ai-engineering-from-scratch vs learn-claude-code
AI learning curricula compared
ai-engineering-from-scratch teaches AI engineering across foundations, LLMs, agents, and production through a broad curriculum of runnable lessons. learn-claude-code focuses on building coding-agent harnesses, adding mechanisms such as tools, permissions, memory, and coordination in progressive Python examples.
ai-engineering-from-scratch: Learn AI by Building It
A free, MIT-licensed curriculum that teaches AI engineering through runnable lessons and hands-on artifacts. It covers foundations through LLMs, agents, protocols, and production, with paths for beginners and experienced developers.
learn-claude-code: Learn to Build LLM Agent Harnesses
A hands-on Python tutorial for building the harness around an LLM coding agent, from a basic tool loop to permissions, memory, teams, and workflows. Suited to developers who want to understand agent infrastructure by studying small runnable examples.
| ai-engineering-from-scratch | learn-claude-code | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 62.9k | 78k |
| Forks | 10.8k | 12.5k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- ai-engineering-from-scratch spans 20 phases and topics from math and machine learning to production, while learn-claude-code centers on 17 lessons about coding-agent harnesses.
- ai-engineering-from-scratch offers runnable code in Python, TypeScript, Rust, and Julia depending on the lesson; learn-claude-code uses standalone Python examples.
- ai-engineering-from-scratch includes focused paths for agents, MCP, Agent Skills, coding agents, and certification preparation; learn-claude-code develops harness concepts such as permissions, context management, and agent-team coordination.
- ai-engineering-from-scratch provides a website, repository lessons, AI tutor skills, and downloadable book editions; learn-claude-code provides a web app alongside standalone chapter code.
- Both projects are MIT-licensed and list Python as a language. Their stated prerequisites differ: ai-engineering-from-scratch recommends programming experience, while learn-claude-code requires Python dependencies and an Anthropic API key to run examples.
Choose ai-engineering-from-scratch if you…
- want a structured route from AI and machine-learning foundations to practical applications and production topics.
- need to explore multiple AI domains or use focused paths for agents, MCP, or coding agents.
- prefer lessons and artifacts across several programming languages, depending on the topic.
Choose learn-claude-code if you…
- want to study coding-agent infrastructure through small, progressive examples.
- need to explore mechanisms such as permissions, memory, context handling, and agent coordination.
- can work with Python and an Anthropic API key for the runnable examples.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.