A hand-verified shortlist of the repositories AI engineers actually keep starred — LLM fundamentals, agent-building courses, production MLOps, and prompt-engineering references, each checked against its live repo page.
Learning to build with LLMs means moving between four kinds of repository: the ones that teach how the models actually work, the ones that teach how to build agents on top of them, the ones that teach how to ship ML to production, and the reference guides you keep bookmarked for prompting and interview prep. This directory checks each repo live and lists its description, primary language, approximate star count, and license exactly as found.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step.
Builds a GPT-style model from first principles -- tokenization, attention, pretraining, and fine-tuning -- as the companion code to Sebastian Raschka's Manning book of the same name.
Official code repo for the O’Reilly Book – "Hands-On Large Language Models".
Nearly 300 custom illustrations and runnable Colab notebooks covering tokenization, transformers, classification, RAG, fine-tuning, and multimodal LLMs.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Three tracks -- LLM foundations, building state-of-the-art models, and shipping LLM applications -- with hands-on notebooks for fine-tuning, quantization, RAG, and agents.
18 Lessons to Get Started Building AI Agents.
Microsoft's structured course on agent fundamentals -- tool use, RAG patterns, multi-agent systems, and production deployment -- with code samples in the Microsoft Agent Framework, in 50+ languages.
50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.
A large, graded collection of agent build-alongs spanning LangGraph and CrewAI, from simple assistants to document processing and research-automation systems.
Learn how to develop, deploy and iterate on production-grade ML applications.
A full-lifecycle MLOps course: experimentation, training, evaluation, serving, CI/CD, and monitoring, taught with Python and Ray.
Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022).
Chapter summaries and MLOps tool references companioning Chip Huyen's book on building production-ready ML systems, from data engineering through deployment and monitoring.
Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
A comprehensive, actively maintained reference on prompting technique -- chain-of-thought, RAG, agent design -- paired with a companion site at promptingguide.ai.
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Organizes GenAI learning into three journeys -- using AI, building AI systems, and following AI research -- plus 90+ free courses and interview prep by role.
No repositories match that search. Try a different term or clear the filter.