| 1 | sindresorhus/awesome </br>  | 😎 Awesome lists about all kinds of interesting topics |
| 2 | public-apis/public-apis </br>  | A collective list of free APIs |
| 3 | codecrafters-io/build-your-own-x </br>  | Master programming by recreating your favorite technologies from scratch. |
| 4 | kamranahmedse/developer-roadmap </br>  | Interactive roadmaps, guides and other educational content to help developers grow in their careers. |
| 5 | vinta/awesome-python </br>  | A curated list of awesome Python frameworks, libraries, software and resources |
| ⭐ 6 | practical-tutorials/project-based-learning </br>  | Curated list of project-based tutorials |
| 7 | tensorflow/tensorflow </br>  | An Open Source Machine Learning Framework for Everyone |
| 8 | Significant-Gravitas/AutoGPT </br>  | An experimental open-source attempt to make GPT-4 fully autonomous. |
| 9 | jackfrued/Python-100-Days </br>  | Python - 100天从新手到大师 |
| 10 | AUTOMATIC1111/stable-diffusion-webui </br>  | Stable Diffusion web UI |
| 11 | huggingface/transformers </br>  | 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. |
| 12 | f/awesome-chatgpt-prompts </br>  <a alt="Click Me" href="https://huggingface.co/datasets/fka/awesome-chatgpt-prompts" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | This repo includes ChatGPT prompt curation to use ChatGPT better. |
| 13 | justjavac/free-programming-books-zh_CN </br>  | 📚 免费的计算机编程类中文书籍，欢迎投稿 |
| 14 | goldbergyoni/nodebestpractices </br>  | ✅ The Node.js best practices list (July 2024) |
| 15 | krahets/hello-algo </br>  | 《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing |
| 16 | ollama/ollama </br>  | Get up and running with Llama 2, Mistral, Gemma, and other large language models. |
| 17 | langchain-ai/langchain </br>  | ⚡ Building applications with LLMs through composability ⚡ |
| 18 | yt-dlp/yt-dlp </br>  | A feature-rich command-line audio/video downloader |
| 19 | puppeteer/puppeteer </br>  | JavaScript API for Chrome and Firefox |
| 20 | pytorch/pytorch </br>  | Tensors and Dynamic neural networks in Python with strong GPU acceleration |
| 21 | mtdvio/every-programmer-should-know </br>  | A collection of (mostly) technical things every software developer should know about |
| 22 | neovim/neovim </br>  | Vim-fork focused on extensibility and usability |
| 23 | tensorflow/models </br>  | Models and examples built with TensorFlow |
| 24 | ChatGPTNextWeb/ChatGPT-Next-Web </br>  | A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。 |
| 25 | supabase/supabase </br>  | The open source Firebase alternative. |
| 26 | home-assistant/core </br>  | 🏡 Open source home automation that puts local control and privacy first. |
| 27 | openai/whisper </br>  | Robust Speech Recognition via Large-Scale Weak Supervision |
| 28 | 3b1b/manim </br>  | Animation engine for explanatory math videos |
| 29 | nomic-ai/gpt4all </br>  | gpt4all: an ecosystem of open-source chatbots trained on a massive collection of clean assistant data including code, stories and dialogue |
| 30 | fighting41love/funNLP </br>  | The Most Powerful NLP-Weapon Arsenal |
| 31 | ggerganov/llama.cpp </br>  | Port of Facebook's LLaMA model in C/C++ |
| 32 | bregman-arie/devops-exercises </br>  | Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions |
| 33 | josephmisiti/awesome-machine-learning </br>  | A curated list of awesome Machine Learning frameworks, libraries and software. |
| 34 | binary-husky/gpt_academic </br>  | Academic Optimization of GPT |
| 35 | hoppscotch/hoppscotch </br>  | Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia) |
| 36 | microsoft/generative-ai-for-beginners </br>  | 12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/ |
| 37 | grafana/grafana </br>  | The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. |
| 38 | d2l-ai/d2l-zh </br>  | Targeting Chinese readers, functional and open for discussion. The Chinese and English versions are used for teaching in over 400 universities across more than 60 countries |
| 39 | python/cpython </br>  | The Python programming language |
| 40 | apache/superset </br>  | Apache Superset is a Data Visualization and Data Exploration Platform |
| 41 | twitter/the-algorithm </br>  | Source code for Twitter's Recommendation Algorithm |
| 42 | xtekky/gpt4free </br>  | decentralizing the Ai Industry, free gpt-4/3.5 scripts through several reverse engineered API's ( poe.com, phind.com, chat.openai.com etc...) |
| 43 | keras-team/keras </br>  | Deep Learning for humans |
| 44 | sherlock-project/sherlock </br>  | Hunt down social media accounts by username across social networks |
| 45 | abi/screenshot-to-code </br>  | Drop in a screenshot and convert it to clean HTML/Tailwind/JS code |
| 46 | scikit-learn/scikit-learn </br>  | scikit-learn: machine learning in Python |
| ⭐ 47 | openai/openai-cookbook </br>  | Examples and guides for using the OpenAI API |
| 48 | binhnguyennus/awesome-scalability </br>  | The Patterns of Scalable, Reliable, and Performant Large-Scale Systems |
| 49 | AppFlowy-IO/AppFlowy </br>  | Bring projects, wikis, and teams together with AI. AppFlowy is an AI collaborative workspace where you achieve more without losing control of your data. The best open source alternative to Notion. |
| 50 | comfyanonymous/ComfyUI </br>  | The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. |
| 51 | meta-llama/llama </br>  | Inference code for Llama models |
| 52 | labmlai/annotated_deep_learning_paper_implementations </br>  | 🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠 |
| 53 | OpenInterpreter/open-interpreter </br>  | A natural language interface for computers |
| 54 | nuxt/nuxt </br>  | The Intuitive Vue Framework. |
| 55 | imartinez/privateGPT </br>  | Interact with your documents using the power of GPT, 100% privately, no data leaks |
| 56 | ageitgey/face_recognition </br>  | The world's simplest facial recognition api for Python and the command line |
| 57 | lencx/ChatGPT </br>  | 🔮 ChatGPT Desktop Application (Mac, Windows and Linux) |
| 58 | PlexPt/awesome-chatgpt-prompts-zh </br>  | ChatGPT Chinese Training Guide. Guidelines for various scenarios. Learn how to make it listen to you |
| 59 | CorentinJ/Real-Time-Voice-Cloning </br>  | Clone a voice in 5 seconds to generate arbitrary speech in real-time |
| 60 | deepfakes/faceswap </br>  | Deepfakes Software For All |
| 61 | gpt-engineer-org/gpt-engineer </br>  | Specify what you want it to build, the AI asks for clarification, and then builds it. |
| 62 | immich-app/immich </br>  | High performance self-hosted photo and video management solution. |
| 63 | langgenius/dify </br>  | One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications. |
| 64 | dair-ai/Prompt-Engineering-Guide </br>  | 🐙 Guides, papers, lecture, notebooks and resources for prompt engineering |
| 65 | commaai/openpilot </br>  | openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 200 supported car makes and models. |
| 66 | xai-org/grok-1 </br>  | Grok open release |
| 67 | jgthms/bulma </br>  | Modern CSS framework based on Flexbox |
| 68 | n8n-io/n8n </br>  | Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services. |
| 69 | open-webui/open-webui </br>  | User-friendly WebUI for LLMs (Formerly Ollama WebUI) |
| 70 | facebookresearch/segment-anything </br>  | The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model. |
| 71 | meilisearch/meilisearch </br>  | A lightning-fast search API that fits effortlessly into your apps, websites, and workflow |
| 72 | Stirling-Tools/Stirling-PDF </br>  | #1 Locally hosted web application that allows you to perform various operations on PDF files |
| 73 | Avik-Jain/100-Days-Of-ML-Code </br>  | 100 Days of ML Coding |
| 74 | v2ray/v2ray-core </br>  | A platform for building proxies to bypass network restrictions. |
| 75 | geekan/MetaGPT </br>  | The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo |
| 76 | lobehub/lobe-chat </br>  | 🤖 Lobe Chat - an open-source, extensible (Function Calling), high-performance chatbot framework. It supports one-click free deployment of your private ChatGPT/LLM web application. |
| 77 | PaddlePaddle/PaddleOCR </br>  | Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices) |
| 78 | alist-org/alist </br>  | 🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。 |
| 79 | type-challenges/type-challenges </br>  | Collection of TypeScript type challenges with online judge |
| 80 | Asabeneh/30-Days-Of-Python </br>  | 30 days of Python programming challenge is a step-by-step guide to learn the Python programming language in 30 days. This challenge may take more than100 days, follow your own pace. These videos may help too: https://www.youtube.com/channel/UC7PNRuno1rzYPb1xLa4yktw |
| 81 | lllyasviel/Fooocus </br>  | Focus on prompting and generating |
| 82 | hacksider/Deep-Live-Cam </br>  | real time face swap and one-click video deepfake with only a single image (uncensored) |
| 83 | jeecgboot/JeecgBoot </br>  | 🔥「企业级低代码平台」前后端分离架构SpringBoot 2.x/3.x，SpringCloud，Ant Design&Vue3，Mybatis，Shiro，JWT。强大的代码生成器让前后端代码一键生成，无需写任何代码! 引领新的开发模式OnlineCoding->代码生成->手工MERGE，帮助Java项目解决70%重复工作，让开发更关注业务，既能快速提高效率，帮助公司节省成本，同时又不失灵活性。 |
| 84 | oobabooga/text-generation-webui </br>  | A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA. |
| 85 | THUDM/ChatGLM-6B </br>  | ChatGLM-6B: An Open Bilingual Dialogue Language Model |
| 86 | fastlane/fastlane </br>  | 🚀 The easiest way to automate building and releasing your iOS and Android apps |
| 87 | mingrammer/diagrams </br>  | 🎨 Diagram as Code for prototyping cloud system architectures |
| 88 | mlabonne/llm-course </br>  | Course with a roadmap and notebooks to get into Large Language Models (LLMs). |
| 89 | dani-garcia/vaultwarden </br>  | Unofficial Bitwarden compatible server written in Rust, formerly known as bitwarden_rs |
| 90 | Stability-AI/stablediffusion </br>  | High-Resolution Image Synthesis with Latent Diffusion Models |
| 91 | getsentry/sentry </br>  | Developer-first error tracking and performance monitoring |
| 92 | psf/black </br>  | The uncompromising Python code formatter |
| 93 | clash-verge-rev/clash-verge-rev </br>  | Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux) |
| 94 | hpcaitech/ColossalAI </br>  | Making large AI models cheaper, faster and more accessible |
| 95 | karpathy/nanoGPT </br>  | The simplest, fastest repository for training/finetuning medium-sized GPTs |
| 96 | apache/airflow </br>  | Apache Airflow - A platform to programmatically author, schedule, and monitor workflows |
| 97 | All-Hands-AI/OpenHands </br>  | 🙌 OpenHands: Code Less, Make More |
| 98 | LAION-AI/Open-Assistant </br>  <a alt="Click Me" href="https://open-assistant.io/chat" target="_blank"><img src="https://img.shields.io/badge/OpenAssistant-Demo-brightgreen" alt="Open in Spaces"/></a> | OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so. |
| 99 | lm-sys/FastChat </br>  | An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5. |
| 100 | QuivrHQ/quivr </br>  | Your GenAI Second Brain 🧠 A personal productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, that you can share with users ! Local & Private alternative to OpenAI GPTs & ChatGPT powered by retrieval-augmented generation. |
| 101 | 2dust/v2rayNG </br>  | A V2Ray client for Android, support Xray core and v2fly core |
| 102 | suno-ai/bark </br>  <a alt="Click Me" href="https://huggingface.co/spaces/suno/bark" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | 🔊 Text-Prompted Generative Audio Model |
| 103 | NaiboWang/EasySpider </br>  | A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。 |
| 104 | RVC-Boss/GPT-SoVITS </br>  | 1 min voice data can also be used to train a good TTS model! (few shot voice cloning) |
| 105 | TencentARC/GFPGAN </br>  | GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration. |
| 106 | streamlit/streamlit </br>  | Streamlit — A faster way to build and share data apps. |
| 107 | ggerganov/whisper.cpp </br>  | Port of OpenAI's Whisper model in C/C++ |
| 108 | XingangPan/DragGAN </br>  <a alt="Click Me" href="https://vcai.mpi-inf.mpg.de/projects/DragGAN/" target="_blank"><img src="https://img.shields.io/badge/Mpg-Project-brightgreen" alt="Open in Spaces"/></a> <a href='https://arxiv.org/abs/2305.10973'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | Code for DragGAN (SIGGRAPH 2023) |
| 109 | coqui-ai/TTS </br>  | 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production |
| 110 | microsoft/DeepSpeed </br>  | A deep learning optimization library that makes distributed training and inference easy, efficient, and effective |
| 111 | typst/typst </br>  | A new markup-based typesetting system that is powerful and easy to learn. |
| 112 | freeCodeCamp/devdocs </br>  | API Documentation Browser |
| 113 | babysor/MockingBird </br>  | 🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time |
| 114 | SimplifyJobs/Summer2025-Internships </br>  | Collection of Summer 2025 tech internships! |
| 115 | langflow-ai/langflow </br>  | ⛓️ Langflow is a visual framework for building multi-agent and RAG applications. It's open-source, Python-powered, fully customizable, model and vector store agnostic. |
| 116 | hiyouga/LLaMA-Factory </br>  | Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM) |
| 117 | LC044/WeChatMsg </br>  | 提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手 |
| 118 | microsoft/autogen </br>  | Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ |
| 119 | lapce/lapce </br>  | Lightning-fast and Powerful Code Editor written in Rust |
| 120 | microsoft/TaskMatrix </br>  <a alt="Click Me" href="https://huggingface.co/spaces/microsoft/visual_chatgpt" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | Talking, Drawing and Editing with Visual Foundation Models |
| 121 | google-research/google-research </br>  | Google Research |
| 122 | ray-project/ray </br>  | Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads. |
| 123 | gradio-app/gradio </br>  | Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work! |
| 124 | OpenBB-finance/OpenBBTerminal </br>  | Investment Research for Everyone, Anywhere. |
| 125 | penpot/penpot </br>  | Penpot: The open-source design tool for design and code collaboration |
| 126 | rasbt/LLMs-from-scratch </br>  | Implementing a ChatGPT-like LLM from scratch, step by step |
| 127 | karanpratapsingh/system-design </br>  | Learn how to design systems at scale and prepare for system design interviews |
| 128 | ultralytics/ultralytics </br>  | NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite |
| 129 | 2noise/ChatTTS </br>  | ChatTTS is a generative speech model for daily dialogue. |
| 130 | chatchat-space/Langchain-Chatchat </br>  | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain |
