#rag Repositories
550 repositories total
RAGLight is a modular framework for Retrieval-Augmented Generation (RAG). It makes it easy to plug in different LLMs, embeddings, and vector stores, and now includes seamless MCP integration to connect external tools and data sources.
On-device AI for Flutter โ Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking, and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
Open-source AI Agent Customer Service Platform. Build AI agent teams with LLM orchestration, RAG knowledge base, multi-channel support, and human collaboration.
Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. A curated list of tools, benchmarks/datasets, demos, leaderboards, and large models, primarily focused on the evaluation of foundation large models, aiming to explore the technological boundaries of generative AI.
Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sourcesโbuilt with Supabase and N8N on a React frontend.
Stanford CS329Z Engineering AI Agents Chinese tutorial: an AI agent course for Python developers, with 19 lectures and 4 hands-on projects, covering LLMs, RAG, tool calling, memory, multi-agent systems, evaluation, and safety. Complete Markdown, online and offline HTML. Chinese course notes.
The open source agentic content system to make your contents alive. Self-hosted on any platform. โ
Turn stateless LLMs into a stateful, compounding AI agent. Local-first persistent memory, quantitative decision screens, and governance harness across Claude Code, Antigravity, Cursor, and VS Code. Own the state. Rent the intelligence.
This tutorial provides a comprehensive guide on how to quickly set up your own AI application environment. Starting from the installation and configuration of Docker Desktop to deploying Dify locally and customizing AI assistant features, it enables you to easily create various unique AI applications such as 'Case Guessing,' 'Sweet Talker,' 'Freshman Orientation Guide,' 'Xiaohongshu Reading Cards,' and 'Interview Bible.' It also teaches you how to master Dify-based LLM application development from basic agents to advanced tasks including workflows, knowledge bases, DeepResearch, databases, MCP, and complex task orchestration.
An open-source AI content search engine designed specifically for content creators. Supports extraction of text, images, and short videos. Allows full local deployment (web app, RAG server, LLM server). Supports multi-modal RAG content Q&A.
AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin.
CookHero is an intelligent diet and cooking management platform based on LLM + RAG + Agent + multimodal technologies. It supports smart recipe search, personalized meal planning, AI-powered diet tracking, nutritional analysis, web search enhancement, and an extensible ReAct Agent / Subagent tool system, helping kitchen novices easily become 'cooking heroes'.
This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.
BullFlow โ Open-source, enterprise-grade RAG solution: from enterprise knowledge bases and automated marketing content production to omnichannel distribution. The entire knowledge-base workflow runs on local, open-source models, with no paid models required. AI agents create text-and-image posts, images, and videos, then publish them to 17 platformsโincluding Douyin, Xiaohongshu, WeChat Official Accounts, LinkedIn, and YouTubeโwith one click. Commercial-grade, with multi-tenancy, billing, and administration built in. MIT.
๐ฅ๐ฅ๐ฅ Turn AI-written code into real apps. Nubase is an open-source, AI-native backend platform for AI Coding, agentic applications, and modern product teams: Memory, Database, Storage, and Auth in one self-hostable service.
An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
Chinese-first enterprise RAG knowledge base: controllable parsing, governance, chunking, hybrid retrieval, reranking, citations, knowledge graphs, evaluation, and Dify integration.
XRAG: eXamining the Core - Benchmarking Foundational Component Modules in Advanced Retrieval-Augmented Generation
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps International Challenge 2024 Winning Team Solution
GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile information retrieval API. It combines local, global, and web searches for advanced Q&A systems and search engines. This tool simplifies graph-based retrieval integration in open web environments.
YT Navigator: AI-powered YouTube content explorer that lets you search and chat with channel videos using AI agents. Extract insights from hours of content in seconds with semantic search and precise timestamps.
AI-powered IDE for novel writing โ local LLM + RAG, privacy-first, BYOK. For web fiction authors and creative writers.
Enables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.
Fullstack "Chat with your PDFs" RAG (Retrieval Augmented Generation) app built fully on Cloudflare
Open-source, self-hosted AI agent platform for your company's AI teammates. Build, run and govern agents on your own servers and models: shared chat, RAG, skills, a real browser, 4,700+ MCP servers, budgets, approvals and an audit trail. An alternative to ChatGPT Enterprise and Grok Bot. Apache-2.0, built on Pydantic AI.
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
FoJin-powered Buddhist AI persona framework โ source-grounded, boundary-aware, fidelity-tested, runtime-ready.
appbuilder-sdk, Qianfan AppBuilder-SDK helps developers flexibly and quickly build AI-native applications
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
โก DocsAgent โ chat with your Zotero library from your phone. Native iPhone app + free Mac companion. MCP server for Claude, Cursor & Cline: instant, private search across Zotero, Obsidian & Apple Notes, fully local (~15 ms).
Train and Infer Powerful Sentence Embeddings with AnglE | ๐ฅ SOTA on STS and MTEB Leaderboard
Caura (formerly MemClaw) โ governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.
[ICLR 2026] LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
Repository for the "Building LLMs for Production" book by Towards AI.
A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.