A 503-lesson open-source curriculum that teaches AI engineering from foundational math to autonomous swarms, with each lesson producing a reusable artifact. The curriculum requires coding knowledge and spans Python, TypeScript, Rust, and Julia.
Project overview
Every lesson ships a reusable tool such as an agent or MCP server, and the curriculum builds every algorithm from raw math before using libraries.
Project type
AI Agent · Learning Resources
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 from raw math.
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.
Script to walk every phase and lesson to produce a catalog.json file.
Limitations and risks
The curriculum requires existing coding knowledge to complete the lessons and build the artifacts.
Getting started
Setup is rated easy because it provides direct one-line execution commands. The first success path involves cloning the repository, navigating to the directory, and running a Python script for linear algebra intuition.
Alternatives and comparisons
A structured, 503-lesson Chinese AI engineering curriculum that teaches by building every algorithm from scratch, delivering reusable artifacts.
Provides a comprehensive learning roadmap, structured tutorials, enterprise AI frameworks, and career strategies for DevOps professionals adopting AI.
Provides a comprehensive educational guide with deep explanations, architecture breakdowns, methodology workflows, templates, security threat intelligence, and a knowledge validation quiz for Claude Code.