| 131 | Pythagora-io/gpt-pilot </br>  | PoC for a scalable dev tool that writes entire apps from scratch while the developer oversees the implementation |
| 132 | FlowiseAI/Flowise </br>  | Drag & drop UI to build your customized LLM flow using LangchainJS |
| 133 | Chanzhaoyu/chatgpt-web </br>  | A demonstration website built with Express and Vue3 called ChatGPT |
| 134 | zhayujie/chatgpt-on-wechat </br>  | Wechat robot based on ChatGPT, which uses OpenAI api and itchat library |
| 135 | upscayl/upscayl </br>  | 🆙 Upscayl - Free and Open Source AI Image Upscaler for Linux, MacOS and Windows built with Linux-First philosophy. |
| 136 | hashicorp/vault </br>  | A tool for secrets management, encryption as a service, and privileged access management |
| 137 | freqtrade/freqtrade </br>  | Free, open source crypto trading bot |
| 138 | milvus-io/milvus </br>  | A cloud-native vector database, storage for next generation AI applications |
| 139 | KRTirtho/spotube </br>  | 🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile! |
| 140 | TheAlgorithms/C-Plus-Plus </br>  | Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes. |
| 141 | vllm-project/vllm </br>  | A high-throughput and memory-efficient inference and serving engine for LLMs |
| 142 | facebookresearch/detectron2 </br>  | Detectron2 is a platform for object detection, segmentation and other visual recognition tasks. |
| 143 | facebookresearch/fairseq </br>  | Facebook AI Research Sequence-to-Sequence Toolkit written in Python. |
| 144 | google/jax </br>  | Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more |
| 145 | pola-rs/polars </br>  | Fast multi-threaded, hybrid-out-of-core query engine focussing on DataFrame front-ends |
| 146 | lllyasviel/ControlNet </br>  | Let us control diffusion models! |
| 147 | alibaba/nacos </br>  | an easy-to-use dynamic service discovery, configuration and service management platform for building cloud native applications. |
| 148 | yunjey/pytorch-tutorial </br>  | PyTorch Tutorial for Deep Learning Researchers |
| 149 | myshell-ai/OpenVoice </br>  | Instant voice cloning by MyShell |
| 150 | v2fly/v2ray-core </br>  | A platform for building proxies to bypass network restrictions. |
| 151 | tatsu-lab/stanford_alpaca </br>  | Code and documentation to train Stanford's Alpaca models, and generate the data. |
| 152 | JushBJJ/Mr.-Ranedeer-AI-Tutor </br>  | A GPT-4 AI Tutor Prompt for customizable personalized learning experiences. |
| 153 | mckaywrigley/chatbot-ui </br>  | The open-source AI chat interface for everyone. |
| 154 | linexjlin/GPTs </br>  | leaked prompts of GPTs |
| 155 | s0md3v/roop </br>  | one-click deepfake (face swap) |
| 156 | xinntao/Real-ESRGAN </br>  | Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration. |
| 157 | facebook/folly </br>  | An open-source C++ library developed and used at Facebook. |
| 158 | Lightning-AI/pytorch-lightning </br>  | Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes. |
| 159 | acheong08/ChatGPT </br>  | Reverse engineered ChatGPT API |
| 160 | google-ai-edge/mediapipe </br>  | Cross-platform, customizable ML solutions for live and streaming media. |
| 161 | Mintplex-Labs/anything-llm </br>  | A full-stack application that turns any documents into an intelligent chatbot with a sleek UI and easier way to manage your workspaces. |
| 162 | hiroi-sora/Umi-OCR </br>  | OCR图片转文字识别软件，完全离线。截屏/批量导入图片，支持多国语言、合并段落、竖排文字。可排除水印区域，提取干净的文本。基于 PaddleOCR 。 |
| 163 | eugeneyan/applied-ml </br>  | 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production. |
| 164 | google-research/tuning_playbook </br>  | A playbook for systematically maximizing the performance of deep learning models. |
| 165 | meta-llama/llama3 </br>  | The official Meta Llama 3 GitHub site |
| 166 | mli/paper-reading </br>  | Classic Deep Learning and In-Depth Reading of New Papers Paragraph by Paragraph |
| 167 | tokio-rs/tokio </br>  | A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ... |
| 168 | tinygrad/tinygrad </br>  | You like pytorch? You like micrograd? You love tinygrad! ❤️ |
| 169 | mouredev/Hello-Python </br>  | Curso para aprender el lenguaje de programación Python desde cero y para principiantes. 75 clases, 37 horas en vídeo, código, proyectos y grupo de chat. Fundamentos, frontend, backend, testing, IA... |
| 170 | iperov/DeepFaceLive </br>  | Real-time face swap for PC streaming or video calls |
| 171 | mindsdb/mindsdb </br>  | The platform for customizing AI from enterprise data |
| 172 | HeyPuter/puter </br>  | 🌐 The Internet OS! Free, Open-Source, and Self-Hostable. |
| 173 | huggingface/diffusers </br>  | 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX. |
| 174 | mudler/LocalAI </br>  | 🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities. |
| 175 | openai/CLIP </br>  | CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image |
| 176 | svc-develop-team/so-vits-svc </br>  | SoftVC VITS Singing Voice Conversion |
| 177 | airbnb/lottie-ios </br>  | An iOS library to natively render After Effects vector animations |
| 178 | XTLS/Xray-core </br>  | Xray, Penetrates Everything. Also the best v2ray-core, with XTLS support. Fully compatible configuration. |
| 179 | OpenBMB/ChatDev </br>  | Create Customized Software using Natural Language Idea (through Multi-Agent Collaboration) |
| 180 | danielmiessler/fabric </br>  | fabric is an open-source framework for augmenting humans using AI. |
| 181 | getcursor/cursor </br>  | An editor made for programming with AI |
| 182 | Vision-CAIR/MiniGPT-4 </br>  <a alt="Click Me" href="https://huggingface.co/spaces/Vision-CAIR/minigpt4" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> <a href='https://arxiv.org/abs/2304.10592'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | Enhancing Vision-language Understanding with Advanced Large Language Models |
| 183 | DataTalksClub/data-engineering-zoomcamp </br>  | Free Data Engineering course! |
| 184 | academic/awesome-datascience </br>  | 📝 An awesome Data Science repository to learn and apply for real world problems. |
| 185 | chatanywhere/GPT_API_free </br>  | Free ChatGPT API Key, Free ChatGPT API, supports GPT-4 API (free), ChatGPT offers a free domestic forwarding API that allows direct connections without the need for a proxy. It can be used in conjunction with software/plugins like ChatBox, significantly reducing interface usage costs. Enjoy unlimited and unrestricted chatting within China |
| 186 | RVC-Project/Retrieval-based-Voice-Conversion-WebUI </br>  | Voice data <= 10 mins can also be used to train a good VC model! |
| 187 | Stability-AI/generative-models </br>  | Generative Models by Stability AI |
| 188 | karpathy/llm.c </br>  | LLM training in simple, raw C/CUDA |
| 189 | gabime/spdlog </br>  | Fast C++ logging library. |
| 190 | roboflow/supervision </br>  | We write your reusable computer vision tools. 💜 |
| 191 | apache/flink </br>  | Apache Flink |
| 192 | yetone/openai-translator </br>  | Browser extension and cross-platform desktop application for translation based on ChatGPT API |
| 193 | nrwl/nx </br>  | Smart Monorepos · Fast CI |
| 194 | invoke-ai/InvokeAI </br>  | InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products. |
| 195 | microsoft/JARVIS </br>  <a alt="Click Me" href="https://huggingface.co/spaces/microsoft/HuggingGPT" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | a system to connect LLMs with ML community |
| 196 | janhq/jan </br>  | Jan is an open source alternative to ChatGPT that runs 100% offline on your computer |
| 197 | infiniflow/ragflow </br>  | RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. |
| 198 | stretchr/testify </br>  | A toolkit with common assertions and mocks that plays nicely with the standard library |
| 199 | deepinsight/insightface </br>  | State-of-the-art 2D and 3D Face Analysis Project |
| 200 | rancher/rancher </br>  | Complete container management platform |
| 201 | google/flatbuffers </br>  | FlatBuffers: Memory Efficient Serialization Library |
| 202 | opentofu/opentofu </br>  | OpenTofu lets you declaratively manage your cloud infrastructure. |
| 203 | modularml/mojo </br>  | The Mojo Programming Language |
| 204 | bazelbuild/bazel </br>  | a fast, scalable, multi-language and extensible build system |
| 205 | openai/openai-python </br>  | The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language. |
| 206 | mem0ai/mem0 </br>  | The memory layer for Personalized AI |
| 207 | TheAlgorithms/Rust </br>  | All Algorithms implemented in Rust |
| 208 | Bin-Huang/chatbox </br>  | A desktop app for GPT-4 / GPT-3.5 (OpenAI API) that supports Windows, Mac & Linux |
| 209 | drawdb-io/drawdb </br>  | Free, simple, and intuitive online database design tool and SQL generator. |
| 210 | openai/gpt-2 </br>  | Code for the paper "Language Models are Unsupervised Multitask Learners" |
| 211 | paul-gauthier/aider </br>  | aider is GPT powered coding in your terminal |
| 212 | PaddlePaddle/Paddle </br>  | PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署） |
| 213 | PostHog/posthog </br>  | 🦔 PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host. |
| 214 | microsoft/semantic-kernel </br>  | Integrate cutting-edge LLM technology quickly and easily into your apps |
| 215 | TabbyML/tabby </br>  | Self-hosted AI coding assistant |
| 216 | frappe/erpnext </br>  | Free and Open Source Enterprise Resource Planning (ERP) |
| 217 | zulip/zulip </br>  | Zulip server and web application. Open-source team chat that helps teams stay productive and focused. |
| 218 | joaomdmoura/crewAI </br>  | Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. |
| 219 | warpdotdev/Warp </br>  | Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster. |
| 220 | shardeum/shardeum </br>  | Shardeum is an EVM based autoscaling blockchain |
| 221 | grpc/grpc-go </br>  | The Go language implementation of gRPC. HTTP/2 based RPC |
| 222 | openai/chatgpt-retrieval-plugin </br>  | Plugins are chat extensions designed specifically for language models like ChatGPT, enabling them to access up-to-date information, run computations, or interact with third-party services in response to a user's request. |
| 223 | facebookresearch/audiocraft </br>  | Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning. |
| 224 | qdrant/qdrant </br>  <a alt="Click Me" href="https://demo.qdrant.tech" target="_blank"><img src="https://img.shields.io/badge/Qdrant-Demo-brightgreen" alt="Open in Demo"/></a> | Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/ |
| 225 | ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code </br>  | 500 AI Machine learning Deep learning Computer vision NLP Projects with code |
| 226 | Mozilla-Ocho/llamafile </br>  | Distribute and run LLMs with a single file. |
| 227 | yoheinakajima/babyagi </br>  | uses OpenAI and Pinecone APIs to create, prioritize, and execute tasks, This is a pared-down version of the original Task-Driven Autonomous Agent |
| 228 | DataExpert-io/data-engineer-handbook </br>  | This is a repo with links to everything you'd ever want to learn about data engineering |
| 229 | haotian-liu/LLaVA </br>  <a alt="Click Me" href="https://llava.hliu.cc" target="_blank"><img src="https://img.shields.io/badge/Gradio-Spaces-brightgreen" alt="Open in Demo"/></a> <a href='https://arxiv.org/abs/2304.08485'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities. |
| 230 | karpathy/minGPT </br>  | A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training |
| 231 | microsoft/unilm </br>  | Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities |
| 232 | PromtEngineer/localGPT </br>  | Chat with your documents on your local device using GPT models. No data leaves your device and 100% private. |
| 233 | yuliskov/SmartTube </br>  | SmartTube - an advanced player for set-top boxes and tvs running Android OS |
| 234 | facefusion/facefusion </br>  | Next generation face swapper and enhancer |
| 235 | elastic/kibana </br>  | Your window into the Elastic Stack |
| 236 | Sanster/lama-cleaner </br>  | Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures. |
| 237 | HumanSignal/label-studio </br>  | Label Studio is a multi-type data labeling and annotation tool with standardized output format |
| 238 | continuedev/continue </br>  | ⏩ the open-source copilot chat for software development—bring the power of ChatGPT to VS Code |
| 239 | blakeblackshear/frigate </br>  | NVR with realtime local object detection for IP cameras |
| 240 | microsoft/graphrag </br>  | A modular graph-based Retrieval-Augmented Generation (RAG) system |
| 241 | songquanpeng/one-api </br>  | OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI. |
| 242 | danny-avila/LibreChat </br>  | Enhanced ChatGPT Clone: Features OpenAI, GPT-4 Vision, Bing, Anthropic, OpenRouter, Google Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development |
| 243 | mlc-ai/mlc-llm </br>  | Enable everyone to develop, optimize and deploy AI models natively on everyone's devices. |
| 244 | guidance-ai/guidance </br>  | A guidance language for controlling large language models. |
| 245 | stanfordnlp/dspy </br>  | Stanford DSPy: The framework for programming—not prompting—foundation models |
| 246 | mendableai/firecrawl </br>  | 🔥 Turn entire websites into LLM-ready markdown |
| 247 | Hannibal046/Awesome-LLM </br>  | Awesome-LLM: a curated list of Large Language Model |
| 248 | BuilderIO/gpt-crawler </br>  | Crawl a site to generate knowledge files to create your own custom GPT from a URL |
| 249 | mlflow/mlflow </br>  | Open source platform for the machine learning lifecycle |
| 250 | tree-sitter/tree-sitter </br>  | An incremental parsing system for programming tools |
| 251 | tloen/alpaca-lora </br>  <a alt="Click Me" href="https://huggingface.co/spaces/tloen/alpaca-lora" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | Instruct-tune LLaMA on consumer hardware |
| 252 | LiLittleCat/awesome-free-chatgpt </br>  | 🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated. |
| 253 | ashishps1/awesome-system-design-resources </br>  | This repository contains System Design resources which are useful while preparing for interviews and learning Distributed Systems |
 254 | stitionai/devika </br>  | Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI. |
 255 | labring/FastGPT </br>  | A platform that uses the OpenAI API to quickly build an AI knowledge base, supporting many-to-many relationships. |
| 256 | unslothai/unsloth </br>  | 5X faster 50% less memory LLM finetuning |
| 257 | ymcui/Chinese-LLaMA-Alpaca </br>  | Chinese LLaMA & Alpaca LLMs |
| 258 | Anjok07/ultimatevocalremovergui </br>  | GUI for a Vocal Remover that uses Deep Neural Networks. |
| 259 | harry0703/MoneyPrinterTurbo </br>  | Generate short videos with one click using a large model |
