🚀 51 GitHub Repositories to Learn Artificial Intelligence in 2025 (From Zero to Advanced)

This curated list presents 51 excellent GitHub repositories to learn Artificial Intelligence, organized by difficulty level: Beginner, Intermediate, and Advanced. They cover a wide range of topics: machine learning, deep learning, generative models, autonomous agents, NLP, computer vision, neural networks, MLOps, and more.

Each repository includes its name with a link and a brief description. These are popular, well-documented projects with practical resources such as notebooks, datasets, and projects.

Beginner (AI and Machine Learning Fundamentals)

• 100 Days of ML Code — A 100-day plan for introducing yourself to Machine Learning with daily concepts and exercises. (~47k stars).

• Data Science for Beginners (Microsoft) — A 10-week curriculum covering essential data science concepts with videos, quizzes, and projects. (~30k stars).

• Machine Learning for Beginners (Microsoft) — A 12-week, 26-lesson course introducing “classical” machine learning with Scikit-learn and real-world datasets. (~76k stars).

• Python Data Science Handbook — Jupyter notebooks from Jake VanderPlas’ book, introducing Python libraries for data science. (~45k stars).

• Awesome Data Science — A curated list of resources for learning data science: courses, books, tutorials, datasets, and more. (~25k stars).

• Project-Based Learning — A massive collection of tutorials to learn by building projects (including AI/ML). (~238k stars).

• IA-PARA-TODOS (in Spanish) — Open tutorials, applications, and resources in Spanish for making AI accessible. (New project, growing stars).

Intermediate (Diving Deeper into ML/DL and Specialized Tools)

• AI for Beginners (Microsoft) — A 12-week, 24-lesson curriculum on general AI, from classical search to deep learning. (~39k stars).

• Hands-On Machine Learning — Notebooks accompanying the popular book covering ML and DL with Scikit-learn, Keras, and TensorFlow. (~29k stars).

• Fastai Course / Fastbook — Practical deep learning course with step-by-step notebooks using the fastai library on PyTorch. (~23.5k stars).

• Awesome Machine Learning — A curated list of machine learning frameworks, libraries, and software by programming language. (~69k stars).

• Dive into Deep Learning (D2L) — An interactive deep learning book with code implementations in PyTorch, TensorFlow, and MXNet. (~26k stars).

• PyTorch Tutorial (Yunjey) — Tutorials for PyTorch, organized into basic, intermediate, and advanced sections. (~31.6k stars).

• Machine Learning From Scratch — Implementations of ML algorithms from scratch with NumPy to understand their inner workings. (~27k stars).

• Homemade Machine Learning — Python implementations of ML algorithms with step-by-step explanations and demos. (~23k stars).

• 500 AI Projects — A comprehensive collection of 500+ AI projects across multiple subfields. (~25.9k stars).

• TensorFlow Examples — Concise TensorFlow tutorials from basic operations to CNNs, RNNs, and GANs. (~43.7k stars).

• NLP Tutorial (Graykode) — PyTorch and NumPy implementations of key NLP models in under 100 lines each. (~14.7k stars).

• Deep Learning with Python (Chollet Notebooks) — Keras notebooks covering all chapters of François Chollet’s book. (~19k stars).

• The Open Source Data Science Masters — A self-taught data science master’s curriculum with free online courses and books. (~25.6k stars).

• Scikit-Learn — The official repository for Scikit-learn, with tutorials and user guides for classical ML. (~55k stars).

Advanced (Deep Learning, Generative Models, RL & Specialized Topics)

• Awesome Deep Learning — A curated list of deep learning tutorials, frameworks, and research papers. (~25.9k stars).

• Awesome Artificial Intelligence — A list of courses, books, and classic AI papers for advanced study. (~12k stars).

• Awesome Computer Vision — Curated resources for computer vision: courses, libraries, datasets, and research. (~15k stars).

• OpenAI Spinning Up — Educational resources and algorithm implementations for Deep Reinforcement Learning. (~11k stars).

• PyTorch-GAN — Implementations of popular GAN architectures in PyTorch. (~17.2k stars).

• Hugging Face Transformers Course — Free Hugging Face course on transformers for NLP, vision, and audio with hands-on notebooks. (~3.2k stars).

• nanoGPT — A minimal, efficient implementation of GPT models, designed for educational purposes. (~42k stars).

• AutoGPT — An experimental autonomous agent powered by GPT-4, capable of breaking down and executing tasks. (~177k stars).

• LangChain — A framework for building applications with LLMs, including chaining prompts, memory, and agents. (~60k+ stars).

• Made With ML (MLOps) — A comprehensive open-source course on MLOps for deploying ML models responsibly. (~41.5k stars).

• RAG Techniques — Implementations and tutorials for Retrieval-Augmented Generation techniques. (~10k stars).

• ML Design Interview — A guide to preparing for machine learning system design interviews. (~11k stars).

• Data Science Interviews — A collection of data science interview questions and detailed answers. (~9.4k stars).

• Generative AI and LLMs Course (in Spanish) — A Spanish-language course on generative AI and LLMs, covering fundamentals, fine-tuning, and deployment.

• micrograd — A minimal autograd engine in 50 lines of Python code, showing backpropagation fundamentals. (~4k stars).

• Stanford Alpaca — Code and data for fine-tuning a LLaMA-based model with instruction-following data. (~30k stars).

• OpenAI Cookbook — Examples and guides for using OpenAI’s APIs effectively, from simple calls to advanced fine-tuning. (~65k stars).

if you want to supercharge your productivity with AI, grab my free ebook:  30 ChatGPT Prompts That Will Make You More Productive