ai-engineering-from-scratch

Learn it. Build it. Ship it for others.

The most comprehensive, open-source AI engineering course ever created. From linear algebra to autonomous agent swarms — 200+ hands-on lessons across 19 phases, in the language that fits best: Python, TypeScript, Rust, or Julia.

This isn't a tutorial. This isn't a bootcamp. This is the curriculum universities wish they had — built by practitioners, free forever, and designed so that every lesson you complete produces something the world can use.

[](LICENSE) [](CONTRIBUTING.md)

---

Every other course teaches you AI and sends you home.

This course teaches you AI and by the time you're done, you've built a library of battle-tested prompts, skills, agents, and MCP servers that others can actually use.

| | Other Courses | This Course | |---|---|---| | Scope | One slice (NLP or Vision or Agents) | Everything: math → ML → DL → NLP → vision → speech → transformers → LLMs → agents → swarms | | Languages | Python only | Python, TypeScript, Rust, Julia — best tool for each job | | Output | "I learned something" | A portfolio of real tools, prompts, skills, and agents | | Depth | Surface-level or theory-heavy | Build from scratch first, then use frameworks | | Format | Videos or docs | Runnable code + notebooks + docs + interactive web app |

> Get your environment ready for everything that follows.

| # | Lesson | Type | Language | |---|--------|------|----------| | 01 | Dev Environment | Build | Python, Node, Rust | | 02 | Git & Collaboration | Learn | — | | 03 | GPU Setup & Cloud | Build | Python | | 04 | APIs & Keys | Build | Python, TypeScript |

> The intuition behind every AI algorithm, through code — not textbooks.

| # |