How to use awesome-artificial-intelligence: a learning guide

What awesome-artificial-intelligence is and who it is for

This is a list of links, not a program. There is nothing to install or run. The README describes it as an opinionated collection of resources for software developers learning to build and ship generative AI and agentic systems.

It is a good fit for developers who want to learn the foundations behind language models and agents, engineers who need practical guides to building LLM applications, students who want a structured set of courses and books on deep learning and NLP, and developers who want to read the original papers behind transformers, RAG, LoRA and RLHF.

It is not a good fit for complete beginners without programming experience, since many listed resources assume coding skills. It is also not a catalogue of AI products. The README says it is not comprehensive and that categories are not quotas.

Get the list onto your computer

The README suggests cloning the repository so you have the files locally. Run the command below in a terminal. The list is a set of Markdown files, so you can also open the README directly on GitHub and skip this step.

Understand how the list is organised

The README is split into two main parts. The Learn section covers books, courses and foundational papers. The Build AI systems section covers guides and playbooks, LLM application engineering, protocols and interoperability, agent frameworks, and durable and asynchronous agents.

Each entry is a link followed by a one-line description of what it covers. The descriptions are the fastest way to decide whether an item matches your level and goals.

• Learn: Books, Courses, Foundational papers
• Build AI systems: Guides and playbooks, LLM application engineering, Protocols and interoperability, Agent frameworks, Durable and asynchronous agents

Choose a starting point based on your goal

If you want foundations, the README lists Artificial Intelligence: A Modern Approach as the broad reference for classical AI, and Hands-On Large Language Models as a visual and practical guide. For a hands-on course, the Hugging Face LLM Course and Karpathy's Neural Networks: Zero to Hero both build language models from first principles.

If you want to build, the guides from Anthropic and OpenAI on agents, the OpenAI Cookbook and the 12-Factor Agents principles are practical starting points. For frameworks, the README lists Pydantic AI, LangGraph, the OpenAI Agents SDK, Google Agent Development Kit and Microsoft Agent Framework.

If you want the research, the Foundational papers section lists the original Transformer paper, the RAG paper, the LoRA paper and the paper on instruction tuning with human feedback, among others. Read the descriptions first and then open the arXiv links.

• Foundations: Artificial Intelligence: A Modern Approach, Hands-On Large Language Models
• Hands-on courses: Hugging Face LLM Course, Karpathy's Neural Networks: Zero to Hero, Fast.ai Practical Deep Learning
• Building agents: Building Effective Agents, A Practical Guide to Building Agents, OpenAI Cookbook
• Papers: Attention Is All You Need, Retrieval-Augmented Generation, LoRA

Check the quality and currency of entries

The README says every entry must clear a quality bar for technical depth, practical value, evidence and distinctiveness. It also says the list is reviewed weekly by an automated process that reviews, validates and merges small changes. The full criteria are described in the CURATION.md file linked from the README.

Because the list changes, always check that a link still works and read the source before committing to a long course or book.

Get the most from the reading list

Pick one track and stay with it. Reading every link at once will not build understanding. A common approach is to read one foundational text, complete one hands-on course, then read one or two papers that explain the ideas you saw in practice.

Use the papers as reference points. Many of them, such as the RAG and LoRA papers, are short enough to read alongside a project.

• Choose one track: foundations, hands-on building, or research
• Pair a course or book with a small project of your own
• Read a paper when a concept from the course needs more depth