Hot on Github: Top Trending Projects of 04/14/2023 — Exclusively Fresh Finds!
Projects that have already appeared in previous Github ranking lists will not display details, please refer to previous lists for information.
Rank #1 openai/consistency_models
https://github.com/openai/consistency_models
Official repo for consistency models.
Language: Python
Stars: 3,452(969 stars today) Forks:180
The Consistency Models project is a repository containing code for conducting large-scale experiments on ImageNet-64, LSUN Bedroom-256, and LSUN Cat-256 using PyTorch. The project is based on the openai/guided-diffusion repository and has been modified to support consistency distillation, consistency training, as well as several sampling and editing algorithms discussed in the paper. The project also provides pre-trained models for ImageNet-64, LSUN Bedroom-256, and LSUN Cat-256, which can be downloaded from the links provided. The intended use and limitations of these models are described in the corresponding model card. The project requires several dependencies, which can be installed by running “pip install -e .” The project also provides examples of model training and sampling, including EDM training, consistency distillation, consistency training, single-step generation, and multistep generation. The project evaluates different generative models using FID, Precision, Recall, and Inception Score, which can be calculated using batches of samples stored in numpy files. This project can be applied in fields such as computer vision and artificial intelligence and has commercial applications in areas such as image and video generation, data augmentation, and content creation.
— — — — — — — — — — — — — — — —
Rank #2 microsoft/DeepSpeed
https://github.com/microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Language: Python
Stars: 18,274(3,613 stars today) Forks:2,118
— — — — — — — — — — — — — — — —
Rank #3 Torantulino/Auto-GPT
https://github.com/Torantulino/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
Language: Python
Stars: 58,033(13,534 stars today) Forks:7,997
— — — — — — — — — — — — — — — —
Rank #4 reworkd/AgentGPT
https://github.com/reworkd/AgentGPT
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
Language: TypeScript
Stars: 9,984(3,265 stars today) Forks:2,017
— — — — — — — — — — — — — — — —
Rank #5 databrickslabs/dolly
https://github.com/databrickslabs/dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Language: Python
Stars: 6,735(1,010 stars today) Forks:647
— — — — — — — — — — — — — — — —
Rank #6 microsoft/DeepSpeedExamples
https://github.com/microsoft/DeepSpeedExamples
Example models using DeepSpeed
Language: Python
Stars: 2,296(707 stars today) Forks:386
— — — — — — — — — — — — — — — —
Rank #7 biobootloader/wolverine
https://github.com/biobootloader/wolverine
Language: Python
Stars: 3,334(743 stars today) Forks:336
— — — — — — — — — — — — — — — —
Rank #8 ohmplatform/FreedomGPT
https://github.com/ohmplatform/FreedomGPT
This codebase is for a React and Electron-based app that executes the FreedomGPT LLM locally (offline and private) on Mac and Windows using a chat-based interface (based on Alpaca Lora)
Language: TypeScript
Stars: 901(194 stars today) Forks:94
— — — — — — — — — — — — — — — —
Rank #9 alexrozanski/LlamaChat
https://github.com/alexrozanski/LlamaChat
Chat with your favourite LLaMA models in a native macOS app
Language: Swift
Stars: 457(77 stars today) Forks:14
LlamaChat is a macOS application that allows users to chat with LLaMa, Alpaca, and GPT4All models running locally on their Mac. The app supports adding LLaMA models in either their raw PyTorch checkpoint form or the .ggml format. LlamaChat is built on top of llama.cpp and llama.swift, which allow for flexible model formats and model conversion. Chat history is persisted within the app, and funky avatars and playful names can be used for chat sources. The current model context can be viewed for a chat in the info popover. LlamaChat can be applied in fields such as natural language processing, machine learning, and artificial intelligence. Commercial applications of LlamaChat include chatbots for customer service, language translation, and intelligent personal assistants. Please note that LlamaChat does not ship with any model files and requires users to obtain these from the respective sources in accordance with their respective terms and conditions.
— — — — — — — — — — — — — — — —
Rank #10 ravenscroftj/turbopilot
https://github.com/ravenscroftj/turbopilot
Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU
Language: Python
Stars: 2,653(537 stars today) Forks:80
— — — — — — — — — — — — — — — —
Rank #11 NVIDIAGameWorks/rtx-remix
https://github.com/NVIDIAGameWorks/rtx-remix
Combined repo for the RTX-Remix runtime
Language:
Stars: Star(177 stars today) Forks:14
RTX-Remix is a runtime engine that adds path-tracing to classic games. The runtime is composed of multiple technologies, each with its own git repo, and this combined repo references those technologies via submodules. The runtime engine can be applied in fields such as computer graphics and game development. The project provides a user guide, development roadmap, and important links such as the Wiki and Releases pages. Contributions should be directed towards the individual technology repos, and contributions accepted to any of the submodules will eventually make it into a release. The project is supported through the RTX Remix Showcase discord channel. Commercial applications of RTX-Remix include game remastering, game design, and virtual reality experiences. The project is particularly useful for developers who want to create modern graphics in classic games.
