patchy631/ai-engineering-hub

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

What it is

AI Engineering Hub is a GitHub repository packed with 93+ ready-to-use projects and tutorials covering everything from beginner basics to advanced production systems. It is designed for anyone who wants to learn AI engineering by building real things – whether you are just starting out, already practicing, or doing research.

The repo is organized by difficulty level, so you can start simple and work your way up. It includes hands-on examples for LLMs (large language models), RAG (retrieval-augmented generation – a way to make AI answer questions with your own data), AI agents, and more.

What you’ll find inside

  • Beginner projects (22) – single-component apps like OCR (text extraction from images), simple chat interfaces, and basic RAG setups.
  • Intermediate projects (48) – multi-component systems, agent workflows, voice and audio processing, advanced RAG, model comparison, and MCP (Model Context Protocol – a way to connect AI to external tools) examples.
  • Advanced projects (23) – fine-tuning your own models, building reasoning models, complex agent systems, production deployments, and full-fledged applications (like a NotebookLM clone).

Every project links to its own folder with code and a tutorial. The README also provides an AI Engineering Roadmap – a step-by-step learning path from Python basics all the way to production AI.

How to get started

The README suggests four steps:

  1. Complete beginners should check out the AI Engineering Roadmap first.
  2. Then dive into beginner projects (like OCR apps or simple RAG).
  3. Move to intermediate projects (agents and complex workflows).
  4. Finally, tackle advanced projects (fine-tuning, production systems).

You can also subscribe to a free newsletter (Daily Dose of Data Science) to get a free Data Science eBook with 150+ lessons.

How to contribute

The project welcomes contributions – you can add tutorials, improve existing code, or report issues. The process is standard: fork the repo, create a branch, make your changes, and submit a pull request. Contributing guidelines are linked.

License

MIT License – you are free to use, modify, and distribute the code with attribution.

Where to connect

For discussions, suggestions, or questions, you can create an issue on the repository or reach out directly.

Related

  • Project
    PDFMathTranslate/PDFMathTranslate

    A scientific PDF translation tool that preserves original layouts, formulas, and charts while supporting multiple translation services and OCR.

  • Project
    khoj-ai/khoj

    Khoj is an open-source personal AI assistant that serves as a second brain, allowing users to chat with their own documents and the internet using various LLMs.

  • Project
    stanfordnlp/dspy

    DSPy is a framework that allows developers to build modular AI systems using Python code instead of manual prompt engineering, automatically optimizing prompts and model weights for better performance.

  • Project
    anthropics/prompt-eng-interactive-tutorial

    An interactive, chapter-based tutorial for learning prompt engineering with Claude 3 Haiku, featuring lessons, exercises, a playground, and an optional Google Sheets version.