rohitg00/ai-engineering-from-scratch

From the creator of Agent Memory - #1 Persistent memory ⭐ which naturally works with any agents or chat assistants.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

How this works

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. You ship a chatbot but can't explain its loss curve. You hook a function to an agent but can't say what attention does inside the model that's calling it.

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 gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time PyTorch shows up, you already know what it's doing under the hood.

Each lesson runs the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste deploys, no hand-holding. Free, open source, and built to run on your own laptop.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

The shape of the curriculum

Twenty phases stack on top of each other. Math is the floor. Agents and production are the roof. Skip ahead if you already know the lower layers, but don't skip and then wonder why something at the top is breaking.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'12px'}}}%%
flowchart TB
  P0["Phase 0 — Setup & Tooling"] --> P1["Phase 1 — Math Foundations"]
  P1 --> P2["Phase 2 — ML Fundamentals"]
  P2 --> P3["Phase 3 — Deep Learning Core"]
  P3 --> P4["Phase 4 — Vision"]
  P3 --> P5["Phase 5 — NLP"]
  P3 --> P6["Phase 6 — Speech & Audio"]
  P3 --> P9["Phase 9 — RL"]
  P5 --> P7["Phase 7 — Transformers"]
  P7 --> P8["Phase 8 — GenAI"]
  P7 --> P10["Phase 10 — LLMs from Scratch"]
  P10 --> P11["Phase 11 — LLM Engineering"]
  P10 --> P12["Phase 12 — Multimodal"]
  P11 --> P13["Phase 13 — Tools & Protocols"]
  P13 --> P14["Phase 14 — Agent Engineering"]
  P14 --> P15["Phase 15 — Autonomous Systems"]
  P15 --> P16["Phase 16 — Multi-Agent & Swarms"]
  P14 --> P17["Phase 17 — Infrastructure & Production"]
  P15 --> P18["Phase 18 — Ethics & Alignment"]
  P16 --> P19["Phase 19 — Capstone Projects"]
  P17 --> P19
  P18 --> P19

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

The shape of a lesson

Each lesson lives in its own folder, with the same structure across the entire curriculum:

phases/<NN>-<phase-name>/<NN>-<lesson-name>/
├── code/      runnable implementations (Python, TypeScript, Rust, Julia)
├── docs/
│   └── en.md  lesson narrative
└── outputs/   prompts, skills, agents, or MCP servers this lesson produces

Every lesson follows six beats. The Build It / Use It split is the spine — you implement the algorithm from scratch first, then run the same thing through the production library. You understand what the framework is doing because you wrote the smaller version yourself.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'13px'}}}%%
flowchart LR
  M["MOTTO<br/><sub>one-line core idea</sub>"] --> Pr["PROBLEM<br/><sub>concrete pain</sub>"]
  Pr --> C["CONCEPT<br/><sub>diagrams &amp; intuition</sub>"]
  C --> B["BUILD IT<br/><sub>raw math, no frameworks</sub>"]
  B --> U["USE IT<br/><sub>same thing in PyTorch / sklearn</sub>"]
  U --> S["SHIP IT<br/><sub>prompt · skill · agent · MCP</sub>"]

Getting started

Three ways in. Pick one.

Option A — read. Open any completed lesson on aiengineeringfromscratch.com or expand a phase under Contents. No setup, no cloning.

Option B — clone and run.

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

*Option C — find your level (recommended).* Skip ahead intelligently. Inside Claude, Cursor, Codex, OpenClaw, Hermes, or any agent with the curriculum skills installed:

/find-your-level

Ten questions. Maps your knowledge to a starting phase, builds a personalized path with hour estimates. After each phase:

/check-understanding 3        # quiz yourself on phase 3
ls phases/03-deep-learning-core/05-loss-functions/outputs/
# ├── prompt-loss-function-selector.md
# └── prompt-loss-debugger.md

Prerequisites

• You can write code (any language; Python helps).
• You want to understand how AI actually works, not just call APIs.

Built-in agent skills (Claude, Cursor, Codex, OpenClaw, Hermes)

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Read it as a book

The whole course compiles into a six-volume book series. EPUB and PDF are built by CI from the same lesson sources and attached to every GitHub release; the links below always resolve to the newest release. Volume numbers index the series, not versions: each copy carries a dated edition stamp, and older editions stay downloadable from their release.

