rohitg00/ai-engineering-from-scratch
ai-engineering-from-scratch
Learn AI Engineering! Learn it. Build it. Ship it for others.
GitHub metrics
- Stars
- 68K
- +5.1K this week
- Forks
- 12K
- 30-day growth
- —
- Open issues
- 17
| Day | GitHub stars |
|---|---|
| 2026-10-04 | 63150 |
| 2026-10-10 | 66334 |
| 2026-10-13 | 68299 |
What it does
AI Engineering from Scratch is a free, MIT-licensed course on GitHub that teaches how AI systems work by having you write each piece yourself, starting with linear algebra and ending with multi-agent systems and production infrastructure.
The material is split into 20 phases and 523 lessons, with code in Python, TypeScript, Rust and Julia. Each lesson folder holds a written explanation, runnable code and an outputs directory. The pattern is to build an algorithm such as backpropagation, a tokenizer, attention or an agent loop from plain math first, and only then run the same idea through a library like PyTorch or scikit-learn. Lessons end with something you keep: a prompt, a SKILL.md file, an agent or an MCP server. The repository holds 396 skills and 99 prompts produced this way, plus a script that copies them into an agent's skills folder.
There are three ways to follow it. You can read lessons on the website with no setup, clone the repository and run the code locally, or install the course's tutor skills into a coding agent such as Claude Code or Codex. Those skills run a placement quiz, write a study plan to LEARNING.md and teach one lesson per session. Separate tracks prepare for the four Claude certification exams and the MCP Associate exam; the README says these are independent and not affiliated with the exam bodies.
Why it matters
Most AI learning material comes in disconnected pieces, so people end up calling models they cannot explain. This course puts the theory and the engineering in one ordered sequence and asks you to implement each technique before using the library version. The agent-skill tutor is unusual for a free course: it keeps progress in files in your project, so a coding agent can resume where you stopped and quiz you per phase.
Main features
- 20 phases and 523 lessons, from math foundations to capstone projects
- Code in Python, TypeScript, Rust and Julia
- Each lesson builds a technique from scratch, then repeats it with a library
- Tutor skills for coding agents: placement quiz, per-lesson teaching and phase quizzes
- Lesson outputs include 396 skills and 99 prompts, installable with a script
- Focused MCP and Agent Skills learning paths
- Certification prep tracks for Claude exams and the MCP Associate exam
- Core curriculum is built into six EPUB and PDF volumes on each release
Who it's for
- Programmers who want to understand models, not only call APIs
- Engineers moving into LLM, agent or MCP work who want a structured path
- Self-learners preparing for Claude or MCP Associate certification exams
- Instructors looking for MIT-licensed material they can fork for a class
Strengths
- Free and MIT-licensed, with all 523 lessons marked complete in the roadmap
- Implements each method by hand before showing the library version
- Readable on the web, runnable from a clone, or taught through an agent
- Every lesson leaves behind a reusable prompt, skill, agent or MCP server
Limitations
- A long commitment: the README estimates about 342 hours, while the roadmap totals about 1,081
- Lesson pages in other languages are machine-translated; English is the canonical version
- Agent tutor labs need Node.js, npx, python3, a supported host and a writable skills folder
- Certification tracks are unofficial and do not guarantee a passing score
Getting started
Lessons can be read on the website without installing anything. To use the tutor inside a coding agent, check that npx works, then add the course skills and pick a host and scope when the installer asks.
npx --version
npx skills add rohitg00/ai-engineering-from-scratch
Requirements: Ability to write code (Python helps); Node.js and npx to install the tutor skills; python3 and a local clone to run lesson code and labs.
Always follow the official instructions in the README on GitHub. This overview is our summary, not a copy.
Sources
- rohitg00/ai-engineering-from-scratchRepositoryPrimarygithub.com
- AI Engineering from ScratchOfficial sitePrimaryaiengineeringfromscratch.com
- github.com/rohitg00/ai-engineering-from-scratch/blob/main/ROADMAP.mdRepositoryPrimary
Alternatives to ai-engineering-from-scratch
ECC is an open-source system that adds reusable engineering workflows, skills, agents, memory, rules, hooks and security checks to coding agents. Its main path is Claude Code, with guided installation also available for Codex and Kimi Code. The repository also contains adapters for other coding agents, but the project warns that support is not equal across them. The current repository includes 68 agents, 293 skills and 94 legacy command shims. The supplied workflows cover tasks such as planning, testing, implementation, review, build repair, security and architecture. ECC also includes AgentShield integration for scanning agent configuration, prompts, hooks, MCP settings, permissions, secrets and related files. Hooks and memory can enforce checks outside the prompt, store session information and support its continuous-learning system. The easiest starting point is the ecc-universal guided installer. Claude Code setup needs Node.js 18 or newer, Git and Claude Code 2.1 or newer on PATH. The multi-agent installer can configure Claude Code, Codex and Kimi Code in one reviewed flow. Kimi installation is more limited: ECC writes managed project files but does not configure Kimi hooks, model or provider settings, or authentication.
