Open-source AI Engineering from Scratch: 503 lessons, 20 phases, 320 hours, free
mdancho84 · x · 2026-11-08
"AI Engineering from Scratch" is a free, MIT-licensed curriculum with 503 lessons across 20 phases (320 hours), already at 48k GitHub stars.
You implement backprop from the math, build a tokenizer, code attention and Transformers, write your own agent loops and MCP servers, then deploy production AI systems—each lesson ships a reusable artifact. Covers Python, TypeScript, Rust, and Julia across foundations, modern AI (NLP/LLM/generative), and AI engineering (RAG, tools, MCP, agents). The pitch: 84% of students use AI tools but only 18% feel prepared to use them professionally.
Related event: Free open-source course "AI Engineering from Scratch" offers 503 lessons(3 posts)→
More from coding & agent
- 12 years, 8,000 commits: solo dev takes Spartan engine from yellow triangle to drivable island — ssh4net · 2026-11-08
- FFmpeg's Assembly code is the go-to test for whether LLMs can out-code human engineers — sh4dy_0011 · 2026-11-08
- DIY LLM vulnerability scanner finds 10 bugs for ~$20/day, 8 novel vs CodeQL — _h4xr · 2026-11-08
- leaf: a terminal Markdown previewer with GUI-like rendering and Mermaid support — 4310sy · 2026-11-08
- AILv1: An Open-Source Context Handover Format for Agents, with an MCP Server — fireheart_101 · 2026-11-08
- Perplexity CEO on Joe Rogan: the desk job was a sales strategy, and AI taking it over isn't bad — 2C_ornot2C · 2026-11-08