The book is the snapshot; this repository is the living edition. Every chapter ends with links back to the lesson's animated figures, quiz, and runnable code. Build locally with python3 scripts/build_book.py (pandoc required); pipeline details in book/README.md.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Every lesson ships something

Other curricula end with "congratulations, you learned X." Each lesson here ends with a reusable tool you can install or paste into your daily workflow.

FIG_002 · A worked sample

Phase 14, lesson 1: the agent loop. ~120 lines of pure Python, no dependencies.

code/agent_loop.py   build it

def run(query, tools):
    history = [user(query)]
    for step in range(MAX_STEPS):
        msg = llm(history)
        if msg.tool_calls:
            for call in msg.tool_calls:
                result = tools[call.name](https://github.com/rohitg00/ai-engineering-from-scratch/blob/main/**call.args)
                history.append(tool_result(call.id, result))
            continue
        return msg.content
    raise StepLimitExceeded

outputs/skill-agent-loop.md   ship it

---
name: agent-loop
description: ReAct-style loop for any tool list
phase: 14
lesson: 01
---

Implement a minimal agent loop that...

outputs/prompt-debug-agent.md

You are an agent debugger. Given the trace
of an agent run, identify the step where
the agent went wrong and explain why...

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Contents

Twenty phases. Click any phase to expand its lesson list.

Phase 0: Setup & Tooling 12 lessons

Each Phase 14 workbench lesson (31-42) ships a mission.md briefing the agent before it opens the full lesson docs.

Deep-build tracks — multi-lesson series that build a complete subsystem from scratch.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

The toolkit

Every lesson produces a reusable artifact. By the end you have:

outputs/
├── prompts/      prompt templates for every AI task
└── skills/       SKILL.md files for AI coding agents

Install them with npx skills add. Plug them into Claude, Cursor, Codex, OpenClaw, Hermes, or any agent that reads a SKILL.md / AGENTS.md directory. Real tools, not homework.

Install every course skill into your agent

The repo ships 388 skills and 99 prompts under phases/**/outputs/.

Recommended: install via skills.sh. No clone, no Python, detects your agent's skills directory automatically:

npx skills add rohitg00/ai-engineering-from-scratch                       # every skill
npx skills add rohitg00/ai-engineering-from-scratch --skill agent-loop    # one skill
npx skills add rohitg00/ai-engineering-from-scratch --phase 14            # one phase

skills writes to whichever directory your agent picks up: .claude/skills/, .cursor/skills/, .codex/skills/, OpenClaw's skills folder, Hermes's bundle path, or any SKILL.md-aware tool. One command, every agent.

Advanced: offline / custom layout via scripts/install_skills.py. Requires cloning the repo. Useful when you need tag filters, dry-runs, or a non-default layout:

python3 scripts/install_skills.py <target>                                 # every skill, default --layout skills (nested)
python3 scripts/install_skills.py <target> --layout skills                 # same as above, explicit
python3 scripts/install_skills.py <target> --type all                      # skills + prompts + agents
python3 scripts/install_skills.py <target> --phase 14                      # one phase only
python3 scripts/install_skills.py <target> --tag rag                       # filter by tag
python3 scripts/install_skills.py <target> --layout flat                   # flat files
python3 scripts/install_skills.py <target> --dry-run                       # preview without writing
python3 scripts/install_skills.py <target> --force                         # overwrite existing files

<target> is the skills directory for your agent (examples: ~/.claude/skills/, ~/.cursor/skills/, ~/.config/openclaw/skills/, .skills/, or any path your agent reads).

By default the script refuses to overwrite an existing destination and exits with code 1 after listing every colliding path. Use --dry-run to preview collisions or --force to overwrite. Every non-dry-run run writes a manifest.json in the target with the full inventory grouped by type and phase. Pick the layout your agent reads:

Drop the agent workbench into your own repo

The Phase 14 capstone ships a reusable Agent Workbench pack (AGENTS.md, schemas, init / verify / handoff scripts). Scaffold it into any repo with:

python3 scripts/scaffold_workbench.py path/to/your-repo            # full pack + seeds
python3 scripts/scaffold_workbench.py path/to/your-repo --minimal  # skip docs/
python3 scripts/scaffold_workbench.py path/to/your-repo --dry-run  # preview only
python3 scripts/scaffold_workbench.py path/to/your-repo --force    # overwrite

You get the seven workbench surfaces wired up, a starter task_board.json, and a fresh agent_state.json at schema_version: 1. From there: edit the task, edit AGENTS.md, run scripts/init_agent.py, hand the contract to your agent. The pack source lives at phases/14-agent-engineering/42-agent-workbench-capstone/outputs/agent-workbench-pack/.

