What it does
This is an open textbook covering the maths, computer science and AI ideas behind modern machine learning. Its author says it puts intuition and real-world context ahead of dense notation.
Chapters run from vectors, matrices, calculus, statistics and probability through machine learning, language, vision, audio, multimodal AI, robotics, graph networks, operating systems, algorithms and production software engineering.
You can read it online. It also includes an MCP server, a connector that lets AI assistants like Claude Code or Cursor use the book as a reference.
Who it's for
Self-learners, students and engineers who want a deeper understanding of the ideas behind AI.
Can I use it without coding?
Yes. You can read it in any web browser; the AI connector is optional and needs a copy of the repository. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Web browser
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
- Open the online version linked at the top of the README.
- Start with the chapter that matches what you want to learn.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- Show HN: Maths, CS and AI CompendiumHacker News · Feb 2026