A full free AI engineering degree on GitHub: 542 lessons, ~400 hours
ghumare64 · x · 2026-10-23
Someone has open-sourced a complete "AI engineering degree" on GitHub, 100% free: 542 lessons across 20 phases, roughly 400 hours of material, built around learning AI from first principles.
The path starts with math, then hand-implements core concepts—backpropagation, tokenizers, attention, agent loops—before touching production frameworks. Each lesson follows five steps: read the problem, derive the math, write the code, run the test, keep the artifact, leaving reusable prompts, SKILL.md files, agent definitions, and self-built MCP servers. Code runs in Python, TypeScript, Rust, or Julia, and the curriculum spans linear algebra through autonomous agent swarms, multi-agent coordination, and production infrastructure.
More from coding & agent
- Open-source tool turns the MacBook notch into a one-click approval panel for Claude Code — cneuralnetwork · 2026-10-23
- Taskuary: open-source bridge that routes email and chat tasks to Codex, Claude Code and Gemini CLIs — Appropriate-Path-461 · 2026-10-23
- AI makes coding 10x faster, so why isn't your team shipping 10x faster? Amdahl's law explains — arpit_bhayani · 2026-10-23
- Side project builds textual 3D worlds in the terminal with custom TUI tooling — sull · 2026-10-23
- Selfdrive AI agent turns an App Store link into a full user-acquisition plan — PrajwalTomar_ · 2026-10-23
- Thorsten Ball mocks SaaS firms building internal agent platforms nobody uses — HankYeomans · 2026-10-23