ai-engineering-from-scratch
AIFree, open-source curriculum of 500+ hands-on lessons across 20 phases to learn and build AI engineering from math to agents.
ai-engineering-from-scratch
Free, open-source curriculum of 500+ hands-on lessons across 20 phases to learn and build AI engineering from math to agents.
About ai-engineering-from-scratch
AI Engineering from Scratch is a free, MIT-licensed learning curriculum hosted on GitHub with a companion website. It contains 523 lessons organized into 20 phases and roughly 342 hours of material, covering setup and tooling, math foundations, LLM engineering, tools and protocols such as MCP and Agent Skills, and agent engineering. Lessons use Python, TypeScript, Rust and Julia, and each one ships a reusable artifact such as a prompt, a skill, an agent or an MCP server. Learners follow a consistent loop of reading the lesson, building the code, running it from the repository root and keeping evidence of the output. Goal-based starting points, learning paths, a placement tutor skill and certification onboarding for Claude and the MCP Associate track help learners choose a route.
Key Features
Use Cases
Frequently asked questions about ai-engineering-from-scratch
What is ai-engineering-from-scratch?
Free, open-source curriculum of 500+ hands-on lessons across 20 phases to learn and build AI engineering from math to agents.
How does ai-engineering-from-scratch work?
ai-engineering-from-scratch works by combining 523 lessons in 20 phases: A structured curriculum of about 342 hours from setup and math to LLM and agent engineering, Multi-language code: Lessons implemented in Python, TypeScript, Rust and Julia, Reusable artifacts: Every lesson ships a prompt, skill, agent or MCP server you can reuse, Goal-based paths: Learning paths for coding agents, MCP, Agent Skills and product delivery, Evidence-based workflow: Learners record the command, output and changes for each lesson to help users with A developer new to AI follows Phase 0 and the math foundations to build a base, An engineer builds production LLM applications using the LLM Engineering phase, A team learns to write and ship Agent Skills and MCP servers through the tools and protocols phase, A coding-agent user follows the agent-assisted engineering path to work on real repositories, A learner prepares for the MCP Associate certification using the onboarding guide.
What are the main features of ai-engineering-from-scratch?
Key features include 523 lessons in 20 phases: A structured curriculum of about 342 hours from setup and math to LLM and agent engineering, Multi-language code: Lessons implemented in Python, TypeScript, Rust and Julia, Reusable artifacts: Every lesson ships a prompt, skill, agent or MCP server you can reuse, Goal-based paths: Learning paths for coding agents, MCP, Agent Skills and product delivery, Evidence-based workflow: Learners record the command, output and changes for each lesson.
Who is ai-engineering-from-scratch for?
ai-engineering-from-scratch is useful for anyone interested in A developer new to AI follows Phase 0 and the math foundations to build a base, An engineer builds production LLM applications using the LLM Engineering phase, A team learns to write and ship Agent Skills and MCP servers through the tools and protocols phase, A coding-agent user follows the agent-assisted engineering path to work on real repositories, A learner prepares for the MCP Associate certification using the onboarding guide.
How much does ai-engineering-from-scratch cost?
ai-engineering-from-scratch is free to use.
How do I get started with ai-engineering-from-scratch?
Visit https://github.com/rohitg00/ai-engineering-from-scratch to sign up and explore ai-engineering-from-scratch.
Explore more AI Ai Services tools
Browse all Ai Services tools →Compare ai-engineering-from-scratch: vs Thanor · vs Hopscotch · vs ZergRouter · vs DokBot