ai-engineering-from-scratch
AI Engineering From Scratch is a free, open source course that teaches how AI models, retrieval systems, and agents work by building them.
What it is good for
- Learning how AI agent runtimes work by writing the code
- Testing retrieval pipelines and inspecting their failures
- Building a tool call firewall with role checks and approvals
- Following a structured path from AI basics to agent delivery
At a glance
- Who it is for
- Setup
- Works in your browser or phone
Level 1 of 5. Nothing to install. Open a website or app and start.
- Cost
- Free and open source
- Type
- List or tutorial
- Tasks
- Works with
- Claude Code, Codex, Cursor
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 76,320
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is ai-engineering-from-scratch free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use ai-engineering-from-scratch?
- No. Nothing to install. Open a website or app and start.
- What does ai-engineering-from-scratch work with?
- According to its own documentation, it works with Claude Code, Codex, and Cursor.
- What is ai-engineering-from-scratch good for?
- Learning how AI agent runtimes work by writing the code, testing retrieval pipelines and inspecting their failures, building a tool call firewall with role checks and approvals, and following a structured path from AI basics to agent delivery.
Similar agents to ai-engineering-from-scratch
- claude-howto
claude-howto is a visual, example-driven guide that teaches developers to use Claude Code features with copy-paste templates.
- agentskills
agentskills is a specification and documentation set for Agent Skills, a standard format that gives AI agents reusable instructions for specialized tasks.
- Open Intelligent UI
Open Intelligent UI is a chat interface that turns questions into explanations, comparisons, and working tools for people exploring ideas.
- rederive
rederive is a skill that teaches you a codebase by asking you to design its parts yourself, for developers learning unfamiliar code.
- caveman
Caveman is a skill and proxy that cuts token use by making coding agents answer tersely and shrink the text they read, for developers and heavy AI users.
- Scientific Agent Skills
Scientific Agent Skills is a collection of 177 skills that teaches an AI agent scientific tools and databases for research work.