A 503-lesson open-source curriculum spanning 20 phases that builds AI engineering knowledge from mathematical foundations to production agents. Learners produce a reusable artifact for every lesson and can install generated skills into agent directories using provided CLI scripts.
Project overview
A 503-lesson open-source curriculum spanning 20 phases that builds AI engineering knowledge from mathematical foundations to production agents. Learners produce a reusable artifact for every lesson and can install generated skills into agent directories using provided CLI scripts.
Project type
MCP · AI Agent
Use cases
Learning & Education
Deployment
Refer to project documentation
License
MIT
Best for
Developers, AI engineers, and educators who possess coding knowledge and want a structured path to build AI systems from mathematical foundations through production agent engineering.
Key capabilities
A 20-phase, 503-lesson curriculum teaching AI from linear algebra to autonomous swarms in Python, TypeScript, Rust, and Julia.
Each lesson ships a reusable artifact such as a prompt, SKILL.md file, agent, or MCP server.
Python script and CLI commands to install curriculum skills into agent directories automatically.
Script to byte-compile Python files under lesson directories to verify syntax correctness.
Script to walk every phase and lesson to produce a catalog.json file mapping the curriculum structure.
Limitations and risks
The curriculum requires users to have pre-existing coding knowledge to understand and execute the lesson material.
Getting started
Setup is straightforward: clone the repository, navigate to the directory, and execute a lesson script such as the linear algebra vectors file directly from the CLI to begin.
Evidence and sources
GitHub project description: Learn it. Build it. Ship it for others.
README: ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` > **84% of students already use AI tools. Only 18% feel prepared to use them > p…
README: Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a flashy agent demo somewhere else. The pieces rarely line up.
README: This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm g…
README: git clone https://github.com/rohitg00/ai-engineering-from-scratch.git cd ai-engineering-from-scratch python phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py