Browse the entire course as JSON

scripts/build_catalog.py walks every phase, every lesson, every artifact on disk and writes catalog.json at the repo root. One file, every course truth.

python3 scripts/build_catalog.py               # writes <repo>/catalog.json
python3 scripts/build_catalog.py --stdout      # to stdout, do not touch repo
python3 scripts/build_catalog.py --out path/to/file.json

The catalog is filesystem-derived, not README-derived, so counts always match what is actually on disk. Use it for site builds, downstream tooling, or to verify the README counts have not drifted. Schema is documented at the top of the script.

A GitHub Action (.github/workflows/curriculum.yml) rebuilds catalog.json on every PR and fails the build if the committed file is stale. After editing any lesson, run python3 scripts/build_catalog.py and commit the result, or CI will reject the PR. The same workflow runs audit_lessons.py in warn-only mode (so existing drift does not block contributors).

Smoke-check every lesson's Python code

scripts/lesson_run.py byte-compiles every .py file under each lesson's code/ directory. Default mode is syntax-check only — no execution, no API keys, no heavy ML deps required. Catches the regressions contributors introduce most often (bad indentation, broken f-strings, stray edits).

python3 scripts/lesson_run.py                  # syntax-check the whole curriculum
python3 scripts/lesson_run.py --phase 14       # one phase only
python3 scripts/lesson_run.py --json           # JSON report on stdout
python3 scripts/lesson_run.py --strict         # exit 1 if any lesson fails
python3 scripts/lesson_run.py --execute        # actually run, 10s timeout per lesson

--execute runs each lesson's code/main.py (or the first .py file) with a 10-second timeout. Lessons whose entry file starts with a # requires: pkg1, pkg2 comment listing non-stdlib deps are skipped with reason needs <deps>. The script is opt-in and not wired into CI.

Stdlib only, Python 3.10+. Set LINK_CHECK_SKIP=domain1,domain2 to override the default skip-list (twitter.com, x.com, linkedin.com, instagram.com, medium.com — domains that aggressively block automated HEAD/GET).

Where to start

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Why this matters now

• Attention Is All You Need — Vaswani et al., 2017 → Phase 7
• Language Models are Few-Shot Learners (GPT-3) → Phase 10
• Denoising Diffusion Probabilistic Models → Phase 8
• InstructGPT / RLHF → Phase 10
• Direct Preference Optimization → Phase 10
• Chain-of-Thought Prompting → Phase 11
• ReAct: Reasoning + Acting in LLMs → Phase 14
• Model Context Protocol — Anthropic → Phase 13

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Contributing

Before submitting a lesson, run the invariant check:

python3 scripts/audit_lessons.py           # full curriculum
python3 scripts/audit_lessons.py --phase 14  # single phase
python3 scripts/audit_lessons.py --json    # CI-friendly output

Exit code is non-zero when any rule fails. Rules (L001–L010) validate directory shape, docs/en.md presence + H1, code/ non-emptiness, quiz.json schema (rejects the legacy q/choices/answer keys that caused issue #102), and relative links inside lesson docs.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Sponsor the work

Free, MIT-licensed, 503 lessons. The curriculum is maintained on sponsorship alone. Cash only.

Reach (verified 2026-05-14): 55,593 monthly visitors · 90,709 page views · 7.5K stars · Twitter/X is the #1 acquisition channel.

Current sponsors: CodeRabbit · iii

Full rate card, hard rules, pricing anchors, and reach data: SPONSORS.md. Sign up via GitHub Sponsors.

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

Star history

If this manual helped you, star the repo. It keeps the project alive.

License

MIT. Use it however you want — fork it, teach it, sell it, ship it. Attribution appreciated, not required.

Maintained by Rohit Ghumare and the community.