— — — — — — — — — — — — — — — —
Rank #12 daveshap/REMO_Framework
https://github.com/daveshap/REMO_Framework
Rolling Episodic Memory Organizer (REMO) for autonomous AI systems
Language: Python
Stars: 171(35 stars today) Forks:25
REMO (Rolling Episodic Memory Organizer) is a microservice that organizes large volumes of text data, such as chat logs, into a hierarchical taxonomy. The microservice is designed to assist AI systems in recalling relevant information and maintaining context. The taxonomy is constructed using summaries of message pairs and message clusters, allowing users to easily search and navigate through the conversation history. REMO utilizes the Universal Sentence Encoder for generating embeddings and clustering algorithms for organizing the data. The microservice is built using FastAPI, providing a simple and easy-to-use RESTful API. REMO can be applied in fields such as natural language processing, machine learning, and artificial intelligence. Commercial applications of REMO include chatbots for customer service, intelligent personal assistants, and virtual assistants. The project is particularly useful for developers who want to improve conversational capabilities and recall accuracy in AI systems. Please note that this code is still in early alpha, and testing and bugs should be expected.
— — — — — — — — — — — — — — — —
Rank #13 shadcn/taxonomy
https://github.com/shadcn/taxonomy
An open source application built using the new router, server components and everything new in Next.js 13.
Language: TypeScript
Stars: 7,912(288 stars today) Forks:733
— — — — — — — — — — — — — — — —
Rank #14 ConnectAI-E/Feishu-OpenAI
https://github.com/ConnectAI-E/Feishu-OpenAI
🎒飞书 ×（GPT-3.5 + DALL·E + Whisper）= 飞一般的工作体验 🚀 语音对话、角色扮演、多话题讨论、图片创作、表格分析、文档导出 🚀
Language: Go
Stars: 3,489(137 stars today) Forks:562
The Feishu OpenAI project is a chatbot powered by GPT-3.5, DALL·E, and Whisper, designed to assist users in natural language conversations. The project includes a team of designers, frontend and backend developers, algorithm experts, and testers, aiming to provide AI-powered solutions for enterprise-level scenarios. The chatbot supports voice communication, multi-topic conversations, text-to-image conversion, role-playing, and AI modes. The project is built using OpenAI’s GPT-3.5 turbo interface and integrated with Feishu and Feishu International. The chatbot can be deployed through various channels, including serverless cloud functions, local environments, Docker, and binary installation packages. The project can be applied in fields such as natural language processing, machine learning, and artificial intelligence. Commercial applications of the Feishu OpenAI project include chatbots for customer service, intelligent personal assistants, and virtual assistants. The project is particularly useful for developers who want to improve conversational capabilities and provide personalized solutions for enterprise-level scenarios.
— — — — — — — — — — — — — — — —
Rank #15 kevmo314/magic-copy
https://github.com/kevmo314/magic-copy
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.
Language: TypeScript
Stars: 1,185(394 stars today) Forks:54
— — — — — — — — — — — — — — — —
Rank #16 HalseySpicy/Geeker-Admin
https://github.com/HalseySpicy/Geeker-Admin
✨✨✨ Geeker Admin，基于 Vue3.2、TypeScript、Vite3、Pinia、Element-Plus 开源的一套后台管理框架。
Language: Vue
Stars: 3,715(19 stars today) Forks:732
Geeker-Admin is an open-source backend management framework based on Vue3.2, TypeScript, Vite3, Pinia, and Element-Plus. It is developed using the latest technology stack and provides powerful features such as ProTable components, common components, Hooks, directives, dynamic routing, and button-level permission control. The project is useful for developers who want to build backend management systems quickly and efficiently. It can be applied in fields such as web development, software development, and enterprise-level scenarios. Commercial applications of Geeker-Admin include building backend management systems for businesses, organizations, and government agencies. The project is available on Gitee and GitHub and comes with a comprehensive documentation guide. It supports various features such as Element component size switching, dark mode, and internationalization. The project is built using Vue3.2 and TypeScript, and it uses Vite3 as its development and packaging tool. It also includes Pinia to replace Vuex and Axios for network requests. The project has a user-friendly interface and provides a seamless experience for developers.
— — — — — — — — — — — — — — — —
Rank #17 NVIDIAGameWorks/dxvk-remix
https://github.com/NVIDIAGameWorks/dxvk-remix
Language: C++
Stars: 83(20 stars today) Forks:8
RTX Remix is a software project that provides a set of tools for building and deploying DXVK-based Vulkan libraries for Windows operating systems. It requires Windows 10 or 11, Visual Studio, Windows SDK, Meson, Vulkan SDK, and Python. The project can be used in fields such as game development, 3D modeling, and computer graphics. Commercial applications of RTX Remix include building and deploying DXVK-based Vulkan libraries for games, virtual reality applications, and other graphics-intensive software. The project provides a comprehensive guide on how to generate and build dxvk-remix project in Visual Studio, and how to deploy built binaries to a game. The project is designed to improve the performance of graphics-intensive applications by providing faster runtime and better instrumentation. The project is available on GitHub and comes with detailed instructions on how to install and use it. It is useful for developers who want to improve the performance of their applications and provide better graphics for their users.