| 260 | opendatalab/MinerU </br>  | A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。 |
| 261 | ml-tooling/best-of-ml-python </br>  | 🏆 A ranked list of awesome machine learning Python libraries. Updated weekly. |
| 262 | kenjihiranabe/The-Art-of-Linear-Algebra </br>  | Graphic notes on Gilbert Strang's "Linear Algebra for Everyone" |
| 263 | wez/wezterm </br>  | A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust |
| 264 | samber/lo </br>  | 💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...) |
| 265 | brave/brave-browser </br>  | Brave browser for Android, iOS, Linux, macOS, Windows. |
| 266 | deepset-ai/haystack </br>  | 🔍 Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build complex question answering, semantic search, text generation applications, and more. |
| 267 | renovatebot/renovate </br>  | Universal dependency update tool that fits into your workflows. |
| 268 | thingsboard/thingsboard </br>  | Open-source IoT Platform - Device management, data collection, processing and visualization. |
| 269 | joonspk-research/generative_agents </br>  | Generative Agents: Interactive Simulacra of Human Behavior |
| 270 | DarkFlippers/unleashed-firmware </br>  | Flipper Zero Unleashed Firmware |
| 271 | PrefectHQ/prefect </br>  | Prefect is a workflow orchestration tool empowering developers to build, observe, and react to data pipelines |
| 272 | LazyVim/LazyVim </br>  | Neovim config for the lazy |
| 273 | Cinnamon/kotaemon </br>  | An open-source RAG-based tool for chatting with your documents. |
| 274 | ml-explore/mlx </br>  | MLX: An array framework for Apple silicon |
| 275 | valkey-io/valkey </br>  | A flexible distributed key-value datastore that supports both caching and beyond caching workloads. |
| 276 | Mikubill/sd-webui-controlnet </br>  | WebUI extension for ControlNet |
| 277 | xx025/carrot </br>  | Free ChatGPT Site List |
| 278 | CodePhiliaX/Chat2DB </br>  | 🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more. |
| 279 | apple/ml-stable-diffusion </br>  | Stable Diffusion with Core ML on Apple Silicon |
| 280 | rlabbe/Kalman-and-Bayesian-Filters-in-Python </br>  | Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions. |
| 281 | microsoft/LightGBM </br>  | A fast, distributed, high-performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. |
| 282 | w-okada/voice-changer </br>  | リアルタイムボイスチェンジャー Realtime Voice Changer |
| 283 | transitive-bullshit/chatgpt-api </br>  | Node.js client for the official ChatGPT API. |
| 284 | ardalis/CleanArchitecture </br>  | Clean Architecture Solution Template: A starting point for Clean Architecture with ASP.NET Core |
| 285 | emilwallner/Screenshot-to-code </br>  | A neural network that transforms a design mock-up into a static website. |
| 286 | unclecode/crawl4ai </br>  | 🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper |
| 287 | openai/swarm </br>  | Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team. |
| 288 | ItzCrazyKns/Perplexica </br>  | Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI |
| 289 | ente-io/ente </br>  | Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos |
| 290 | HqWu-HITCS/Awesome-Chinese-LLM </br>  | Organizing smaller, cost-effective, privately deployable open-source Chinese language models, including related datasets and tutorials |
| 291 | meta-llama/codellama </br>  | Inference code for CodeLlama models |
| 292 | dair-ai/ML-YouTube-Courses </br>  | 📺 Discover the latest machine learning / AI courses on YouTube. |
| 293 | khoj-ai/khoj </br>  | Your AI second brain. A copilot to get answers to your questions, whether they be from your own notes or from the internet. Use powerful, online (e.g gpt4) or private, local (e.g mistral) LLMs. Self-host locally or use our web app. Access from Obsidian, Emacs, Desktop app, Web or Whatsapp. |
| 294 | VinciGit00/Scrapegraph-ai </br>  | Python scraper based on AI |
| 295 | Stability-AI/StableLM </br>  | Stability AI Language Models |
| 296 | pybind/pybind11 </br>  | Seamless operability between C++11 and Python |
| 297 | apify/crawlee </br>  | Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation. |
| 298 | THUDM/ChatGLM2-6B </br>  | ChatGLM2-6B: An Open Bilingual Chat LLM |
| 299 | microsoft/qlib </br>  | Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL. |
| 300 | phidatahq/phidata </br>  | Build AI Assistants using function calling |
| 301 | chroma-core/chroma </br>  | the AI-native open-source embedding database |
| 302 | ddbourgin/numpy-ml </br>  | Machine learning, in numpy |
| 303 | Avaiga/taipy </br>  | Turns Data and AI algorithms into production-ready web applications in no time. |
| 304 | exo-explore/exo </br>  | Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚ |
| 305 | RPCS3/rpcs3 </br>  | PS3 emulator/debugger |
| 306 | TransformerOptimus/SuperAGI </br>  | <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably. |
| 307 | umijs/umi </br>  | A framework in react community ✨ |
| 308 | typescript-eslint/typescript-eslint </br>  | ✨ Monorepo for all the tooling which enables ESLint to support TypeScript |
| 309 | meta-llama/llama-recipes </br>  | Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger |
| 310 | GaiZhenbiao/ChuanhuChatGPT </br>  | GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI. |
| 311 | sunner/ChatALL </br>  | Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vincuna, Claude, ChatGLM, MOSS, iFlytek Spark, ERNIE and more, discover the best answers |
| 312 | amplication/amplication </br>  | 🔥🔥🔥 The Only Production-Ready AI-Powered Backend Code Generation |
| 313 | NVIDIA/open-gpu-kernel-modules </br>  | NVIDIA Linux open GPU kernel module source |
| 314 | neondatabase/neon </br>  | Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero. |
| 315 | IDEA-Research/Grounded-Segment-Anything </br>  | Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect, Segment and Generate Anything with Image and Text Inputs |
| 316 | microsoft/Bringing-Old-Photos-Back-to-Life </br>  | Bringing Old Photo Back to Life (CVPR 2020 oral) |
| 317 | KindXiaoming/pykan </br>  | Kolmogorov Arnold Networks |
| 318 | abseil/abseil-cpp </br>  | Abseil Common Libraries (C++) |
| 319 | openai/evals </br>  | Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks. |
| 320 | arc53/DocsGPT </br>  | GPT-powered chat for documentation, chat with your documents |
| 321 | assafelovic/gpt-researcher </br>  | GPT based autonomous agent that does online comprehensive research on any given topic |
| 322 | mayooear/gpt4-pdf-chatbot-langchain </br>  | GPT4 & LangChain Chatbot for large PDF docs |
| 323 | influxdata/telegraf </br>  | Agent for collecting, processing, aggregating, and writing metrics, logs, and other arbitrary data. |
| 324 | microsoft/onnxruntime </br>  | ONNX Runtime: cross-platform, high-performance ML inferencing and training accelerator |
| 325 | serengil/deepface </br>  | A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python |
| 326 | graphdeco-inria/gaussian-splatting </br>  | Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering" |
| 327 | alibaba/lowcode-engine </br>  | An enterprise-class low-code technology stack with scale-out design / 一套面向扩展设计的企业级低代码技术体系 |
| 328 | xcanwin/KeepChatGPT </br>  | Using ChatGPT is more efficient and smoother, perfectly solving ChatGPT network errors. No longer do you need to frequently refresh the webpage, saving over 10 unnecessary steps |
| 329 | apache/arrow </br>  | Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing |
| 330 | fishaudio/fish-speech </br>  | Brand new TTS solution |
| 331 | fauxpilot/fauxpilot </br>  | An open-source GitHub Copilot server |
| 332 | HumanAIGC/AnimateAnyone </br>  | Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation |
| 333 | Dao-AILab/flash-attention </br>  | Fast and memory-efficient exact attention |
| 334 | VikParuchuri/surya </br>  | Accurate line-level text detection and recognition (OCR) in any language |
| 335 | QwenLM/Qwen-7B </br>  | The official repo of Qwen-7B (通义千问-7B) chat & pretrained large language model proposed by Alibaba Cloud. |
| 336 | Raphire/Win11Debloat </br>  | A simple, easy to use PowerShell script to remove pre-installed apps from windows, disable telemetry, remove Bing from windows search as well as perform various other changes to declutter and improve your windows experience. This script works for both windows 10 and windows 11. |
| 337 | overleaf/overleaf </br>  | A web-based collaborative LaTeX editor |
| 338 | BerriAI/litellm </br>  | Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs) |
| 339 | AI4Finance-Foundation/FinGPT </br>  | Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We'll soon release the trained model. |
| 340 | LlamaFamily/Llama-Chinese </br>  | Llama Chinese Community, the best Chinese Llama large model, fully open source and commercially available |
| 341 | unifyai/ivy </br>  | Unified AI |
| 342 | datawhalechina/leedl-tutorial </br>  | 《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases |
| 343 | espressif/esp-idf </br>  | Espressif IoT Development Framework. Official development framework for Espressif SoCs. |
| 344 | eosphoros-ai/DB-GPT </br>  | Revolutionizing Database Interactions with Private LLM Technology |
| 345 | naklecha/llama3-from-scratch </br>  | llama3 implementation one matrix multiplication at a time |
| 346 | princeton-nlp/SWE-agent </br>  | SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models |
| 347 | mlc-ai/web-llm </br>  | Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support. |
| 348 | bleedline/aimoneyhunter </br>  | AI Side Hustle Money Mega Collection: Teaching You How to Utilize AI for Various Side Projects to Earn Extra Income. |
| 349 | gventuri/pandas-ai </br>  | Pandas AI is a Python library that integrates generative artificial intelligence capabilities into Pandas, making dataframes conversational |
| 350 | THUDM/ChatGLM3 </br>  | ChatGLM3 series: Open Bilingual Chat LLMs |
| 351 | triton-lang/triton </br>  | Development repository for the Triton language and compiler |
| 352 | stanford-oval/storm </br>  | An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. |
| 353 | stefan-jansen/machine-learning-for-trading </br>  | Code for Machine Learning for Algorithmic Trading, 2nd edition. |
| 354 | state-spaces/mamba </br>  | Mamba: Linear-Time Sequence Modeling with Selective State Spaces |
| 355 | fuergaosi233/wechat-chatgpt </br>  | Use ChatGPT On Wechat via wechaty |
| 356 | wong2/chatgpt-google-extension</br>  | A browser extension that enhances search engines with ChatGPT, this repos will not be updated from 2023-02-20 |
| 357 | neonbjb/tortoise-tts </br>  | A multi-voice TTS system trained with an emphasis on quality |
| 358 | steven-tey/novel </br>  | Notion-style WYSIWYG editor with AI-powered autocompletions |
| 359 | teableio/teable </br>  | ✨ The Next Gen Airtable Alternative: No-Code Postgres |
| 360 | adobe/react-spectrum </br>  | A collection of libraries and tools that help you build adaptive, accessible, and robust user experiences. |
| 361 | letta-ai/letta </br>  | Letta (formerly MemGPT) is a framework for creating LLM services with memory. |
| 362 | CopilotKit/CopilotKit </br>  | Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps. |
| 363 | Zeyi-Lin/HivisionIDPhotos </br>  | ⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。 |
| 364 | lukas-blecher/LaTeX-OCR </br>  | pix2tex: Using a ViT to convert images of equations into LaTeX code. |
| 365 | BradyFU/Awesome-Multimodal-Large-Language-Models </br>  | Latest Papers and Datasets on Multimodal Large Language Models |
| 366 | nocobase/nocobase </br>  | NocoBase is a scalability-first, open-source no-code/low-code platform for building business applications and enterprise solutions. |
| 367 | pgvector/pgvector </br>  | Open-source vector similarity search for Postgres |
| 368 | OpenBMB/MiniCPM-V </br>  | MiniCPM-V 2.0: An Efficient End-side MLLM with Strong OCR and Understanding Capabilities |
| 369 | BlinkDL/RWKV-LM </br>  | RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it combines the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding. |
| 370 | chidiwilliams/buzz </br>  | Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper. |
| 371 | guillaumekln/faster-whisper </br>  | Faster Whisper transcription with CTranslate2 |
| 372 | m-bain/whisperX </br>  | WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) |
| 373 | cline/cline </br>  | Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way. |
| 374 | openai/tiktoken </br>  | tiktoken is a fast BPE tokeniser for use with OpenAI's models. |
| 375 | pytube/pytube </br>  | A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos. |
| 376 | plasma-umass/scalene </br>  | Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals |
| 377 | NVIDIA/NeMo </br>  | A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) |
| 378 | Koenkk/zigbee2mqtt </br>  | Zigbee 🐝 to MQTT bridge 🌉, get rid of your proprietary Zigbee bridges 🔨 |
| 379 | xenova/transformers.js </br>  | State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server! |
| 380 | vanna-ai/vanna </br>  | 🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄. |
| 381 | OpenTalker/SadTalker </br>  | [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation |
| 382 | willwulfken/MidJourney-Styles-and-Keywords-Reference </br>  | A reference containing Styles and Keywords that you can use with MidJourney AI |
| 383 | udecode/plate </br>  | A rich-text editor powered by AI |
| 384 | OpenLMLab/MOSS </br>  | An open-source tool-augmented conversational language model from Fudan University |
| 385 | netease-youdao/QAnything </br>  | Question and Answer based on Anything. |
| 386 | smol-ai/developer </br>  | With 100k context windows on the way, it's now feasible for every dev to have their own smol developer |
| 387 | ComposioHQ/composio </br>  | Composio equips agents with well-crafted tools empowering them to tackle complex tasks |
| 388 | stas00/ml-engineering </br>  | Machine Learning Engineering Guides and Tools |
| 389 | official-stockfish/Stockfish </br>  | UCI chess engine |
| 390 | openai/shap-e </br>  | Generate 3D objects conditioned on text or images |
| 391 | illacloud/illa-builder </br>  | Create AI-Driven Apps like Assembling Blocks |
| 392 | PKU-YuanGroup/Open-Sora-Plan </br>  | This project aim to reproduce Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project. |
| 393 | 1Panel-dev/MaxKB </br>  | ? Based on LLM large language model knowledge base Q&A system. Ready to use out of the box, supports quick integration into third-party business systems. Officially produced by 1Panel |
| 394 | e2b-dev/awesome-ai-agents </br>  | A list of AI autonomous agents |
| 395 | ShishirPatil/gorilla </br>  | Gorilla: An API store for LLMs |
