ai-engineering-from-scratch vs rag_techniques
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
rag_techniques
Collection of 42 runnable notebooks implementing RAG techniques
Verdict
ai-engineering-from-scratch ranks higher, 89 to 79. Of the 4 score parts we measure for both, ai-engineering-from-scratch leads on 2, rag_techniques on none and 2 are even.
- Adoptionai-engineering-from-scratch leads by 16 points, 89 to 73: a wide gap.
- FreshnessEven at 100.
- Maintenanceai-engineering-from-scratch leads by 16 points, 92 to 76: a wide gap.
- Agent-readyEven at 45.
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 rag_techniques if you are
Engineers learning and comparing RAG techniques through runnable code
- 42 notebooks grouped by category: foundational, query enhancement, context enrichment, and more
- Colab badge on listed notebooks, so no local setup is needed to run them
| What we compare | ai-engineering-from-scratch | rag_techniques |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 89, widely used | 73, popular |
| Freshness | 100, active | 100, active |
| Maintenance | 92, healthy | 76, fair |
| Agent-ready | 45, minimal | 45, minimal |
| Facts from GitHub and the README | ||
| Stars | 76.2k | 30.2k |
| License | MIT (permissive) | custom license (read the license) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Oct 2026 |
| 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)
rag_techniques
A repository of Jupyter notebooks, each implementing one RAG technique, from basic RAG and CSV RAG to HyDE, proposition chunking, contextual chunk headers, MemoRAG and RAG evaluation. Notebooks open in GitHub or Colab. It is a teaching resource with code and references, not a library or a deployable service.
Who it is for: Engineers learning and comparing RAG techniques through runnable code
Strengths
- 42 notebooks grouped by category: foundational, query enhancement, context enrichment, and more
- Colab badge on listed notebooks, so no local setup is needed to run them
- Covers chunking, query transformation, reliability and evaluation, with video explainers for some
- Recent additions include MemoRAG, Open-RAG-Eval and JSON RAG
Weaknesses
- Notebooks, not an installable package or service; code must be adapted for production
- License reported as NOASSERTION, so reuse terms are unclear
- README carries heavy sponsor, book and newsletter promotion
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.