBC MedAI is an open source intelligent medical assistant system. It uses FastAPI as the backend framework and Vue 3 as the frontend technology stack. The core capability of this system is to be able to integrate multiple AI big language models at the same time, such as DeepSeek, locally deployed Ollama, and other compatible ope...

DeepSieve is an open source Retrieval Augmented Generation (RAG) framework hosted on GitHub that focuses on processing complex queries and multi-source data. It provides efficient information filtering capabilities by decomposing queries, routing sub-questions, reflecting on failed retrievals and fusing answers.DeepSieve is developed by MinghoKwok ....

RAGLight is a lightweight, modular Python library designed to implement Retrieval Augmented Generation (RAG). It improves the contextual understanding of Large Language Models (LLMs) by combining document retrieval and natural language generation.RAGLight supports multiple language models, embedded models, and vector stores,...

ThinkDoc is an intelligent knowledge base platform from Bluedigit that focuses on transforming unstructured data into AI-ready knowledge assets. It helps organizations and individuals efficiently manage knowledge and accelerate AI project implementation through deep document parsing, converged search and intelligent Q&A. The platform supports multiple formats of documents,...

GitBook is an online platform that helps teams create, edit and share technical documents. It supports Markdown formatting and provides an intuitive editing interface for both technical teams and non-technical users.GitBook integrates with Git workflows and can be synchronized with GitHub or GitLab, making it easy to code...

llmware is an open source framework focused on helping developers rapidly build enterprise-class Retrieval Augmentation Generation (RAG) applications. It provides over 50 small, specialized Large Language Models (LLMs) that support running in local or private cloud environments, and is particularly suited to data security-sensitive industries such as financial, legal, and compliance...

Cursor Memories is an open source project, hosted on GitHub, that aims to provide persistent context memory capabilities for the AI code editor Cursor. It helps AI assistants retain project information across sessions through structured document files, solving the problem of AI forgetting the context after each session...

THEO is a tool designed for startups and SMEs, with the core function of organizing fragmented business information into a structured knowledge base that can be understood by AI. It automatically generates "business DNA" by analyzing enterprise websites, documents and other information, allowing AI tools such as ChatGPT and Claude to more accurately understand the needs of the enterprise....

Brainfork is a personal AI knowledge platform that allows users to build their own MCP (Memory, Context, Processing) server to centrally manage and utilize their personal knowledge. Users can import scattered notes and documents, connect to Claude, ChatGPT and other ...

PandaWiki is an open source knowledge base building system developed by Changting Technology. It utilizes AI big model technology to help users quickly create intelligent product documentation, technical documentation, FAQ and blog systems. The system provides content creation, Q&A and search functions through AI to simplify document management and user interaction....