| 396 | bytebase/bytebase </br>  | World's most advanced database DevOps and CI/CD for Developer, DBA and Platform Engineering teams. The GitLab/GitHub for database DevOps. |
| 397 | h2oai/h2ogpt </br>  | Come join the movement to make the world's best open source GPT led by H2O.ai - 100% private chat and document search, no data leaks, Apache 2.0 |
| 398 | ggerganov/ggml </br>  | Tensor library for machine learning |
| 399 | eugeneyan/open-llms </br>  | A list of open LLMs available for commercial use. |
| 400 | kgrzybek/modular-monolith-with-ddd </br>  | Full Modular Monolith application with Domain-Driven Design approach. |
| 401 | DataTalksClub/mlops-zoomcamp </br>  | Free MLOps course from DataTalks.Club |
| 402 | InstantID/InstantID </br>  | InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥 |
| 403 | mrdbourke/pytorch-deep-learning </br>  | Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course. |
| 404 | hajimehoshi/ebiten </br>  | Ebitengine - A dead simple 2D game engine for Go |
| 405 | kubeshark/kubeshark </br>  | The API traffic analyzer for Kubernetes providing real-time K8s protocol-level visibility, capturing and monitoring all traffic and payloads going in, out and across containers, pods, nodes and clusters. Inspired by Wireshark, purposely built for Kubernetes |
| 406 | owainlewis/awesome-artificial-intelligence </br>  | A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers. |
| 407 | facebookresearch/seamless_communication </br>  | Foundational Models for State-of-the-Art Speech and Text Translation |
| 408 | Rudrabha/Wav2Lip </br>  | This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. |
| 409 | NVIDIA/TensorRT </br>  | NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT. |
| 410 | getumbrel/llama-gpt </br>  | A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. |
| 411 | plandex-ai/plandex </br>  | An AI coding engine for complex tasks |
| 412 | databrickslabs/dolly </br>  | A large language model trained on the Databricks Machine Learning Platform |
| 413 | Lightning-AI/litgpt </br>  | Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more. |
| 414 | danswer-ai/danswer </br>  | Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc. |
| 415 | gitroomhq/postiz-app </br>  | 📨 Schedule social posts, measure them, exchange with other members and get a lot of help from AI 🚀 |
| 416 | NVIDIA/Megatron-LM </br>  | Ongoing research training transformer models at scale |
| 417 | facebookresearch/AnimatedDrawings </br>  <a alt="Click Me" href="https://sketch.metademolab.com/canvas" target="_blank"><img src="https://img.shields.io/badge/Meta-Demo-brightgreen" alt="Open in Spaces"/></a> | Code to accompany "A Method for Animating Children's Drawings of the Human Figure" |
| 418 | Skyvern-AI/skyvern </br>  | Automate browser-based workflows with LLMs and Computer Vision |
| 419 | DS4SD/docling </br>  | Get your docs ready for gen AI |
| 420 | karpathy/micrograd </br>  | A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API |
| 421 | WordPress/gutenberg </br>  | The Block Editor project for WordPress and beyond. Plugin is available from the official repository. |
| 422 | HigherOrderCO/HVM </br>  | A massively parallel, optimal functional runtime in Rust |
| 423 | magic-research/magic-animate </br>  | MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model |
| 424 | RUCAIBox/LLMSurvey </br>  | A collection of papers and resources related to Large Language Models. |
| 425 | lz4/lz4 </br>  | Extremely Fast Compression algorithm |
| 426 | Z3Prover/z3 </br>  | The Z3 Theorem Prover |
| 427 | libretro/RetroArch </br>  | Cross-platform, sophisticated frontend for the libretro API. Licensed GPLv3. |
| 428 | dair-ai/ML-Papers-of-the-Week </br>  | 🔥Highlighting the top ML papers every week. |
| 429 | szimek/sharedrop </br>  | Easy P2P file transfer powered by WebRTC - inspired by Apple AirDrop |
| 430 | vercel-labs/ai </br>  | Build AI-powered applications with React, Svelte, and Vue |
| 431 | aws/amazon-sagemaker-examples </br>  | Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker. |
| 432 | huggingface/trl </br>  | Train transformer language models with reinforcement learning. |
| 433 | bentoml/OpenLLM </br>  | An open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease. |
| 434 | artidoro/qlora </br>  <a alt="Click Me" href="https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> <a href='https://arxiv.org/abs/2305.14314'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | QLoRA: Efficient Finetuning of Quantized LLMs |
| 435 | chathub-dev/chathub </br>  | All-in-one chatbot client |
| 436 | AIGC-Audio/AudioGPT</br>  | AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head |
| 437 | PaperMC/Paper </br>  | The most widely used, high performance Minecraft server that aims to fix gameplay and mechanics inconsistencies |
| 438 | kedro-org/kedro </br>  | Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular. |
| 439 | activepieces/activepieces </br>  | Your friendliest open source all-in-one automation tool ✨ Workflow automation tool 100+ integration / Enterprise automation tool / Zapier Alternative |
| 440 | THU-MIG/yolov10 </br>  | YOLOv10: Real-Time End-to-End Object Detection |
| 441 | salesforce/LAVIS </br>  | LAVIS - A One-stop Library for Language-Vision Intelligence |
| 442 | srush/GPU-Puzzles </br>  | Solve puzzles. Learn CUDA. |
| 443 | zyronon/douyin </br>  | Vue3 + Pinia + Vite5 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile |
| 444 | QwenLM/Qwen2.5 </br>  | Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud. |
| 445 | vosen/ZLUDA </br>  | CUDA on AMD GPUs |
| 446 | mistralai/mistral-src </br>  | Reference implementation of Mistral AI 7B v0.1 model. |
| 447 | LibreTranslate/LibreTranslate </br>  | Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup. |
| 448 | cumulo-autumn/StreamDiffusion </br>  | StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation |
| 449 | TheR1D/shell_gpt </br>  | A command-line productivity tool powered by ChatGPT, will help you accomplish your tasks faster and more efficiently |
| 450 | vercel/ai-chatbot </br>  | A full-featured, hackable Next.js AI chatbot built by Vercel |
| 451 | mediar-ai/screenpipe </br>  | 24/7 local AI screen & mic recording. Build AI apps that have the full context. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust. |
| 452 | DataTalksClub/machine-learning-zoomcamp </br>  | The code from the Machine Learning Bookcamp book and a free course based on the book |
| 453 | normal-computing/outlines </br>  | Generative Model Programming |
| 454 | nerfstudio-project/nerfstudio </br>  | A collaboration friendly studio for NeRFs |
| 455 | microsoft/promptflow </br>  | Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring. |
| 456 | NielsRogge/Transformers-Tutorials </br>  | This repository contains demos I made with the Transformers library by HuggingFace. |
| 457 | cupy/cupy </br>  | NumPy & SciPy for GPU |
| 458 | popcorn-official/popcorn-desktop </br>  | Popcorn Time is a multi-platform, free software BitTorrent client that includes an integrated media player ( Windows / Mac / Linux ) A Butter-Project Fork |
| 459 | electric-sql/pglite </br>  | Lightweight Postgres packaged as WASM into a TypeScript library for the browser, Node.js, Bun and Deno from https://electric-sql.com |
| 460 | BloopAI/bloop </br>  | A fast code search engine written in Rust |
| 461 | BlinkDL/ChatRWKV </br>  <a alt="Click Me" href="https://huggingface.co/spaces/BlinkDL/Raven-RWKV-7B" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source. |
| 462 | mshumer/gpt-prompt-engineer </br>  | |
| 463 | THUDM/CogVideo </br>  | Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023) |
| 464 | aishwaryanr/awesome-generative-ai-guide </br>  | A one stop repository for generative AI research updates, interview resources, notebooks and much more! |
| 465 | facebookresearch/dinov2 </br>  <a alt="Click Me" href="https://dinov2.metademolab.com/demos" target="_blank"><img src="https://img.shields.io/badge/Meta-Demo-brightgreen" alt="Open in Demo"/></a> <a href='https://arxiv.org/abs/2304.07193'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | PyTorch code and models for the DINOv2 self-supervised learning method. |
| 466 | sashabaranov/go-openai </br>  | OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go |
| 467 | dice2o/BingGPT </br>  | Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux) |
| 468 | TheRamU/Fay </br>  | Fay is a complete open source project that includes Fay controller and numeral models, which can be used in different applications such as virtual hosts, live promotion, numeral human interaction and so on |
| 469 | bigscience-workshop/petals </br>  | 🌸 Run large language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading |
| 470 | Unstructured-IO/unstructured </br>  | Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines. |
| 471 | karpathy/minbpe </br>  | Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization. |
| 472 | wandb/wandb </br>  | 🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API. |
| 473 | autowarefoundation/autoware </br>  | Autoware - the world's leading open-source software project for autonomous driving |
| 474 | modelscope/facechain </br>  | FaceChain is a deep-learning toolchain for generating your Digital-Twin. |
| 475 | huggingface/text-generation-inference </br>  | Large Language Model Text Generation Inference |
| 476 | manticoresoftware/manticoresearch </br>  | Easy to use open source fast database for search |
| 477 | google/benchmark </br>  | A microbenchmark support library |
| 478 | WongKinYiu/yolov9 </br>  | Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information |
| 479 | togethercomputer/OpenChatKit </br>  | OpenChatKit provides a powerful, open-source base to create both specialized and general purpose chatbots for various applications |
| 480 | facebookresearch/nougat </br>  | Implementation of Nougat Neural Optical Understanding for Academic Documents |
| 481 | burn-rs/burn </br>  | Burn - A Flexible and Comprehensive Deep Learning Framework in Rust |
| 482 | dataelement/bisheng </br>  | Bisheng is an open LLM devops platform for next generation AI applications. |
| 483 | timlrx/tailwind-nextjs-starter-blog </br>  | This is a Next.js, Tailwind CSS blogging starter template. Comes out of the box configured with the latest technologies to make technical writing a breeze. Easily configurable and customizable. Perfect as a replacement to existing Jekyll and Hugo individual blogs. |
| 484 | OthersideAI/self-operating-computer </br>  | A framework to enable multimodal models to operate a computer. |
| 485 | RayTracing/raytracing.github.io </br>  | Main Web Site (Online Books) |
| 486 | adams549659584/go-proxy-bingai </br>  <a alt="Click Me" href="https://bing.vcanbb.top" target="_blank"><img src="https://img.shields.io/badge/ProxyBing-Demo-brightgreen" alt="Open in Demo"/></a> | A Microsoft New Bing demo site built with Vue3 and Go, providing a consistent UI experience, supporting ChatGPT prompts, and accessible within China |
| 487 | Stability-AI/StableStudio </br>  | Community interface for generative AI |
| 488 | Visualize-ML/Book4_Power-of-Matrix </br>  | Book_4 'Power of Matrix' |
| 489 | voicepaw/so-vits-svc-fork </br>  <a alt="Click Me" href="https://colab.research.google.com/github/34j/so-vits-svc-fork/blob/main/notebooks/so-vits-svc-fork-4.0.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/></a> | so-vits-svc fork with realtime support, improved interface and more features. |
| 490 | pymc-devs/pymc </br>  | Bayesian Modeling and Probabilistic Programming in Python |
| 491 | NVIDIA/TensorRT-LLM </br>  | TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines. |
| 492 | gorse-io/gorse </br>  | Gorse open source recommender system engine |
| 493 | lllyasviel/stable-diffusion-webui-forge </br>  | a platform on top of Stable Diffusion WebUI (based on Gradio) to make development easier, optimize resource management, and speed up inference |
| 494 | kedacore/keda </br>  | KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes |
| 495 | espnet/espnet </br>  | End-to-End Speech Processing Toolkit |
| 496 | Const-me/Whisper </br>  | High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model |
| 497 | nashsu/FreeAskInternet </br>  | FreeAskInternet is a completely free, private and locally running search aggregator & answer generate using LLM, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to the ChatGPT3.5 LLM and generate the answer based on search results. |
| 498 | brexhq/prompt-engineering </br>  | Tips and tricks for working with Large Language Models like OpenAI's GPT-4. |
| 499 | lucidrains/denoising-diffusion-pytorch </br>  | Implementation of Denoising Diffusion Probabilistic Model in Pytorch |
| 500 | facebookresearch/ImageBind </br>  | ImageBind One Embedding Space to Bind Them All |
| 501 | erincatto/box2d </br>  | Box2D is a 2D physics engine for games |
| 502 | ashawkey/stable-dreamfusion </br>  | A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion. |
| 503 | open-mmlab/mmsegmentation </br>  | OpenMMLab Semantic Segmentation Toolbox and Benchmark. |
| 504 | wasp-lang/open-saas </br>  | A free, open-source SaaS app starter for React & Node.js with superpowers. Production-ready. Community-driven. |
| 505 | OptimalScale/LMFlow </br>  | An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All. |
| 506 | jxnl/instructor </br>  | structured outputs for llms |
| 507 | meetecho/janus-gateway </br>  | Janus WebRTC Server |
| 508 | LouisShark/chatgpt_system_prompt </br>  | store all agent's system prompt |
| 509 | microsoft/TypeChat </br>  | TypeChat is a library that makes it easy to build natural language interfaces using types. |
| 510 | OpenBMB/XAgent </br>  | An Autonomous LLM Agent for Complex Task Solving |
| 511 | google/magika </br>  | Detect file content types with deep learning |
| 512 | GoogleCloudPlatform/generative-ai </br>  | Sample code and notebooks for Generative AI on Google Cloud |
| 513 | anthropics/courses </br>  | Anthropic's educational courses |
| 514 | acheong08/EdgeGPT </br>  | Reverse engineered API of Microsoft's Bing Chat |
| 515 | fishaudio/Bert-VITS2 </br>  | vits2 backbone with multilingual-bert |
| 516 | anse-app/chatgpt-demo </br>  | A demo repo based on OpenAI API (gpt-3.5-turbo) |
| 517 | SJTU-IPADS/PowerInfer </br>  | High-speed Large Language Model Serving on PCs with Consumer-grade GPUs |
| 518 | marimo-team/marimo </br>  | A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git. |
| 519 | jzhang38/TinyLlama </br>  | The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens. |
