Discover The Top AI hackers & Projects

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

Sim Studio is an open-source AI agent workflow builder. Sim Studio's interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools.

AI Agent Builder in Python

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

Laminar - open-source all-in-one platform for engineering AI products. Create data flywheel for your AI app. Traces, Evals, Datasets, Labels. YC S24.

Chat with any codebase in under two minutes | Fully local or via third-party APIs

Dynamiq is an orchestration framework for agentic AI and LLM applications

一个轻量级、支持全链路且易于二次开发的大模型应用项目(Large Model Data Assistant) 支持DeepSeek/Qwen2.5等大模型 基于 Dify 、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 ECharts 📈 实现基于大模型的数据图形化问答，具备处理 CSV 文件 📂 表格问答的能力。同时，能方便对接第三方开源 RAG 系统 检索系统 🌐等，以支持广泛的通用知识问答。

TypeScript AI Framework specialized AI Function Calling enhanced by compiler skills.

Parsing-free RAG supported by VLMs

Minimalist LLM Framework in 100 Lines. Enable LLMs to Program Themselves.

Fullstack "Chat with your PDFs" RAG (Retrieval Augmented Generation) app built fully on Cloudflare

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.

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

Universal AI agent building apps using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more.

Turn any app into agent knowledge

Flock is a workflow-based low-code platform for rapidly building chatbots, RAG, and coordinating multi-agent teams.（Flock 是一个基于workflow工作流的低代码平台，用于快速构建聊天机器人、RAG、Agent和Muti-Agent应用。）

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

Local LLM Powered Recursive Search & Smart Knowledge Explorer

AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Graph Foundation Model for Retrieval Augmented Generation

AI agent to search Google Flights data

Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama

Too many docs? Quickly search over any PDF or Markdown documents

Jupyter Notebooks for Mastering LLM with Advanced RAG Course

This project is a dynamic AI Agent chatbot that can be trained from various sources, such as PDFs, documents, websites, and YouTube videos.

Building blocks for rapid development of GenAI applications

graph + ai in your products; reduce costs and get correct answers from your data

Coffee Chat Voice Assistant is a voice-driven ordering system powered by Azure OpenAI GPT-4o Realtime API, simulating the experience of ordering coffee with a café barista. It supports natural conversations, live order updates, and real-time transcription, showcasing the power of AI for seamless customer interactions.

Blueprint for Ingesting massive volumes of live or archived videos and extract insights for summarization and interactive Q&A

这是一个汇集了众多优秀大型语言模型应用的合集，这些应用采用了检索增强生成（RAG）技术，并使用了 OpenAI、Anthropic、Gemini 以及开源模型。Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.

从零开始基于 LangGraph 和 Streamlit 实现基于本地模型的 RAG、Agent 应用

minRAG is a RAG system that starts from scratch, pursuing the ultimate simplicity and power. It consists of no more than 10,000 lines of code, requires no installation, and can be launched with a double-click

SpeakingAI is a demo of privately deployable 'GPT-4o like AI + RAG', a fully functional web AI server with audio query/answer in streaming, using LLM and RAG for backend knowledge.

Lecca.io | AI Agents & Automations

An open-source template for building a RAG chatbot for your company 🤖

REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model

DocGPT (Doctor GPT) is an advanced medical diagnosis system that combines Vision Transformer (ViT) based deep learning models with LangChain agents to provide comprehensive medical image analysis and detailed diagnostic reports. The system leverages the power of PyTorch for deep learning and Groq's LLM for generating human-like medical insights.

Llama_RAG_System is a local Retrieval-Augmented Generation (RAG) system that leverages the LLaMA model to provide intelligent answers to user queries by processing uploaded PDFs and fetching relevant web information while ensuring privacy.

Next.js LangChain Gemini RAG Chatbot: An advanced Retrieval-Augmented Generation (RAG) chatbot that enables users to upload multiple PDFs and receive precise answers to their questions based on the content. Powered by LangChain and Gemini, this chatbot is built with Next.js and offers efficient PDF-based query handling for enhanced user engagement.

This application allows users to upload PDF files, process them, and ask questions about the content using a locally hosted language model. The system uses Retrieval-Augmented Generation (RAG) to provide accurate answers based on the uploaded PDFs.

A web interface for GraphRAG. 🚀