AI Tools & Frameworks
Tools, frameworks and libraries for AI development and applications
A stable diffusion web interface, developed based on the grado library, provides a friendly browser interface for users to visualize and operate the stable diffusion model conveniently.
An advanced natural language processing model library built for Jax, PyTorch and TensorFlow. It provides a rich set of pre-trained models and tools to help users achieve better results and performance in natural language processing tasks.
A development tool for creating powerful AI applications, it provides APIs for plugins and datasets, as well as an interface for quick engineering and visualization operations. For developers and researchers who want to develop applications, Dify provides convenient tools and interfaces to help them build feature-rich AI applications.
A powerful and modular GUI and graphics/node interface that provides stable and scalable user interface components. The design of this project focuses on customization and usability, enabling developers to quickly build beautiful and feature-rich graphical user interface applications.
🤖 An open-source, high-performance chatbot framework that supports voice synthesis, multimodal and scalable function call plugin systems. Users can deploy private ChatGPT/LLM web applications with one click for free, providing powerful chatbot features for projects.
vLLM is a high-performance, open-source library designed for efficient and scalable large language model (LLM) inference and serving. It features state-of-the-art serving throughput, optimized memory management with **PagedAttention**, and supports advanced techniques like continuous batching, CUDA/HIP graph execution, and various quantization methods (e.g., GPTQ, AWQ, INT4, INT8, FP8). vLLM integrates seamlessly with popular Hugging Face models, offers OpenAI-compatible API servers, and supports distributed inference with tensor and pipeline parallelism. It is highly flexible, supporting a wide range of hardware (NVIDIA, AMD, Intel, TPU, AWS Neuron) and models, including Transformer-based LLMs, Mixture-of-Experts, and multi-modal models. vLLM is community-driven, with contributions from academia and industry, and is backed by sponsors like a16z, Google Cloud, and NVIDIA.
A full-stack application that turns any documents into an intelligent chatbot with a sleek UI and an easier way to manage your workspaces.
A data framework for LLM (large language model) applications. It provides a solution for data storage and management for LLM applications, helping users build and manage LLM applications more efficiently.
Ultralytics provides a new deployment tool that supports the conversion of YOLOv8 models from PyTorch to various platforms, including ONNX, OpenVINO, CoreML and TFLite. For computer vision developers and researchers, this tool can help quickly deploy YOLOv8 models to different platforms, improving the performance of model applications.
A scheduled task management platform, which manages and schedules various offline scheduled tasks with a built-in web management interface. When the number of scheduled tasks reaches hundreds, it becomes impossible to effectively and conveniently manage these tasks using crontab. This project was born to solve this problem.
TTS is a library for advanced text-to-speech generation. It includes pre-trained models in over 1100 languages. Tools are provided for training new models and fine-tuning existing ones for any language. Utility programs are available for dataset analysis and management.
A tool for building customized low-code machine learning (LLM) workflows using a drag-and-drop UI with LangchainJS. It simplifies the development and deployment of machine learning processes, enabling users to design their own machine learning workflows through drag-and-drop operations, thereby enhancing development efficiency.
A decentralized web AI photo app🌈💎✨. It provides powerful features including photo management, smart categorization, search and sharing. Photoprism uses AI technology to automatically recognize objects, scenes and people in photos, allowing you to easily organize and browse your photo collection.
A practical real-world face restoration algorithm. It utilizes the rich prior knowledge from pre-trained face GANs (such as StyleGAN2) for blind face restoration, improving the quality and realism of the restored faces.
Use large models to build WeChat chatbots, based on GPT3.5/GPT4.0/Claude/ERNIE 1.0/Xunfei Xinghuo/LinkAI, support deployment of personal WeChat, official accounts and enterprise WeChat, can process text, voice and pictures, access operating systems and the Internet, support customized exclusive robots based on knowledge bases.
A free and open-source similarity search engine for massive feature vectors. Compared to operator libraries such as Faiss and SPTAG, Milvus provides a complete framework for vector data updates, indexing, and queries. Milvus utilizes GPU for index acceleration and query acceleration, significantly improving single-machine performance. Its deployment and usage are simple, reducing the difficulty of AI application implementation.
This Python-based toolkit, developed by the Facebook AI Research team, is a sequence-to-sequence modeling toolkit. It offers a comprehensive and robust set of tools and models, suitable for natural language processing tasks such as machine translation and text generation.
An open-source PyTorch tutorial code, the content is mainly tutorial code provided for deep learning researchers to learn PyTorch. Most of the models are implemented with less than 30 lines of code. You can use it in conjunction with the official PyTorch reference for learning.
An image super-resolution model, especially good at repairing cartoon images, makes the image effect amazing. Through AI technology, you can "enhance" your image to ultra-high definition, making the photo as clear as a movie scene, bringing you a new visual experience.
A collection of carefully organized large language models in practical applications in different fields, covering scenarios such as customer service, law, health, tourism, data analysis, etc., and combined with RGA and memory functions. It also collects tutorials on LLM fine-tuning, advanced tools, and framework usage, providing detailed information.
Netron is a versatile viewer for neural network, deep learning, and machine learning models, supporting a wide range of formats including ONNX, TensorFlow Lite, Core ML, Keras, Caffe, Darknet, PyTorch, and more. It offers experimental support for additional frameworks like TorchScript, OpenVINO, and PaddlePaddle. Available across multiple platforms—macOS, Linux, Windows, browsers, and Python—Netron provides an intuitive interface for visualizing and analyzing model architectures. Users can easily install it via package managers or directly download the application. Sample models are provided for quick exploration, making it a valuable tool for developers and researchers working with diverse machine learning frameworks.
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.
