ai-engineering-from-scratch vs ai-for-beginners
Two of the top projects in Learning and cookbooks, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
ai-engineering-from-scratch
Hands-on AI engineering curriculum with 542 lessons across 20 phases
ai-for-beginners
24-lesson AI curriculum with notebooks in PyTorch and TensorFlow
Verdict
ai-engineering-from-scratch ranks higher, 91 to 81. Of the 4 score parts we measure for both, ai-engineering-from-scratch leads on 3, ai-for-beginners on none and 1 is even.
- Adoptionai-engineering-from-scratch leads by 2 points, 94 to 92: close to even.
- FreshnessEven at 100.
- Maintenanceai-engineering-from-scratch leads by 29 points, 96 to 67: a wide gap.
- Agent-readyai-engineering-from-scratch leads by 15 points, 45 to 30: a wide gap.
Pick ai-engineering-from-scratch if you are
Developers learning to build AI systems from first principles
- 542 lessons in 20 phases, each with runnable code in the repo
- Three staged projects with reference solutions and local graders
Pick ai-for-beginners if you are
Beginners learning AI and deep learning through runnable notebooks
- Most lessons have notebooks in both PyTorch and TensorFlow
- Covers symbolic AI, genetic algorithms and multi-agent systems alongside deep learning
| What we compare | ai-engineering-from-scratch | ai-for-beginners |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 94, widely used | 92, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 96, healthy | 67, fair |
| Agent-ready | 45, minimal | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 78.6k | 70.7k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Nov 2026 | None published |
| Language | Python | Jupyter Notebook |
| Docker | No | No |
| GPU | Not stated | Not stated |
| arm64 or Apple Silicon | Mentioned | Not stated |
ai-engineering-from-scratch
A course where learners implement model internals, retrieval pipelines and agent runtimes in Python, TypeScript, Rust and Julia, from math foundations to LLM engineering and agents. Lessons can be read on the website, taught by coding-agent skills installed with `npx skills add`, or run locally. Three projects (retrieval evaluation, agent trace debugger, tool call firewall) ship with staged starters and local graders.
Who it is for: Developers learning to build AI systems from first principles
Strengths
- 542 lessons in 20 phases, each with runnable code in the repo
- Three staged projects with reference solutions and local graders
- Agent skills act as a tutor with placement and per-phase quizzes
- Website lessons need no setup; early local lessons are dependency-free
Weaknesses
- Tutor skills need Node.js, npx, python3 and a supported coding-agent host
- Hardware needs for later phases (GPU, RAM) are unknown from the README excerpt
- Large curriculum with no single linear path; learner must pick a route
- Projects need different toolchains: Python, Node.js 22.18+ and Rust
- Needs Python 3.10+, Node.js 22.18+ (agent trace debugger project), Rust (tool call firewall project), npx (tutor skills)
ai-for-beginners
A Microsoft course covering symbolic AI, neural networks, computer vision, NLP, genetic algorithms, reinforcement learning, multi-agent systems and AI ethics. Each lesson pairs text with notebooks in PyTorch, Keras or TensorFlow, and many have labs. Notebooks can be run locally or through Binder.
Who it is for: Beginners learning AI and deep learning through runnable notebooks
Strengths
- Most lessons have notebooks in both PyTorch and TensorFlow
- Covers symbolic AI, genetic algorithms and multi-agent systems alongside deep learning
- Many lessons include labs; Binder badge allows running without local setup
- Translated into 50+ languages with Co-op Translator
Weaknesses
- Excludes generative AI services, chatbots and deep math; points to other courses
- README says neural architecture coverage may lag the state of the art
- Full clone is large because of translations; sparse checkout is needed
- Some lessons, such as multi-agent systems, list no notebook
- Needs Jupyter, PyTorch, TensorFlow, Keras, OpenCV
More in Learning and cookbooks
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.