| 520 | UFund-Me/Qbot </br>  | Qbot is an AI-oriented quantitative investment platform, which aims to realize the potential, empower AI technologies in quantitative investment |
| 521 | idootop/mi-gpt </br>  | ? Transform XiaoAi speaker into a personal voice assistant with ChatGPT and DouBao integration. |
| 522 | sebastianstarke/AI4Animation </br>  | Bringing Characters to Life with Computer Brains in Unity |
| 523 | goldmansachs/gs-quant </br>  | Python toolkit for quantitative finance |
| 524 | o3de/o3de </br>  | Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations. |
| 525 | leptonai/search_with_lepton </br>  | Building a quick conversation-based search demo with Lepton AI. |
| 526 | kroma-network/tachyon </br>  | Modular ZK(Zero Knowledge) backend accelerated by GPU |
| 527 | 01-ai/Yi </br>  | A series of large language models trained from scratch by developers @01-ai |
| 528 | xiangsx/gpt4free-ts </br>  | Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free |
| 529 | open-mmlab/Amphion </br>  | Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development. |
| 530 | deep-floyd/IF </br>  <a alt="Click Me" href="https://huggingface.co/spaces/DeepFloyd/IF" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> <a alt="Click Me" href="https://colab.research.google.com/drive/1AzP33O8rnMW__7ocWJhVBXjKziJXPtim?usp=sharing" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/></a> | A novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding |
| 531 | Plachtaa/VALL-E-X </br>  | An open source implementation of Microsoft's VALL-E X zero-shot TTS model. The demo is available at https://plachtaa.github.io |
| 532 | FlagOpen/FlagEmbedding </br>  | Dense Retrieval and Retrieval-augmented LLMs |
| 533 | jasonppy/VoiceCraft </br>  | Zero-Shot Speech Editing and Text-to-Speech in the Wild |
| 534 | THUDM/CodeGeeX2 </br>  | CodeGeeX2: A More Powerful Multilingual Code Generation Model |
| 535 | huggingface/chat-ui </br>  | Open source codebase powering the HuggingChat app |
| 536 | baptisteArno/typebot.io </br>  | 💬 Typebot is a powerful chatbot builder that you can self-host. |
| 537 | delta-io/delta </br>  | An open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs |
| 538 | ai-collection/ai-collection</br>  | The Generative AI Landscape - A Collection of Awesome Generative AI Applications |
| 539 | huggingface/lerobot </br>  | 🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch |
| 540 | CASIA-IVA-Lab/FastSAM </br>  | Fast Segment Anything |
| 541 | ahmedbahaaeldin/From-0-to-Research-Scientist-resources-guide </br>  | Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation. |
| 542 | sweepai/sweep </br>  | Sweep is an AI junior developer |
| 543 | abhishekkrthakur/approachingalmost </br>  | Approaching (Almost) Any Machine Learning Problem |
| 544 | netease-youdao/EmotiVoice </br>  | EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine |
| 545 | openlm-research/open_llama </br>  | OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset |
| 546 | enso-org/enso </br>  | Hybrid visual and textual functional programming. |
| 547 | lllyasviel/Omost </br>  | Your image is almost there! |
| 548 | bigcode-project/starcoder </br>  | Home of StarCoder: fine-tuning & inference! |
| 549 | dair-ai/ML-Papers-Explained </br>  | Explanation to key concepts in ML |
| 550 | openvinotoolkit/openvino </br>  | OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference |
| 551 | GreyDGL/PentestGPT</br>  | A GPT-empowered penetration testing tool |
| 552 | firmai/financial-machine-learning </br>  | A curated list of practical financial machine learning tools and applications. |
| 553 | zilliztech/GPTCache </br>  | GPTCache is a library for creating semantic cache to store responses from LLM queries. |
| 554 | reorproject/reor </br>  | AI note-taking app that runs models locally. |
| 555 | OpenBMB/MiniCPM </br>  | MiniCPM-2B: An end-side LLM outperforms Llama2-13B. |
| 556 | zmh-program/chatnio </br>  | 🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot 等模型，支持对话分享，自定义预设，云端同步，模型市场，支持弹性计费和订阅计划模式，支持图片解析，支持联网搜索，支持模型缓存，丰富美观的后台管理与仪表盘数据统计。 |
| 557 | thuml/Time-Series-Library </br>  | A Library for Advanced Deep Time Series Models. |
| 558 | ymcui/Chinese-LLaMA-Alpaca-2 </br>  | Chinese LLaMA-2 & Alpaca-2 LLMs |
| 559 | adam-maj/tiny-gpu </br>  | A minimal GPU design in Verilog to learn how GPUs work from the ground up |
| 560 | e2b-dev/e2b </br>  | Vercel for AI agents. We help developers to build, deploy, and monitor AI agents. Focusing on specialized AI agents that build software for you - your personal software developers. |
| 561 | alibaba-damo-academy/FunASR </br>  | A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models. |
| 562 | EleutherAI/lm-evaluation-harness </br>  | A framework for few-shot evaluation of autoregressive language models. |
| 563 | LiheYoung/Depth-Anything </br>  | Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data |
| 564 | Huanshere/VideoLingo </br>  | Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team |
| 565 | jina-ai/reader </br>  | Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/ |
| 566 | PWhiddy/PokemonRedExperiments </br>  | Playing Pokemon Red with Reinforcement Learning |
| 567 | apple/corenet </br>  | CoreNet: A library for training deep neural networks |
| 568 | bhaskatripathi/pdfGPT</br>  | PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The only open source solution to turn your pdf files in a chatbot! |
| 569 | Acly/krita-ai-diffusion </br>  | Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required. |
| 570 | PKU-YuanGroup/ChatLaw </br>  | Chinese Legal Large Model |
| 571 | open-mmlab/mmagic</br>  | OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox |
| 572 | git-ecosystem/git-credential-manager </br>  | Secure, cross-platform Git credential storage with authentication to GitHub, Azure Repos, and other popular Git hosting services. |
| 573 | anthropics/anthropic-cookbook </br>  | A collection of notebooks/recipes showcasing some fun and effective ways of using Claude. |
| 574 | jaywalnut310/vits </br>  | VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech |
| 575 | deepseek-ai/DeepSeek-Coder </br>  | DeepSeek Coder: Let the Code Write Itself |
| 576 | WooooDyy/LLM-Agent-Paper-List </br>  | The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al. |
| 577 | niedev/RTranslator </br>  | RTranslator is the world's first open source real-time translation app. |
| 578 | nadermx/backgroundremover </br>  | Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source. |
| 579 | AbdullahAlfaraj/Auto-Photoshop-StableDiffusion-Plugin </br>  | A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using Automatic1111-sd-webui as a backend. |
| 580 | jrouwe/JoltPhysics </br>  | A multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West. |
| 581 | IDEA-Research/GroundingDINO </br>  | Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection" |
| 582 | langchain-ai/langgraph </br>  | |
| 583 | intel-analytics/ipex-llm </br>  | Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc. |
| 584 | llmware-ai/llmware </br>  | Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models. |
| 585 | mit-han-lab/streaming-llm </br>  | Efficient Streaming Language Models with Attention Sinks |
| 586 | langfuse/langfuse </br>  | 🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management, testing, prompt playground, datasets, LLM evaluations -- 🍊YC W23 🤖 integrate via Typescript, Python / Decorators, OpenAI, Langchain, LlamaIndex, Litellm, Instructor, Mistral, Perplexity, Claude, Gemini, Vertex |
| 587 | OpenTalker/video-retalking </br>  | [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild |
| 588 | spdustin/ChatGPT-AutoExpert </br>  | 🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding). |
| 589 | getomni-ai/zerox </br>  | Zero shot pdf OCR with gpt-4o-mini |
| 590 | geekyutao/Inpaint-Anything </br>  | Inpaint anything using Segment Anything and inpainting models. |
| 591 | lencx/Noi </br>  | 🦄 AI + Tools + Plugins + Community |
| 592 | modelscope/DiffSynth-Studio </br>  | Enjoy the magic of Diffusion models! |
| 593 | react-native-webview/react-native-webview </br>  | React Native Cross-Platform WebView |
| 594 | udlbook/udlbook </br>  | Understanding Deep Learning - Simon J.D. Prince |
| 595 | bunkerity/bunkerweb </br>  | 🛡️ Make your web services secure by default ! |
| 596 | mylxsw/aidea </br>  | AIdea is a versatile app that supports GPT and domestic large language models，also supports "Stable Diffusion" text-to-image generation, image-to-image generation, SDXL 1.0, super-resolution, and image colorization |
| 597 | kuafuai/DevOpsGPT </br>  | Multi agent system for AI-driven software development. Convert natural language requirements into working software. Supports any development language and extends the existing base code. |
| 598 | gaomingqi/Track-Anything</br>  | A flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI. |
| 599 | InternLM/InternLM </br>  | InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system. |
| 600 | langchain-ai/opengpts </br>  | This is an open source effort to create a similar experience to OpenAI's GPTs and Assistants API |
| 601 | qunash/chatgpt-advanced </br>  | A browser extension that augments your ChatGPT prompts with web results. |
| 602 | jeremylong/DependencyCheck </br>  | OWASP dependency-check is a software composition analysis utility that detects publicly disclosed vulnerabilities in application dependencies. |
| 603 | openstatusHQ/openstatus </br>  | 🏓 The open-source synthetic monitoring platform 🏓 |
| 604 | Future-House/paper-qa </br>  | High accuracy RAG for answering questions from scientific documents with citations |
| 605 | Licoy/ChatGPT-Midjourney </br>  | 🎨 Own your own ChatGPT+Midjourney web service with one click |
| 606 | facebookresearch/DiT </br>  | Official PyTorch Implementation of "Scalable Diffusion Models with Transformers" |
| 607 | gunnarmorling/1brc </br>  | 1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java |
| 608 | weaviate/Verba </br>  | Retrieval Augmented Generation (RAG) chatbot powered by Weaviate |
| 609 | rany2/edge-tts </br>  | Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key |
| 610 | Azure-Samples/azure-search-openai-demo </br>  | A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. |
| 611 | linyiLYi/street-fighter-ai </br>  | This is an AI agent for Street Fighter II Champion Edition. |
| 612 | threestudio-project/threestudio </br>  | A unified framework for 3D content generation. |
| 613 | miurla/morphic </br>  | An AI-powered answer engine with a generative UI |
| 614 | Portkey-AI/gateway </br>  | A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API. |
| 615 | run-llama/rags </br>  | Build ChatGPT over your data, all with natural language |
| 616 | digitalinnovationone/dio-lab-open-source </br>  | Repositório do lab "Contribuindo em um Projeto Open Source no GitHub" da Digital Innovation One. |
| 617 | yihong0618/xiaogpt </br>  | Play ChatGPT with xiaomi ai speaker |
| 618 | jianchang512/ChatTTS-ui </br>  | 一个简单的本地网页界面，直接使用ChatTTS将文字合成为语音，同时支持对外提供API接口。 |
| 619 | ml-explore/mlx-examples </br>  | Examples in the MLX framework |
| 620 | wenda-LLM/wenda </br>  | Wenda: An LLM invocation platform. Its objective is to achieve efficient content generation tailored to specific environments while considering the limited computing resources of individuals and small businesses, as well as knowledge security and privacy concerns |
| ⭐ 621 | meshery/meshery </br>  | Meshery, the cloud native manager |
| 622 | civitai/civitai </br>  | Build a platform where people can share their stable diffusion models |
| 623 | TaskingAI/TaskingAI </br>  | The open source platform for AI-native application development. |
| 624 | aptos-labs/aptos-core </br>  | Aptos is a layer 1 blockchain built to support the widespread use of blockchain through better technology and user experience. |
| 625 | sgl-project/sglang </br>  | SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable. |
| 626 | openai/consistency_models </br>  | Official repo for consistency models. |
| 627 | PixarAnimationStudios/OpenUSD </br>  | Universal Scene Description |
| 628 | microsoft/DeepSpeedExamples </br>  | Example models using DeepSpeed |
| 629 | OpenGVLab/InternVL </br>  | [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型 |
| 630 | graviraja/MLOps-Basics </br>  | |
| 631 | rustformers/llm </br>  | Run inference for Large Language Models on CPU, with Rust |
| 632 | Moonvy/OpenPromptStudio </br>  <a alt="Click Me" href="https://moonvy.com/apps/ops/" target="_blank"><img src="https://img.shields.io/badge/Moonvy-Demo-brightgreen" alt="Open in Demo"/></a> | AIGC Hint Word Visualization Editor |
| 633 | Shaunwei/RealChar </br>  | 🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime(All in One Codebase!). Have a natural seamless conversation with AI everywhere(mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖 |
| 634 | google/gemma.cpp </br>  | lightweight, standalone C++ inference engine for Google's Gemma models. |
| 635 | HVision-NKU/StoryDiffusion </br>  | Create Magic Story! |
| 636 | k8sgpt-ai/k8sgpt </br>  | Giving Kubernetes Superpowers to everyone |
| 637 | Project-MONAI/MONAI </br>  | AI Toolkit for Healthcare Imaging |
| 638 | SevaSk/ecoute </br>  | Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation. |
| 639 | steven2358/awesome-generative-ai </br>  | A curated list of modern Generative Artificial Intelligence projects and services |
| 640 | yangjianxin1/Firefly </br>  | Firefly: Chinese conversational large language model (full-scale fine-tuning + QLoRA), supporting fine-tuning of Llma2, Llama, Baichuan, InternLM, Ziya, Bloom, and other large models |
| 641 | Tohrusky/Final2x </br>  | 2^x Image Super-Resolution |
| 642 | clovaai/donut </br>  | Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022 |
| 643 | vespa-engine/vespa </br>  | The open big data serving engine. https://vespa.ai |
| 644 | pengxiao-song/LaWGPT </br>  | Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge |
| 645 | friuns2/BlackFriday-GPTs-Prompts </br>  | List of free GPTs that doesn't require plus subscription |
| 646 | RayVentura/ShortGPT </br>  | 🚀🎬 ShortGPT - An experimental AI framework for automated short/video content creation. Enables creators to rapidly produce, manage, and deliver content using AI and automation. |
| 647 | vikhyat/moondream </br>  | tiny vision language model |
| 648 | a16z-infra/companion-app </br>  | AI companions with memory: a lightweight stack to create and host your own AI companions |
| 649 | OpenGVLab/LLaMA-Adapter</br>  | Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters |
| 650 | vladmandic/automatic </br>  | SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models |
