Top AI Open Source Projects by Stars in 2025

An open-source machine learning framework for everyone

AutoGPT is a powerful AI automation platform that makes it easy for anyone to create, deploy, and manage continuous AI agents to automate complex workflows.

A Gradio-based Stable Diffusion Web UI interface, providing AI painting functions such as text-to-image and image-to-image.

Transformers provides thousands of pre-trained models to support tasks in over 100 languages across text, vision, audio, and more.

Ollama: Run, create, and share large language models locally.

An open-source Faircode workflow automation platform with native AI capabilities, combining visual building and custom code, supporting 400+ integrations.

An open-source LLM application development platform that integrates agent workflows, RAG pipelines, model management, and more, allowing you to quickly go from prototype to production deployment.

A feature-rich, self-hosted AI chat interface that supports Ollama and OpenAI API, providing a completely offline AI conversation experience.

PyTorch: Python tensor and dynamic neural network with strong GPU acceleration

A lightweight and fast AI assistant that supports multi-platform deployment and integrates various AI models such as ChatGPT, Claude, and Gemini.

OpenCV is an open-source computer vision, machine learning, and image processing library that provides a rich set of algorithms and tools, widely used in areas such as image recognition, object detection, and video analysis.

llama.cpp is a LLaMA model inference engine written in pure C/C++, designed for high performance and low resource usage.

A powerful and modular Stable Diffusion visual interface with node-based workflow design.

A powerful low-code AI application building platform designed for creating intelligent agents and RAG applications.

Open-source real-time infrastructure monitoring platform providing AI-powered full-stack observability solutions.

GPT4All: An open-source AI chatbot application for running local large language models on any device.

High-performance in-memory data structure server supporting vector search and real-time data structures for AI applications.

The easiest way for AI agents to connect to and control browsers, enabling website automation.

Keras is a high-level neural networks API, written in Python, capable of running on top of TensorFlow, JAX, or PyTorch. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.

An open-source, modern AI chat framework that supports multiple AI providers, knowledge base management, multimodal interaction, and more.

Scikit-learn: Machine learning library in Python, providing simple and efficient tools for data mining and data analysis.

An open-source Retrieval-Augmented Generation engine based on deep document understanding, providing accurate and reliable question answering capabilities for businesses of all sizes.

A fast high-level Python web crawling and web scraping framework used to crawl websites and extract structured data from pages.

Multi-agent framework, the first AI software company, enabling natural language programming

YOLOv5 is a state-of-the-art, real-time object detection model based on PyTorch, supporting object detection, image segmentation, and image classification tasks.

FaceSwap is a deep learning-based face swapping tool that can identify and swap faces in images and videos.

A no-code, low-code large language model fine-tuning and deployment framework that supports unified and efficient fine-tuning of 100+ LLMs/VLMs.

PaddleOCR aims to create a rich, leading, and easy-to-use OCR toolkit to help developers train better, faster, and more accurate OCR models.

vllm is a fast and easy-to-use library for fast inference of large language models.

GPT-SoVITS: A few-shot voice cloning tool that can train a high-quality TTS model with just 1 minute of voice data.

An open-source multi-agent AI application framework developed by Microsoft, supporting multiple AI agents to collaborate on solving complex tasks.

Open-source, high-performance web crawler and data extraction tool optimized for LLMs and AI agents.

Open-source, all-in-one AI desktop application with built-in RAG, AI agents, and a no-code agent builder.

A leading data framework for building LLM-powered intelligent agents, specializing in private data augmentation.

YOLOv5 is a state-of-the-art, real-time object detection model based on PyTorch, supporting object detection, image segmentation, and image classification tasks.

An open-source financial investment research platform providing comprehensive financial data analysis and investment research tools for users worldwide.

High-resolution text-to-image generation model based on latent diffusion models

Colossal-AI: Making large model training easy, efficient, and cost-effective.

A high-performance C/C++ port of the OpenAI Whisper speech recognition model, supporting pure CPU inference and multi-platform deployment.

Unsloth: Efficient fine-tuning and reinforcement learning tool for large language models - 2x faster training, 70% less memory usage

Coqui TTS: A deep learning toolkit for text-to-speech, proven through research and production practice.

An open-source drag-and-drop visual AI agent building platform based on LangChain technology, allowing users to quickly create custom LLM applications without programming.

Transforms entire websites into LLM-ready Markdown or structured data, with scraping, crawling, and extraction through a single API.

Streamlit is a Python library that allows you to create beautiful, custom web applications with pure Python code for machine learning, data science, and more.

A completely free visual web scraping tool that allows you to design and execute data collection tasks without programming.

DeepSpeed is a deep learning optimization library designed to make distributed training easy, efficient, and powerful. It supports large-scale model training and provides various optimization techniques, such as ZeRO optimizer, pipeline parallelism, and tensor parallelism, to improve training speed and reduce memory footprint.

FastChat is an open platform for training, serving, and evaluating large language models.

An intelligent Retrieval-Augmented Generation (RAG) platform based on generative AI, helping users build a second brain for intelligent document Q&A and knowledge management.

Ray is a unified framework for scaling Python and AI applications. It makes it easy to transform single-machine Python code into distributed applications.

Open-source, chat-based AI assistant trained using Reinforcement Learning from Human Feedback, aiming to provide free large language model access to everyone.