An innovative platform that integrates machine learning into databases through SQL. It treats models as virtual tables (AI-tables), allowing users to directly use SQL queries for time series, regression, and classification predictions without the need for complex data preparation and preprocessing steps. This greatly simplifies the machine learning development process. MindsDB provides developers with a simple and efficient way to accomplish machine learning tasks.
A project for writing reusable computer vision tools. Through this project, users can more easily create and manage the tools and processes needed for computer vision applications. Whether it's dataset preparation or model training, Supervision provides tools to help developers.
Make it more efficient and convenient for Python developers to integrate image text recognition functions
Develop voice applications: Alexa, Google Home, Siri, Cortana, and Mycroft Mark II.
An interactive deep learning book that provides code, math, and discussions across multiple frameworks. This project has been adopted at over 500 universities in 70 countries around the world, including Stanford University, Massachusetts Institute of Technology, Harvard University, Cambridge University, etc. It provides rich resources and an interactive learning experience for learning deep learning.
The main content of this book is the author's study during his graduate school period. The tutorial will be presented in the form of videos, mainly introducing the network structure and innovation points, as well as building and training networks based on PyTorch / TensorFlow.
An open platform for training, servicing, and evaluating large language models.
A vector database for next-generation AI applications. It provides efficient vector indexing and retrieval functions, supporting fast similarity search and relevance calculation, suitable for various AI application fields.
A project that uses artificial intelligence to monitor your security camera. By integrating artificial intelligence technology, frigate can intelligently analyze surveillance footage, providing intelligent monitoring and safety alerts. Whether it's home security, commercial surveillance, or other security scenarios, frigate is a powerful and intelligent monitoring tool.
A 100-day machine learning tutorial in Chinese
The goal of the "PyTorch Chinese Manual" is to help friends who want to learn and use PyTorch for deep learning development and research get started quickly.
It includes some practical machine learning and Python open source projects and tools. There are more than 900 projects in total, including data visualization, natural language processing, text and image data, web crawling, etc.
Convert the MXNet code implementation in the original "Dive into Deep Learning" book to a PyTorch implementation.
A practical list of machine learning projects, which includes a series of excellent open-source machine learning libraries that can help you monitor, deploy and protect your project.
Quickly build data-driven web applications. This is a project based on Python and Flask, combined with front-end technologies such as React, providing developers with a simple and efficient development framework. It can simplify the development process of data processing, API development, and user interface construction. Whether you are a data scientist, machine learning engineer, or web developer, you can use Taipy to quickly complete the entire process from prototype to web application. Sharing from @Liu Sanfei
Chat with your SQL database. This project uses LLM+RAG+database technology to allow users to query SQL databases through natural language and generate SQL answers to your questions.
The Llama Cookbook is the official guide for building applications with Llama Models, offering comprehensive resources for inference, fine-tuning, and end-to-end use cases. It includes tutorials for popular models like Llama 4 Scout and Llama 3.2 Vision, as well as safety-focused tools like Llama Guard. The repository features practical recipes for diverse applications, such as email agents, text-to-SQL, and multimodal inference. Structured into sections for third-party integrations, use cases, and getting started, it also provides FAQs and fine-tuning guidance. The project supports community contributions and adheres to Meta’s licensing and acceptable use policies for Llama models.
A cross-platform, high-performance machine learning inference and training accelerator launched by Microsoft. The project aims to provide machine learning developers with a flexible, high-performance runtime environment that supports multiple frameworks and hardware accelerators, making model inference and training more efficient. ONNX Runtime not only supports multiple operating systems but can also seamlessly integrate into various applications and services, providing convenience for the deployment of machine learning applications.
A large language model in the financial domain, trained through democratized internet-scale data on FinNLP and the FinNLP website. This project aims to provide robust natural language processing capabilities for the financial sector, assisting analysts, traders, and researchers in obtaining more accurate language model support for various tasks in finance.
LightRAG is a lightweight, efficient Retrieval-Augmented Generation (RAG) system designed for fast and scalable knowledge retrieval and generation. It supports multiple retrieval modes, including local, global, hybrid, and mix, integrating both structured knowledge graphs and unstructured vector search for comprehensive answers. Key features include multi-file type support (PDF, DOC, PPT, CSV), custom knowledge graph integration, and advanced query capabilities with citation functionality. LightRAG is compatible with various storage solutions like Neo4J, PostgreSQL, and Faiss, and supports LLM models from OpenAI, Hugging Face, and Ollama. It also offers a user-friendly GUI for document indexing, querying, and graph visualization. Designed for simplicity and speed, LightRAG is ideal for applications requiring efficient knowledge extraction and generation.
A list of open-source libraries related to PyTorch on GitHub, containing learning tutorials, examples, etc.
A master's student at South China University of Technology has compiled it, which contains various technical tutorials, excellent articles and video tutorials related to deep learning.
A collection of RAG tutorial. This project provides more than 20 advanced RAG technology tutorials, including implementation guides and example codes, which are updated regularly. The content covers various RAG technologies such as retrieval queries, context enhancement, fusion retrieval, hierarchical indexing, context compression, knowledge graph integration, etc.
A GPT-based document query tool designed for real-time interaction with documents. It enables users to perform document queries using natural language, providing detailed explanations and answers. DocsGPT leverages advanced natural language processing capabilities to make document understanding and querying more intuitive and user-friendly.
A project based on PyTorch, which uses artificial intelligence technology to quickly repair old photos. This project supports operations such as scratch detection, facial modification, and global restoration, helping users bring old photos back to life. This project demonstrates the potential and application of artificial intelligence in the field of image processing.
NLP tutorial, which includes 13 commonly used models and code implementation such as CNN, RNN, Transformer, and most of them are compatible with TensorFlow and PyTorch two frameworks.