| 651 | ramonvc/freegpt-webui </br>  | GPT 3.5/4 with a Chat Web UI. No API key is required. |
| 652 | nilsherzig/LLocalSearch </br>  | LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed. |
| 653 | nsarrazin/serge </br>  | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API |
| 654 | firebase/firebase-ios-sdk </br>  | Firebase SDK for Apple App Development |
| 655 | sczhou/ProPainter </br>  | [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting |
| 656 | baichuan-inc/baichuan-7B </br>  | A large-scale 7B pretraining language model developed by BaiChuan-Inc. |
| 657 | pytorch-labs/gpt-fast </br>  | Simple and efficient pytorch-native transformer text generation in <1000 LOC of python. |
| 658 | lightaime/camel </br>  <a alt="Click Me" href="https://colab.research.google.com/drive/1AzP33O8rnMW__7ocWJhVBXjKziJXPtim?usp=sharing" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/></a> | 🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society |
| 659 | MineDojo/Voyager </br>  | An Open-Ended Embodied Agent with Large Language Models |
| 660 | fr0gger/Awesome-GPT-Agents </br>  | A curated list of GPT agents for cybersecurity |
| 661 | HumanAIGC/OutfitAnyone </br>  | Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person |
| 662 | ethereum-optimism/optimism </br>  | Optimism is Ethereum, scaled. |
| 663 | google/mesop </br>  | |
| 664 | levihsu/OOTDiffusion </br>  | Official implementation of OOTDiffusion |
| 665 | PawanOsman/ChatGPT </br>  | OpenAI API Free Reverse Proxy |
| 666 | open-metadata/OpenMetadata </br>  | OpenMetadata is a unified platform for discovery, observability, and governance powered by a central metadata repository, in-depth lineage, and seamless team collaboration. |
| 667 | lllyasviel/IC-Light </br>  | More relighting! |
| 668 | roboflow/notebooks </br>  | Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM. |
| 669 | HariSekhon/DevOps-Bash-tools </br>  | 1000+ DevOps Bash Scripts - AWS, GCP, Kubernetes, Docker, CI/CD, APIs, SQL, PostgreSQL, MySQL, Hive, Impala, Kafka, Hadoop, Jenkins, GitHub, GitLab, BitBucket, Azure DevOps, TeamCity, Spotify, MP3, LDAP, Code/Build Linting, pkg mgmt for Linux, Mac, Python, Perl, Ruby, NodeJS, Golang, Advanced dotfiles: .bashrc, .vimrc, .gitconfig, .screenrc, tmux.. |
| 670 | yetone/bob-plugin-openai-translator </br>  | A Bob Plugin base ChatGPT API |
| 671 | enricoros/big-AGI </br>  | Generative AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. It features AI personas, AGI functions, multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud. |
| 672 | Azure/azure-sdk-for-net </br>  | This repository is for active development of the Azure SDK for .NET. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/dotnet/azure/ or our versioned developer docs at https://azure.github.io/azure-sdk-for-net. |
| 673 | lavague-ai/LaVague </br>  | Automate automation with Large Action Model framework |
| 674 | xorbitsai/inference </br>  | Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. |
| 675 | apache/hudi </br>  | Upserts, Deletes And Incremental Processing on Big Data. |
| 676 | SkalskiP/courses </br>  | This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI) |
| 677 | microsoft/promptbase </br>  | All things prompt engineering |
| 678 | Dooy/chatgpt-web-midjourney-proxy </br>  | chatgpt web, midjourney, gpts,tts, whisper 一套ui全搞定 |
| 679 | ToonCrafter/ToonCrafter </br>  | a research paper for generative cartoon interpolation |
| 680 | microsoft/TaskWeaver </br>  | A code-first agent framework for seamlessly planning and executing data analytics tasks. |
| 681 | getmaxun/maxun </br>  | 🔥 Open-source no-code web data extraction platform. Turn websites to APIs and spreadsheets with no-code robots in minutes! [In Beta] |
| 682 | homanp/superagent </br>  | 🥷 Superagent - Build, deploy, and manage LLM-powered agents |
| 683 | dsdanielpark/Bard-API </br>  | The python package that returns a response of Google Bard through API. |
| 684 | modelscope/agentscope </br>  | Start building LLM-empowered multi-agent applications in an easier way. |
| 685 | ai-boost/awesome-prompts </br>  | Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers. |
| 686 | aiwaves-cn/agents </br>  | An Open-source Framework for Autonomous Language Agents |
| 687 | PrefectHQ/marvin </br>  | A batteries-included library for building AI-powered software |
| 688 | josStorer/RWKV-Runner </br>  | A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use. |
| 689 | google/gemma_pytorch </br>  | The official PyTorch implementation of Google's Gemma models |
| 690 | fullstackhero/dotnet-starter-kit </br>  | Production Grade Cloud-Ready .NET 8 Starter Kit (Web API + Blazor Client) with Multitenancy Support, and Clean/Modular Architecture that saves roughly 200+ Development Hours! All Batteries Included. |
| 691 | imoneoi/openchat </br>  | OpenChat: Advancing Open-source Language Models with Imperfect Data |
| 692 | onuratakan/gpt-computer-assistant </br>  | gpt-4o for windows, macos and ubuntu |
| 693 | biobootloader/wolverine </br>  | Automatically repair python scripts through GPT-4 to give them regenerative abilities. |
| 694 | openchatai/OpenChat </br>  | Run and create custom ChatGPT-like bots with OpenChat, embed and share these bots anywhere, the open-source chatbot console. |
| 695 | mosaicml/composer </br>  | Train neural networks up to 7x faster |
| 696 | mnotgod96/AppAgent </br>  | AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. |
| 697 | lxfater/inpaint-web </br>  | A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。 |
| 698 | openchatai/OpenCopilot </br>  | 🤖 🔥 Let your users chat with your product features and execute things by text - open source Shopify sidekick |
| 699 | microsoft/SynapseML </br>  | Simple and Distributed Machine Learning |
| 700 | srbhr/Resume-Matcher </br>  | Open Source Free ATS Tool to compare Resumes with Job Descriptions and create a score to rank them. |
| 701 | OpenGVLab/DragGAN </br>  | Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux） |
| 702 | mpociot/chatgpt-vscode </br>  | A VSCode extension that allows you to use ChatGPT |
| 703 | Permify/permify </br>  | An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application. |
| 704 | OpenInterpreter/01 </br>  | The open-source language model computer |
| 705 | aigc-apps/sd-webui-EasyPhoto </br>  | 📷 EasyPhoto |
| 706 | frdel/agent-zero </br>  | Agent Zero AI framework |
| 707 | lvwzhen/law-cn-ai </br>  <a alt="Click Me" href="https://law-cn-ai.vercel.app/" target="_blank"><img src="https://img.shields.io/badge/Vercel-Demo-brightgreen" alt="Open in Demo"/></a> | ⚖️ AI Legal Assistant |
| 708 | alpkeskin/mosint </br>  | An automated e-mail OSINT tool |
| 709 | OpenBMB/ToolBench </br>  | An open platform for training, serving, and evaluating large language model for tool learning. |
| 710 | myshell-ai/MeloTTS </br>  | High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean. |
| 711 | ChaoningZhang/MobileSAM </br>  | This is the official code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight |
| 712 | GaiaNet-AI/gaianet-node </br>  | Install and run your own AI agent service |
| 713 | qiuyu96/CoDeF </br>  | Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing |
| ⭐ 714 | tmc/langchaingo </br>  | LangChain for Go, the easiest way to write LLM-based programs in Go |
| 715 | SuperDuperDB/superduperdb </br>  | 🔮 SuperDuperDB: Bring AI to your database: Integrate, train and manage any AI models and APIs directly with your database and your data. |
| 716 | xxlong0/Wonder3D </br>  | A cross-domain diffusion model for 3D reconstruction from a single image |
| 717 | Plachtaa/VITS-fast-fine-tuning </br>  | This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion |
| 718 | fudan-generative-vision/champ </br>  | Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance |
| 719 | microsoft/Mastering-GitHub-Copilot-for-Paired-Programming </br>  | A 6 Lesson course teaching everything you need to know about harnessing GitHub Copilot and an AI Paired Programing resource. |
| 720 | leanprover/lean4 </br>  | Lean 4 programming language and theorem prover |
| 721 | AILab-CVC/YOLO-World </br>  | Real-Time Open-Vocabulary Object Detection |
| 722 | huggingface/alignment-handbook </br>  | Robust recipes for to align language models with human and AI preferences |
| 723 | ollama/ollama-python </br>  | Ollama Python library |
| 724 | microsoft/LLMLingua </br>  | To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss. |
| 725 | developersdigest/llm-answer-engine </br>  | Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Mixtral, Langchain, OpenAI, Brave & Serper |
| 726 | Zejun-Yang/AniPortrait </br>  | AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation |
| 727 | allenai/OLMo </br>  | Modeling, training, eval, and inference code for OLMo |
| 728 | huggingface/parler-tts </br>  | Inference and training library for high-quality TTS models. |
| 729 | google-deepmind/graphcast </br>  | |
| 730 | Akegarasu/lora-scripts </br>  | LoRA training scripts use kohya-ss's trainer, for diffusion model. |
| 731 | apify/crawlee-python </br>  | Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation. |
| 732 | Deci-AI/super-gradients </br>  | Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS. |
| 733 | togethercomputer/RedPajama-Data </br>  | code for preparing large datasets for training large language models |
| 734 | SCIR-HI/Huatuo-Llama-Med-Chinese </br>  | Repo for HuaTuo (华驼), Llama-7B tuned with Chinese medical knowledge |
| 735 | AILab-CVC/VideoCrafter </br>  | VideoCrafter1: Open Diffusion Models for High-Quality Video Generation |
| 736 | facebookincubator/AITemplate </br>  | AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference. |
| 737 | EricLBuehler/mistral.rs </br>  | Blazingly fast LLM inference. |
| 738 | build-trust/ockam </br>  | Orchestrate end-to-end encryption, cryptographic identities, mutual authentication, and authorization policies between distributed applications – at massive scale. |
| 739 | terraform-aws-modules/terraform-aws-eks </br>  | Terraform module to create AWS Elastic Kubernetes (EKS) resources 🇺🇦 |
| 740 | 1rgs/jsonformer </br>  | A Bulletproof Way to Generate Structured JSON from Language Models |
| 741 | sanchit-gandhi/whisper-jax </br>  <a alt="Click Me" href="https://huggingface.co/spaces/sanchit-gandhi/whisper-jax" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | Optimised JAX code for OpenAI's Whisper Model, largely built on the Hugging Face Transformers Whisper implementation |
| 742 | madawei2699/myGPTReader </br>  | A slack bot that can read any webpage, ebook or document and summarize it with chatGPT |
| 743 | Fanghua-Yu/SUPIR </br>  | SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild |
| 744 | NVlabs/neuralangelo </br>  | Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023) |
| 745 | snakers4/silero-vad </br>  | Silero VAD: pre-trained enterprise-grade Voice Activity Detector |
| 746 | UX-Decoder/Segment-Everything-Everywhere-All-At-Once</br>  | Official implementation of the paper "Segment Everything Everywhere All at Once" |
| 747 | luosiallen/latent-consistency-model </br>  | Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference |
| 748 | Codium-ai/cover-agent </br>  | CodiumAI Cover-Agent: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞 |
| 749 | kyegomez/tree-of-thoughts </br>  <a href='https://arxiv.org/abs/2305.10601'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70% |
| 750 | sjvasquez/handwriting-synthesis </br>  | Handwriting Synthesis with RNNs ✏️ |
| 751 | pytorch/torchtune </br>  | A Native-PyTorch Library for LLM Fine-tuning |
| 752 | Nukem9/dlssg-to-fsr3 </br>  | Adds AMD FSR3 Frame Generation to games by replacing Nvidia DLSS-G Frame Generation (nvngx_dlssg). |
| 753 | modelscope/swift </br>  | ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs |
| 754 | FoundationVision/VAR </br>  | [GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction" |
| 755 | openai/plugins-quickstart </br>  | Get a ChatGPT plugin up and running in under 5 minutes! |
| 756 | asg017/sqlite-vec </br>  | Work-in-progress vector search SQLite extension that runs anywhere. |
| 757 | espeak-ng/espeak-ng </br>  | eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents. |
| 758 | OpenBMB/AgentVerse </br>  | 🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs). |
| 759 | NVIDIA/NeMo-Guardrails </br>  | NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. |
| 760 | Shubhamsaboo/awesome-llm-apps </br>  | Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models. |
| 761 | smol-ai/GodMode </br>  | AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day. |
| 762 | BuilderIO/ai-shell </br>  | A CLI that converts natural language to shell commands. |
| 763 | google-deepmind/alphageometry </br>  | Solving Olympiad Geometry without Human Demonstrations |
| 764 | Doriandarko/maestro </br>  | A framework for Claude Opus to intelligently orchestrate subagents. |
| 765 | open-compass/opencompass </br>  | OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets. |
| 766 | Facico/Chinese-Vicuna </br>  | Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model |
| 767 | microsoft/TinyTroupe </br>  | LLM-powered multiagent persona simulation for imagination enhancement and business insights. |
| 768 | ray-project/llm-numbers </br>  | Numbers every LLM developer should know |
| 769 | Blealtan/efficient-kan </br>  | An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN). |
| 770 | openai/grok </br>  | |
| 771 | Speykious/cve-rs </br>  | Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀 |
| 772 | leetcode-mafia/cheetah </br>  | Whisper & GPT-based app for passing remote SWE interviews |
| 773 | WhiskeySockets/Baileys </br>  | Lightweight full-featured typescript/javascript WhatsApp Web API |
| 774 | CrazyBoyM/llama3-Chinese-chat </br>  | Llama3 Chinese Repository with modified versions, and training and deployment resources |
| 775 | livekit/agents </br>  | Build real-time multimodal AI applications 🤖🎙️📹 |
| 776 | a16z-infra/ai-getting-started </br>  | A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs |
| 777 | damo-vilab/AnyDoor </br>  | Official implementations for paper: Anydoor: zero-shot object-level image customization |
| 778 | xlang-ai/OpenAgents </br>  | OpenAgents: An Open Platform for Language Agents in the Wild |
| 779 | PathOfBuildingCommunity/PathOfBuilding </br>  | Offline build planner for Path of Exile. |
| 780 | argilla-io/argilla </br>  | Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency. |
| 781 | keijiro/AICommand </br>  | ChatGPT integration with Unity Editor |
