Image by author
# introduction
Learning AI today is not just about understanding machine learning models. From math and fundamentals to building real applications, agents, and operational systems, it's important to know how things actually fit together. With so much content online, it's easy to get lost or jump between random tutorials without a clear path.
In this article, you will learn about 10 of the most popular and really useful GitHub repositories for learning AI. These repositories cover everything from generative AI, large-scale language models, agent systems, ML mathematics, computer vision, real-world projects, and production-grade AI engineering.
# GitHub repository for learning AI
// 1.microsoft/generative-ai-for-beginners
Generative AI for Beginners is a structured 21-lesson course from Microsoft Cloud Advocates that teaches you how to build real-world generative AI applications from scratch. It combines clear conceptual lessons with hands-on builds in Python and TypeScript, covering prompts, chat, RAGs, agents, fine-tuning, security, and deployment. This beginner-friendly, multilingual course is designed to move learners from the basics to production-ready AI apps with practical examples and community support.
// 2. Create rasbt/LLM from scratch
Build a Large Language Model (From Scratch) is a hands-on educational repository and sister edition to Manning's book that explains how LLM works by step-by-step implementing a GPT-style model in pure PyTorch. Learn about tokenization, attention, GPT architecture, pre-training, and fine-tuning (including instruction tuning and LoRA). All of these are designed to run on regular laptops. The focus is on deep understanding through code, diagrams, and exercises, rather than using high-level LLM libraries, making it ideal for learning the internals of LLM from scratch.
// 3. DataTalksClub/llm-zoomcamp
LLM Zoomcamp is a free 10-week hands-on course focused on building real-world LLM applications, specifically RAG-based systems using your own data. Cover vector search, evaluation, monitoring, agents, and best practices through hands-on workshops and capstone projects. Designed for self-paced or cohort learning, it focuses on not just theory but production-ready skills, community feedback, and end-to-end system building.
// 4.Shubhamsaboo/awesome-llm-apps
Awesome LLM Apps is a curated showcase of real, executable LLM applications built with RAGs, AI agents, multi-agent teams, MCPs, voice interfaces, and memory. We focus on practical projects using OpenAI, Anthropic, Gemini, xAI, and open source models such as Llama and Qwen, many of which can be run locally. The focus is on learning by example, exploring modern agent patterns, and accelerating the hands-on development of operational-style LLM apps.
// 5.panaversity/learn-agentic-ai
Learn Agentic AI with Dapr Agentic Cloud Ascent (DACA) is a cloud-native, systems-first learning program focused on designing and scaling global agenttic AI systems. Learn how to use Kubernetes, Dapr, OpenAI Agents SDK, MCP, and A2A protocols to build reliable, interoperable multi-agent architectures with a focus on workflow, resiliency, cost management, and real-world execution. The goal is to train developers not just to build agents, but to design production-ready agent fleets that can scale to millions of concurrent agents under real-world constraints.
// 6. dair-ai/Mathematics-for-ML
Mathematics for Machine Learning is a carefully selected collection of high-quality books, articles, and video lectures covering the mathematical fundamentals behind modern ML and deep learning. It focuses on core areas such as linear algebra, calculus, probability, statistics, optimization, and information theory, with resources ranging from beginner level to research-level depth. The goal is to enable learners to build strong mathematical intuition and confidently understand the theory behind machine learning models and algorithms.
// 7. ashishpatel26/500-AI-Machine Learning-Deep Learning-Computer Vision-NLP-Projects with Code
The 500+ Artificial Intelligence Projects with Code list is a large, continuously updated directory of AI/ML/DL project ideas and learning resources, grouped across disciplines such as computer vision, NLP, time series, recommender systems, healthcare, production ML, and more. We link to hundreds of tutorials, datasets, GitHub repositories, and “projects with source code,” and encourage community contributions via pull requests to keep the links working and expand the collection.
// 8. armanchondker/awesome-ai-ml-resources
Machine Learning & AI Roadmap (2025) is a structured beginner-to-advanced guide that maps out how to learn AI and machine learning step-by-step. Covering core concepts, math fundamentals, tools, roles, projects, MLOps, interviews, research, and links to trusted courses, books, articles, and communities. The goal is to provide learners with a clear path forward in a rapidly changing field, allowing them to build practical skills and career readiness without becoming overwhelmed.
// 9. spmallick/learnopencv
LearnOpenCV is a comprehensive, hands-on repository that accompanies the LearnOpenCV.com blog, offering hundreds of tutorials with executable code across computer vision, deep learning, and modern AI. It covers topics from classic OpenCV fundamentals to cutting-edge models such as YOLO, SAM, diffusion models, VLM, robotics, and edge AI, with an emphasis on practical implementation. This repository is perfect for learners and practitioners who want to understand AI concepts by building real systems rather than just reading theory.
// 10. x1xhlol/System prompt and AI tools model
System Prompts and Models for AI Tools is an open source AI engineering repository that documents how real-world AI tools and agents are structured, publishing over 30,000 lines of system prompts, model behaviors, and design patterns. This is particularly useful for developers building reliable agents and prompts, providing practical insight into how production AI systems are designed, while also highlighting the importance of rapid security and leak prevention.
# final thoughts
In my experience, the fastest way to learn AI is to stop treating it as a theory and start building it in parallel. These repositories work because they're practical, opinionated, and shaped by real engineers solving real problems.
My advice is to pick a few that suit your current level and goals, consider them from start to finish, and build on them consistently. Depth, repetition, and practical practice are far more important than chasing every new trend.
Abid Ali Awan (@1abidaliawan) is a certified data scientist professional who loves building machine learning models. Currently, he is focusing on content creation and writing technical blogs about machine learning and data science technology. Abid holds a master's degree in technology management and a bachelor's degree in communications engineering. His vision is to use graph neural networks to build AI products for students suffering from mental illness.
