Open-source AI engineering curriculum trends on GitHub
The open-source project "AI Engineering from Scratch" has appeared on GitHub's Python trending list. It describes 20 phases, 523 lessons and roughly 342 hours of material in Python, TypeScript, Rust and Julia, released free under an MIT license, with each lesson having learners implement algorithms such as backpropagation, tokenizers, attention and the agent loop from raw math before running the same thing through production libraries like PyTorch. It also offers focused Model Context Protocol (MCP) and Agent Skills routes plus preparation for Claude certification tracks, and can be installed as learning skills for coding agents including Codex and Claude Code.
It turns scattered AI learning material into one path from linear algebra to autonomous agent systems, using a build-it-then-use-it approach that reduces reliance on opaque tools.
Learn AI Engineering! Learn it. Build it. Ship it for others.

https://aiengineeringfromscratch.com
Implement model internals, retrieval pipelines, and agent runtimes. Test them, inspect failures, and keep the code and evaluation results.
Start learning · Choose a path · Try a lab · Build a project · Browse the curriculum
Some source content is omitted. Continue reading on the original site.
#AI Engineering from Scratch#GitHub#Anthropic#Claude Code#Model Context Protocol