| 782 | collabora/WhisperSpeech </br>  | An Open Source text-to-speech system built by inverting Whisper. |
| 783 | InternLM/xtuner </br>  | An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM) |
| 784 | lipku/metahuman-stream </br>  | Real time interactive streaming digital human |
| 785 | mshumer/gpt-llm-trainer </br>  | |
| 786 | yisol/IDM-VTON </br>  | IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild |
| 787 | argmaxinc/WhisperKit </br>  | Swift native speech recognition on-device for iOS and macOS applications. |
| 788 | philz1337x/clarity-upscaler </br>  | Clarity-Upscaler: Reimagined image upscaling for everyone |
| 789 | metavoiceio/metavoice-src </br>  | AI for human-level speech intelligence |
| 790 | Significant-Gravitas/Auto-GPT-Plugins </br>  | Plugins for Auto-GPT |
| 791 | luban-agi/Awesome-AIGC-Tutorials </br>  | Curated tutorials and resources for Large Language Models, AI Painting, and more. |
| 792 | MarkFzp/mobile-aloha </br>  | Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation |
| 793 | ragapp/ragapp </br>  | The easiest way to use Agentic RAG in any enterprise |
| 794 | apple/ml-mgie </br>  | |
| 795 | facebookresearch/co-tracker </br>  | CoTracker is a model for tracking any point (pixel) on a video. |
| 796 | AutoMQ/automq </br>  | AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x cost-effective. Autoscale in seconds. Single-digit ms latency. |
| 797 | llSourcell/DoctorGPT </br>  | DoctorGPT is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private. |
| 798 | intelowlproject/IntelOwl </br>  | IntelOwl: manage your Threat Intelligence at scale |
| 799 | LLM-Red-Team/kimi-free-api </br>  | 🚀 KIMI AI 长文本大模型白嫖服务，支持高速流式输出、联网搜索、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。 |
| 800 | FlagAI-Open/FlagAI </br>  | FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model. |
| 801 | ravenscroftj/turbopilot </br>  | Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU |
| 802 | google-research/timesfm </br>  | TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. |
| 803 | shroominic/codeinterpreter-api </br>  | Open source implementation of the ChatGPT Code Interpreter 👾 |
| 804 | jackMort/ChatGPT.nvim </br>  | ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API |
| 805 | raspberrypi/pico-sdk </br>  | |
| 806 | MahmoudAshraf97/whisper-diarization </br>  | Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper |
| 807 | alibaba-damo-academy/FunClip </br>  | Open-source, accurate and easy-to-use video clipping tool, LLM based AI clipping intergrated |
| 808 | SysCV/sam-hq </br>  | Segment Anything in High Quality |
| 809 | n8n-io/self-hosted-ai-starter-kit </br>  | The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows. |
| 810 | SciPhi-AI/R2R </br>  | A framework for rapid development and deployment of production-ready RAG systems |
| 811 | hiyouga/ChatGLM-Efficient-Tuning </br>  | Fine-tuning ChatGLM-6B with PEFT |
| 812 | k2-fsa/sherpa-onnx </br>  | Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift |
| 813 | deepseek-ai/DeepSeek-V2 </br>  | |
| 814 | 0hq/WebGPT </br>  | Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~2000 lines of vanilla Javascript. |
| 815 | Codium-ai/AlphaCodium </br>  | code generation tool that surpasses most human competitors in CodeContests |
| 816 | Yue-Yang/ChatGPT-Siri </br>  | Shortcuts for Siri using ChatGPT API gpt-3.5-turbo model |
| 817 | deanxv/coze-discord-proxy </br>  | 代理Discord-Bot对话Coze-Bot，实现API形式请求GPT4对话模型/微调模型 |
| 818 | huggingface/distil-whisper </br>  | Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate. |
| 819 | fchollet/ARC-AGI </br>  | The Abstraction and Reasoning Corpus |
| 820 | Luodian/Otter </br>  | 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability. |
| 821 | ricklamers/gpt-code-ui </br>  | An open source implementation of OpenAI's ChatGPT Code interpreter |
| 822 | whoiskatrin/chart-gpt</br>  | AI tool to build charts based on text input |
| 823 | hemansnation/God-Level-Data-Science-ML-Full-Stack </br>  | A collection of scientific methods, processes, algorithms, and systems to build stories & models. This roadmap contains 16 Chapters, whether you are a fresher in the field or an experienced professional who wants to transition into Data Science & AI |
| 824 | OpenDriveLab/UniAD </br>  | [CVPR 2023 Best Paper] Planning-oriented Autonomous Driving |
| 825 | alibaba/higress </br>  | 🤖 AI Gateway |
| 826 | minimaxir/simpleaichat </br>  | Python package for easily interfacing with chat apps, with robust features and minimal code complexity. |
| 827 | e2b-dev/fragments </br>  | Open-source Next.js template for building apps that are fully generated by AI. By E2B. |
| 828 | Kent0n-Li/ChatDoctor </br>  | A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge |
| 829 | xtekky/chatgpt-clone </br>  | ChatGPT interface with better UI |
| 830 | Tencent/HunyuanDiT </br>  | Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding |
| 831 | run-llama/llama-hub </br>  | A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain |
| 832 | ostris/ai-toolkit </br>  | Various AI scripts. Mostly Stable Diffusion stuff. |
| 833 | agiresearch/AIOS </br>  | AIOS: LLM Agent Operating System |
| 834 | cvg/LightGlue </br>  | LightGlue: Local Feature Matching at Light Speed (ICCV 2023) |
| 835 | pipecat-ai/pipecat </br>  | Open Source framework for voice and multimodal conversational AI |
| 836 | nucleuscloud/neosync </br>  | Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments. |
| 837 | google/security-research </br>  | This project hosts security advisories and their accompanying proof-of-concepts related to research conducted at Google which impact non-Google owned code. |
| 838 | pytorch/torchchat </br>  | Run PyTorch LLMs locally on servers, desktop and mobile |
| 839 | iryna-kondr/scikit-llm </br>  | Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks. |
| 840 | Dataherald/dataherald </br>  | Interact with your SQL database, Natural Language to SQL using LLMs |
| 841 | BasedHardware/OpenGlass </br>  | Turn any glasses into AI-powered smart glasses |
| 842 | Netflix/maestro </br>  | Maestro: Netflix’s Workflow Orchestrator |
| 843 | truefoundry/cognita </br>  | RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry |
| 844 | spring-projects/spring-ai </br>  | An Application Framework for AI Engineering |
| 845 | NExT-GPT/NExT-GPT </br>  | Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model |
| 846 | srush/Tensor-Puzzles </br>  | Solve puzzles. Improve your pytorch. |
| 847 | pashpashpash/vault-ai </br>  | OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, etc) using a simple React frontend. |
| 848 | krishnaik06/Roadmap-To-Learn-Generative-AI-In-2024 </br>  | Roadmap To Learn Generative AI In 2024 |
| 849 | jupyterlab/jupyter-ai </br>  | A generative AI extension for JupyterLab |
| 850 | AprilNEA/ChatGPT-Admin-Web </br>  <a alt="Click Me" href="https://lmo.best" target="_blank"><img src="https://img.shields.io/badge/Lmo-Demo-brightgreen" alt="Open in Demo"/></a> | ChatGPT WebUI with user management and admin dashboard system |
| 851 | albertan017/LLM4Decompile </br>  | Reverse Engineering: Decompiling Binary Code with Large Language Models |
| 852 | dvlab-research/MiniGemini </br>  | Official implementation for Mini-Gemini |
| 853 | OpenGVLab/InternGPT </br>  | InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统) |
| 854 | ethen8181/machine-learning </br>  | 🌎 machine learning tutorials (mainly in Python3) |
| 855 | project-baize/baize-chatbot </br>  | Let ChatGPT teach your own chatbot in hours with a single GPU! |
| 856 | linyiLYi/bilibot </br>  | A local chatbot fine-tuned by bilibili user comments. |
| 857 | iusztinpaul/hands-on-llms </br>  | 🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴 |
| 858 | ai-boost/Awesome-GPTs </br>  | Curated list of awesome GPTs 👍. |
| 859 | gptscript-ai/gptscript </br>  | Natural Language Programming |
| 860 | opengeos/segment-geospatial </br>  <a alt="Click Me" href="https://colab.research.google.com/github/opengeos/segment-geospatial/blob/main/docs/examples/satellite.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/></a> | A Python package for segmenting geospatial data with the Segment Anything Model (SAM) |
| 861 | MarkFzp/act-plus-plus </br>  | Imitation Learning algorithms with Co-traing for Mobile ALOHA: ACT, Diffusion Policy, VINN |
| 862 | daveshap/OpenAI_Agent_Swarm </br>  | HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!" |
| 863 | microsoft/torchscale </br>  | Foundation Architecture for (M)LLMs |
| 864 | dnhkng/GlaDOS </br>  | This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve. |
| 865 | CVI-SZU/Linly </br>  | Chinese-LLaMA basic model; ChatFlow Chinese conversation model; NLP pre-training/command fine-tuning dataset |
| 866 | neuralmagic/deepsparse </br>  | Sparsity-aware deep learning inference runtime for CPUs |
| 867 | X-PLUG/MobileAgent </br>  | Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception |
| 868 | PKU-YuanGroup/Video-LLaVA </br>  <a alt="Click Me" href="https://huggingface.co/spaces/LanguageBind/Video-LLaVA" target="_blank"><img src="https://img.shields.io/badge/%F0%9F%A4%97-Spaces-brightgreen" alt="Open in Spaces"/></a> | Video-LLaVA: Learning United Visual Representation by Alignment Before Projection |
| 869 | hustvl/Vim </br>  | Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model |
| 870 | baichuan-inc/Baichuan-13B </br>  | A 13B large language model developed by Baichuan Intelligent Technology |
| 871 | damo-vilab/i2vgen-xl </br>  | Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models |
| 872 | williamyang1991/Rerender_A_Video </br>  | [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation |
| 873 | Azure-Samples/cognitive-services-speech-sdk </br>  | Sample code for the Microsoft Cognitive Services Speech SDK |
| 874 | adamcohenhillel/ADeus </br>  | An open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own server. You can then chat with Adeus using the app, and it will have all the right context about what you want to talk about - a truly personalized, personal AI. |
| 875 | li-plus/chatglm.cpp </br>  | C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & more LLMs |
| 876 | QwenLM/Qwen2.5-Coder </br>  | Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud. |
| 877 | gmpetrov/databerry </br>  | The no-code platform for building custom LLM Agents |
| 878 | DataTalksClub/llm-zoomcamp </br>  | LLM Zoomcamp - a free online course about building an AI bot that can answer questions about your knowledge base |
| 879 | huggingface/safetensors </br>  | Simple, safe way to store and distribute tensors |
| 880 | unit-mesh/auto-dev </br>  | 🧙AutoDev: The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀 |
| 881 | iree-org/iree </br>  | A retargetable MLIR-based machine learning compiler and runtime toolkit. |
| 882 | eureka-research/Eureka </br>  | Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" |
| 883 | cohere-ai/cohere-toolkit </br>  | Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications. |
| 884 | facebookresearch/ijepa </br>  | Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture." |
| 885 | salesforce/CodeT5 </br>  | Home of CodeT5: Open Code LLMs for Code Understanding and Generation |
| 886 | muellerberndt/mini-agi </br>  | A minimal generic autonomous agent based on GPT3.5/4. Can analyze stock prices, perform network security tests, create art, and order pizza. |
| 887 | SamurAIGPT/privateGPT </br>  | An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks |
| 888 | Marker-Inc-Korea/AutoRAG </br>  | AutoML tool for RAG |
| 889 | Ironclad/rivet </br>  <a alt="Click Me" href="https://rivet.ironcladapp.com/" target="_blank"><img src="https://img.shields.io/badge/Rivet-Website-brightgreen" alt="Open Website"/></a> | The open-source visual AI programming environment and TypeScript library |
| 890 | NVIDIA/trt-llm-rag-windows </br>  | A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM |
| 891 | rashadphz/farfalle </br>  | 🔍 AI search engine - self-host with local or cloud LLMs |
| 892 | CanadaHonk/porffor </br>  | A from-scratch experimental AOT JS engine, written in JS |
| 893 | NVIDIA/garak </br>  | the LLM vulnerability scanner |
| 894 | meta-llama/PurpleLlama </br>  | Set of tools to assess and improve LLM security. |
| 895 | Stability-AI/stable-audio-tools </br>  | Generative models for conditional audio generation |
| 896 | nus-apr/auto-code-rover </br>  | A project structure aware autonomous software engineer aiming for autonomous program improvement |
| 897 | Alpha-VLLM/LLaMA2-Accessory </br>  | An Open-source Toolkit for LLM Development |
| 898 | cvlab-columbia/zero123 </br>  | Zero-1-to-3: Zero-shot One Image to 3D Object: https://zero123.cs.columbia.edu/ |
| 899 | hegelai/prompttools </br>  | Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate). |
| 900 | SCUTlihaoyu/open-chat-video-editor </br>  | Open source short video automatic generation tool |
| 901 | facebookresearch/audio2photoreal </br>  | Code and dataset for photorealistic Codec Avatars driven from audio |
| 902 | OpenBMB/CPM-Bee </br>  | A bilingual large-scale model with trillions of parameters |
| 903 | Azure/azure-rest-api-specs </br>  | The source for REST API specifications for Microsoft Azure. |
| 904 | facebookresearch/jepa </br>  | PyTorch code and models for V-JEPA self-supervised learning from video. |
| 905 | facebookresearch/Pearl </br>  | A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta. |
| 906 | mazzzystar/Queryable </br>  | Run CLIP on iPhone to Search Photos. |
| 907 | facebookresearch/habitat-sim </br>  | A flexible, high-performance 3D simulator for Embodied AI research. |
| 908 | ToTheBeginning/PuLID </br>  | Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment |
| 909 | sugarforever/chat-ollama </br>  | ChatOllama is an open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management. |
| 910 | leptonai/leptonai </br>  | A Pythonic framework to simplify AI service building |
| 911 | Josh-XT/AGiXT </br>  | AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions. |
| 912 | ishan0102/vimGPT </br>  | Browse the web with GPT-4V and Vimium |
| 913 | billmei/every-chatgpt-gui </br>  | Every front-end GUI client for ChatGPT |
| 914 | pytorch/torchtitan </br>  | A native PyTorch Library for large model training |
| 915 | gptlink/gptlink </br>  | Build your own free commercial ChatGPT environment in 10 minutes. The setup is simple and includes features such as user management, orders, tasks, and payments |
| 916 | georgia-tech-db/eva </br>  | AI-Relational Database System |
| 917 | src-d/hercules </br>  | Gaining advanced insights from Git repository history. |