- Stars
- 278K
- Language
- JavaScript
- License
- MIT
- Momentum
- +2.2% 7dEstablished
UI UX Pro Max is an agent skill that hands coding assistants a searchable library of design guidance, so a request such as a landing page for a spa comes back with a matching style, color palette, font pairing and page structure. It installs into Claude Code, Cursor, Windsurf, GitHub Copilot, Codex, Gemini CLI, Kiro and about a dozen more assistants, through the Claude Code plugin marketplace or the uipro command from the ui-ux-pro-max-cli npm package. Under the hood it is a set of CSV datasets and a Python search script that ranks entries with BM25. The README counts 79 searchable UI styles (50 active), 192 palettes tied to 192 product types, 74 font pairings, 25 chart types, 119 UX guidelines and advice for 22 stacks, from React and Next.js to SwiftUI, Flutter and WPF. Version 2.0 added a design system generator that merges those searches into one recommendation, with anti-patterns to avoid and a pre-delivery checklist covering contrast, focus states and reduced motion. You can save the result as a master file with per-page overrides that the agent reads in later sessions. In most supported assistants the skill switches on by itself for UI requests. Kiro, Copilot, Roo Code and KiloCode use the /ui-ux-pro-max slash command instead. A paid premium edition with brand and asset features is sold separately on uupm.cc.
- Stars
- 135K
- Language
- Python
- License
- MIT
- Momentum
- +1.9% 7dEstablished
Ponytail is a rule set and skill collection that pushes an AI coding agent to write as little code as a task needs. It ships as a plugin for Claude Code, Codex, GitHub Copilot CLI, Gemini CLI and several other agent hosts, and as plain rules files for editors such as Cursor, Windsurf and Cline. Before writing anything, the agent works down a fixed ladder: drop the feature if it does not need to exist, reuse what the codebase already has, then try the standard library, a native platform feature, an installed dependency and a one-line answer. New code comes only after all of those fail. The README is firm that validation, error handling, security and accessibility are off limits for cutting. Its example: asked for a date picker, the agent reaches for a native <input type="date"> instead of adding a library and a wrapper component. The plugin adds commands to set the intensity (lite, full, ultra or off), to review a diff or a whole repository for over-engineering, and to collect deferred shortcuts into a ledger. The maintainer publishes a benchmark: across twelve feature tasks on a FastAPI and React template with Haiku 4.5, the README reports about 54% fewer lines of code than the same agent without the skill, plus smaller drops in tokens, cost and time.
- Stars
- 162K
- Language
- JavaScript
- License
- MIT
- Momentum
- +5.7% 7dEstablished
Agent Skills is a repository of 25 Markdown workflows for AI coding agents, covering software work from specification and planning through testing, review, performance, security, deployment and documentation. Each skill is a SKILL.md process with triggers, steps, red flags, verification criteria and common rationalizations to counter. The pack can be installed with the skills CLI or integrated with tools including Claude Code, Cursor, Gemini CLI, OpenCode, GitHub Copilot and Codex. Nine slash commands map development tasks to skills. /build auto can generate a plan and implement its tasks after one approval, while stopping on failures or risky steps. This suits teams that want an agent to follow a defined engineering process instead of relying on isolated prompts. The repository also contains four review personas, shared checklists, evaluation cases and host-specific adapters. One installation limitation matters: installing a single skill through npx does not copy the repository-level references/ directory, so links to shared checklists are unavailable unless those files are supplied another way.
- Stars
- 106K
- Language
- JavaScript
- License
- MIT
- Momentum
- +4.9% 7dEstablished
Related AI tools
Ollama
Models & inference
An open-source tool and API for running open models on your own machine or on Ollama's cloud.
Open sourceFree tierAPIVerifiedLM Studio
Models & inference
Desktop apps for running open LLMs locally, with a local API server and Bionic, an agent for documents, code and automation.
FreemiumFree tierAPIVerifiedElevenLabs
Audio & speech
AI audio platform for text to speech, voice cloning, dubbing, music and voice agents, with a web app and a developer API.
FreemiumFree tierAPIVerifiedGemini Notebook
Writing & research
Google's source-grounded research notebook, formerly NotebookLM: add your documents and get cited answers, summaries and Audio Overviews.
FreemiumFree tierVerifiedLangfuse
Evaluation & observability
Open-source tracing, evaluation and prompt management for LLM apps and agents, as a cloud service or self-hosted.
Open sourceFree tierAPIVerifiedCommunicate
Business & productivity
AI support agent for website chat that answers from your help content with citations, runs approved tasks and hands off to people.
PaidAPIVerified