— — — — — — — — — — — — — — — —
Rank #18 toeverything/AFFiNE
https://github.com/toeverything/AFFiNE
There can be more than Notion and Miro. AFFiNE is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.
Language: TypeScript
Stars: 14,703(174 stars today) Forks:718
AFFiNE.PRO is a next-generation knowledge base that combines planning, sorting, and creating all in one platform. It is an open-source, customizable, and privacy-first platform that is designed to be a free replacement for Notion & Miro. The project can be applied in fields such as project management, team collaboration, and personal organization. Commercial applications of AFFiNE.PRO include building knowledge bases for businesses, organizations, and educational institutions. The platform provides a comprehensive set of tools for creating, organizing, and sharing information, including hyper-merged docs, canvas, and tables. The project is available on GitHub and comes with detailed instructions on how to install and use it. It is useful for developers who want to build knowledge bases for their teams or clients and for individuals who want to organize their personal information. The project is still under active development and is not yet ready for production use.
— — — — — — — — — — — — — — — —
Rank #19 DataTalksClub/mlops-zoomcamp
https://github.com/DataTalksClub/mlops-zoomcamp
Free MLOps course from DataTalks.Club
Language: Jupyter Notebook
Stars: 5,380(20 stars today) Forks:1,002
MLOps Zoomcamp is a course that teaches practical aspects of productionizing machine learning (ML) services, from training and experimenting to model deployment and monitoring. The course is designed for data scientists, ML engineers, software engineers, and data engineers interested in learning about putting ML in production. The course covers topics such as MLOps maturity model, experiment tracking and model management, building and deploying ML models, and monitoring and troubleshooting. The course materials are freely available, and participants can take the course at their own pace. The course requires prior exposure to machine learning, programming experience, and familiarity with Python and Docker. The project provides a comprehensive syllabus with recommended readings and homework assignments. The course is useful for developers who want to build ML applications and services and for businesses that want to implement ML in their operations. The project is available on GitHub, and participants can join the DataTalks.Club’s Slack community for support and discussions.
— — — — — — — — — — — — — — — —
Rank #20 diego3g/rsxp-2023
https://github.com/diego3g/rsxp-2023
Repositório contendo o código do app do RS/XP 2023
Language: TypeScript
Stars: 377(7 stars today) Forks:78
Rocketseat Experience 2023 — Mobile App is a community-built app for the largest programming event in Brazil, the RS/XP. The app is built using React Native and Expo, and its back-end is built using Node.js, NestJS, Prisma, and PostgreSQL. The app provides information about the event, including schedules, speakers, and sponsors, and allows attendees to interact with each other and participate in activities. The project is useful for event organizers who want to provide a mobile app for their attendees and for developers who want to learn about building mobile apps using React Native and Expo. The project is available on GitHub, and the community provides detailed instructions on how to run the project on your machine. The project uses TypeScript, NativeWind, and Tailwind for styling, and it is recommended to use Docker to run the PostgreSQL database. The project is a good example of how to build a mobile app using React Native and Expo and how to integrate it with a back-end built using Node.js and Prisma.
— — — — — — — — — — — — — — — —
Rank #21 agiresearch/OpenAGI
https://github.com/agiresearch/OpenAGI
OpenAGI: When LLM Meets Domain Experts (an open-source AGI research, development and testing platform)
Language: Jupyter Notebook
Stars: 790(219 stars today) Forks:42
— — — — — — — — — — — — — — — —
Rank #22 skills/introduction-to-github
https://github.com/skills/introduction-to-github
Get started using GitHub in less than an hour.
Language:
Stars: Star(20 stars today) Forks:902
Introduction to GitHub is a course designed to help new developers, new GitHub users, and students get started with GitHub in less than an hour. The course covers the basics of GitHub, including repositories, branches, commits, and pull requests. The course is four steps long and takes less than one hour to complete. The course provides step-by-step instructions on how to create a new repository, create a branch, make a commit, and create a pull request. The course also includes a short Markdown file that participants can use as their profile README. The project is useful for anyone who wants to learn how to use GitHub for version control, collaboration, and open-source software development. The project is available on GitHub, and participants can follow the instructions to create their own repository and practice using GitHub. The project has commercial applications for businesses that want to use GitHub for software development and collaboration. It is a good starting point for new developers who want to learn how to use GitHub and become part of the GitHub community.
— — — — — — — — — — — — — — — —
Rank #23 eumemic/ai-legion
https://github.com/eumemic/ai-legion
An LLM-powered autonomous agent platform
Language: TypeScript
Stars: 668(216 stars today) Forks:69
— — — — — — — — — — — — — — — —
Rank #24 oobabooga/text-generation-webui
https://github.com/oobabooga/text-generation-webui
A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, Pythia, OPT, and GALACTICA.
Language: Python
Stars: 8,694(351 stars today) Forks:810
— — — — — — — — — — — — — — — —
Rank #25 fudan-zvg/Semantic-Segment-Anything
https://github.com/fudan-zvg/Semantic-Segment-Anything
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
Language: Python
Stars: 625(220 stars today) Forks:26
— — — — — — — — — — — — — — — —