| 918 | johnma2006/mamba-minimal </br>  | Simple, minimal implementation of the Mamba SSM in one file of PyTorch. |
| 919 | xenova/whisper-web </br>  | ML-powered speech recognition directly in your browser |
| 920 | Doubiiu/DynamiCrafter </br>  | DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors |
| 921 | amazon-science/chronos-forecasting </br>  | Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting |
| 922 | FranxYao/chain-of-thought-hub </br>  | Benchmarking large language models' complex reasoning ability with chain-of-thought prompting |
| 923 | kubernetes-sigs/controller-runtime </br>  | Repo for the controller-runtime subproject of kubebuilder (sig-apimachinery) |
| 924 | liou666/polyglot </br>  | Desktop AI Language Practice Application |
| 925 | SuperTux/supertux </br>  | SuperTux source code |
| 926 | neo4j-labs/llm-graph-builder </br>  | Neo4j graph construction from unstructured data using LLMs |
| 927 | baaivision/Painter </br>  | Painter & SegGPT Series: Vision Foundation Models from BAAI |
| 928 | jqnatividad/qsv </br>  | CSVs sliced, diced & analyzed. |
| 929 | lamini-ai/lamini </br>  | Official repo for Lamini's data generator for generating instructions to train instruction-following LLMs |
| 930 | databricks/dbrx </br>  | Code examples and resources for DBRX, a large language model developed by Databricks |
| 931 | microsoft/Phi-3CookBook </br>  | This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks. |
| 932 | OpenPipe/OpenPipe </br>  | Turn expensive prompts into cheap fine-tuned models |
| 933 | Lightning-AI/LitServe </br>  | Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale. |
| 934 | Zipstack/unstract </br>  | No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents |
| 935 | abi/secret-llama </br>  | Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3. |
| 936 | google-deepmind/gemma </br>  | Open weights LLM from Google DeepMind. |
| 937 | elastic/otel-profiling-agent </br>  | The production-scale datacenter profiler |
| 938 | mshumer/gpt-author </br>  | |
| 939 | microsoft/promptbench </br>  | A unified evaluation framework for large language models |
| 940 | NVIDIA/GenerativeAIExamples </br>  | Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture. |
| 941 | TMElyralab/MuseV </br>  | MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising |
| 942 | CodingChallengesFYI/SharedSolutions </br>  | Publicly shared solutions to Coding Challenges |
| 943 | kevmo314/magic-copy </br>  | Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard. |
| 944 | TracecatHQ/tracecat </br>  | 😼 The AI-native, open source alternative to Tines / Splunk SOAR. |
| 945 | mishushakov/llm-scraper </br>  | Turn any webpage into structured data using LLMs |
| 946 | tencentmusic/supersonic </br>  | SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms. |
| 947 | MrForExample/ComfyUI-3D-Pack </br>  | An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.) |
| 948 | paulpierre/RasaGPT </br>  | 💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram |
| 949 | girafe-ai/ml-course </br>  | Open Machine Learning course |
| 950 | LLMBook-zh/LLMBook-zh.github.io </br>  | 《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣 |
| 951 | SoraWebui/SoraWebui </br>  | SoraWebui is an open-source Sora web client, enabling users to easily create videos from text with OpenAI's Sora model. |
| 952 | dvmazur/mixtral-offloading </br>  | Run Mixtral-8x7B models in Colab or consumer desktops |
| 953 | MervinPraison/PraisonAI </br>  | PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration. |
| 954 | TMElyralab/MusePose </br>  | MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation |
| 955 | isaac-sim/IsaacLab </br>  | Unified framework for robot learning built on NVIDIA Isaac Sim |
| 956 | IDEA-Research/T-Rex </br>  | T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy |
| 957 | tencent-ailab/V-Express </br>  | V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images. |
| 958 | nerfstudio-project/gsplat </br>  | CUDA accelerated rasterization of gaussian splatting |
| 959 | mshumer/gpt-investor </br>  | |
| 960 | aixcoder-plugin/aiXcoder-7B </br>  | official repository of aiXcoder-7B Code Large Language Model |
| 961 | Eladlev/AutoPrompt </br>  | A framework for prompt tuning using Intent-based Prompt Calibration |
| 962 | pytorch/executorch </br>  | On-device AI across mobile, embedded and edge for PyTorch |
| 963 | emcf/engshell </br>  | An English-language shell for any OS, powered by LLMs |
| 964 | ashishpatel26/LLM-Finetuning </br>  | LLM Finetuning with peft |
| 965 | lanqian528/chat2api </br>  | A service that can convert ChatGPT on the web to OpenAI API format. |
| 966 | JiauZhang/DragGAN </br>  <a href='https://arxiv.org/abs/2305.10973'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> | Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold |
| 967 | semanser/codel </br>  | ✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor. |
| 968 | openai/consistencydecoder </br>  | Consistency Distilled Diff VAE |
| 969 | janhq/nitro </br>  | A fast, lightweight, embeddable inference engine to supercharge your apps with local AI. OpenAI-compatible API |
| 970 | THUDM/CogVLM2 </br>  | GPT4V-level open-source multi-modal model based on Llama3-8B |
| 971 | hncboy/chatgpt-web-java </br>  | ChatGPT project developed in Java, based on Spring Boot 3 and JDK 17, supports both AccessToken and ApiKey modes |
| 972 | Kludex/fastapi-tips </br>  | FastAPI Tips by The FastAPI Expert! |
| 973 | luijait/DarkGPT </br>  | DarkGPT is an OSINT assistant based on GPT-4-200K (recommended use) designed to perform queries on leaked databases, thus providing an artificial intelligence assistant that can be useful in your traditional OSINT processes. |
| 974 | cgpotts/cs224u </br>  | Code for Stanford CS224u |
| 975 | 6drf21e/ChatTTS_colab </br>  | 🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。 |
| 976 | deepseek-ai/DeepSeek-VL </br>  | DeepSeek-VL: Towards Real-World Vision-Language Understanding |
| 977 | Alpha-VLLM/Lumina-T2X </br>  | Lumina-T2X is a unified framework for Text to Any Modality Generation |
| 978 | timescale/pgai </br>  | A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL |
| 979 | mlabonne/llm-datasets </br>  | High-quality datasets, tools, and concepts for LLM fine-tuning. |
| 980 | AI-Citizen/SolidGPT </br>  | Chat everything with your code repository, ask repository level code questions, and discuss your requirements. AI Scan and learning your code repository, provide you code repository level answer🧱 🧱 |
| 981 | princeton-nlp/SWE-bench </br>  | [ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues? |
| 982 | NVlabs/VILA </br>  | VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops) |
| 983 | PKU-YuanGroup/MoE-LLaVA </br>  | Mixture-of-Experts for Large Vision-Language Models |
| 984 | iterative/datachain </br>  | AI-data warehouse to enrich, transform and analyze data from cloud storages |
| 985 | microsoft/genaiscript </br>  | Automatable GenAI Scripting |
| 986 | PRIS-CV/DemoFusion </br>  | Let us democratise high-resolution generation! (arXiv 2023) |
| 987 | openai/simple-evals </br>  | |
| 988 | liltom-eth/llama2-webui </br>  | Run Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Supporting Llama-2-7B/13B/70B with 8-bit, 4-bit. Supporting GPU inference (6 GB VRAM) and CPU inference. |
| 989 | microsoft/aici </br>  | AICI: Prompts as (Wasm) Programs |
| 990 | ai16z/eliza </br>  | Conversational Agent for Twitter and Discord |
| 991 | Azure/PyRIT </br>  | The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems. |
| 992 | Yonom/assistant-ui </br>  | React Components for AI Chat 💬 🚀 |
| 993 | Niek/chatgpt-web </br>  | ChatGPT web interface using the OpenAI API |
| 994 | Azure-Samples/graphrag-accelerator </br>  | One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure |
| 995 | apple/axlearn </br>  | An Extensible Deep Learning Library |
| 996 | BAAI-Agents/Cradle </br>  | The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements. |
| 997 | darrenburns/elia </br>  | A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more. |
| 998 | NVIDIA/gpu-operator </br>  | NVIDIA GPU Operator creates/configures/manages GPUs atop Kubernetes |
| ⭐ 999 | awslabs/multi-agent-orchestrator </br>  | Flexible and powerful framework for managing multiple AI agents and handling complex conversations |
| 1000 | bghira/SimpleTuner </br>  | A general fine-tuning kit geared toward Stable Diffusion 2.1, Stable Diffusion 3, DeepFloyd, and SDXL. |
| 1001 | flowtyone/flowty-realtime-lcm-canvas </br>  | A realtime sketch to image demo using LCM and the gradio library. |
| 1002 | idaholab/moose </br>  | Multiphysics Object Oriented Simulation Environment |
| 1003 | ytongbai/LVM </br>  | Sequential Modeling Enables Scalable Learning for Large Vision Models |
| 1004 | Nutlope/notesGPT </br>  | Record voice notes & transcribe, summarize, and get tasks |
| 1005 | ymcui/Chinese-LLaMA-Alpaca-3 </br>  | 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3 |
| 1006 | YangLing0818/RPG-DiffusionMaster </br>  | Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG) |
| 1007 | kyegomez/BitNet </br>  | Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch |
| 1008 | huggingface/cookbook </br>  | Open-source AI cookbook |
| 1009 | InstantStyle/InstantStyle </br>  | InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥 |
| 1010 | AI4Finance-Foundation/FinRobot </br>  | FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀 |
| 1011 | flowdriveai/flowpilot </br>  | flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines. |
| 1012 | baaivision/Emu </br>  | Emu Series: Generative Multimodal Models from BAAI |
| 1013 | GaParmar/img2img-turbo </br>  | One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more |
| 1014 | microsoft/sample-app-aoai-chatGPT </br>  | [PREVIEW] Sample code for a simple web chat experience targeting chatGPT through AOAI. |
| 1015 | linyiLYi/snake-ai </br>  | An AI agent that beats the classic game "Snake". |
| 1016 | The-OpenROAD-Project/OpenROAD </br>  | OpenROAD's unified application implementing an RTL-to-GDS Flow. Documentation at https://openroad.readthedocs.io/en/latest/ |
| 1017 | pytorch/ao </br>  | PyTorch native quantization and sparsity for training and inference |
| 1018 | eloialonso/diamond </br>  | DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. |
| 1019 | collabora/WhisperFusion </br>  | WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI. |
| 1020 | google/maxtext </br>  | A simple, performant and scalable Jax LLM! |
| 1021 | GoogleCloudPlatform/localllm </br>  | Run LLMs locally on Cloud Workstations |
| 1022 | lichao-sun/Mora </br>  | Mora: More like Sora for Generalist Video Generation |
| 1023 | TencentARC/BrushNet </br>  | The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion" |
| 1024 | AnswerDotAI/fsdp_qlora </br>  | Training LLMs with QLoRA + FSDP |
| 1025 | andrewnguonly/Lumos </br>  | A RAG LLM co-pilot for browsing the web, powered by local LLMs |
| 1026 | SharifiZarchi/Introduction_to_Machine_Learning </br>  | دورهی مقدمهای بر یادگیری ماشین، برای دانشجویان |
| 1027 | xlang-ai/OSWorld </br>  | OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments |
| 1028 | TeamNewPipe/NewPipeExtractor </br>  | NewPipe's core library for extracting data from streaming sites |
| 1029 | mhamilton723/FeatUp </br>  | Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024 |
| 1030 | McGill-NLP/webllama </br>  | Llama-3 agents that can browse the web by following instructions and talking to you |
| 1031 | elastic/elasticsearch </br>  | Free and Open, Distributed, RESTful Search Engine |
| 1032 | naver/mast3r </br>  | Grounding Image Matching in 3D with MASt3R |
| 1033 | jgravelle/AutoGroq </br>  | |
| 1034 | lucidrains/self-rewarding-lm-pytorch </br>  | Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI |
| 1035 | landing-ai/vision-agent </br>  | Vision agent |
| 1036 | OpenGenerativeAI/llm-colosseum </br>  | Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM |
| 1037 | PKU-YuanGroup/MagicTime </br>  | MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators |
| 1038 | ishaan1013/sandbox </br>  | A cloud-based code editing environment with an AI copilot and real-time collaboration. |
| 1039 | a-real-ai/pywinassistant </br>  | The first open source Large Action Model generalist Artificial Narrow Intelligence that controls completely human user interfaces by only using natural language. PyWinAssistant utilizes Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models. |
| 1040 | goatcorp/Dalamud </br>  | FFXIV plugin framework and API |
| 1041 | SakanaAI/evolutionary-model-merge </br>  | Official repository of Evolutionary Optimization of Model Merging Recipes |
| 1042 | microsoft/vscode-ai-toolkit </br>  | |
| 1043 | olimorris/codecompanion.nvim </br>  | ✨ AI-powered coding, seamlessly in Neovim. Supports Anthropic, Copilot, Gemini, Ollama, OpenAI and xAI LLMs |
| 1044 | Lightning-AI/lightning-thunder </br>  | Make PyTorch models Lightning fast! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once. |
| 1045 | TraceMachina/nativelink </br>  | NativeLink is an open source high-performance build cache and remote execution server, compatible with Bazel, Buck2, Reclient, and other RBE-compatible build systems. It offers drastically faster builds, reduced test flakiness, and significant infrastructure cost savings. |
| 1046 | microsoft/RD-Agent </br>  | Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automate these high-value generic R&D processes through our open source R&D automation tool RD-Agent, which let AI drive data-driven AI. |
| 1047 | elfvingralf/macOSpilot-ai-assistant </br>  | Voice + Vision powered AI assistant that answers questions about any application, in context and in audio. |
| 1048 | MLSysOps/MLE-agent </br>  | 🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Ollama, etc supported. 🎆 Code RAG |
| 1049 | FoundationVision/GLEE </br>  | 【CVPR2024】GLEE: General Object Foundation Model for Images and Videos at Scale |
| 1050 | wpilibsuite/allwpilib </br>  | Official Repository of WPILibJ and WPILibC |
| 1051 | Profluent-AI/OpenCRISPR </br>  | AI-generated gene editing systems |
| 1052 | langchain-ai/langchain-extract </br>  | 🦜⛏️ Did you say you like data? |
| 1053 | ml-explore/mlx-swift-examples </br>  | Examples using MLX Swift |
| 1054 | PaddlePaddle/PaddleHelix </br>  | Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集 |
| 1055 | likejazz/llama3.np </br>  | llama3.np is pure NumPy implementation for Llama 3 model. |
| 1056 | myshell-ai/JetMoE </br>  | Reaching LLaMA2 Performance with 0.1M Dollars |
| 1057 | mustafaaljadery/gemma-2B-10M </br>  | Gemma 2B with 10M context length using Infini-attention. |
