this is free f*cking gold for AI engineers 10 repos i'd actually keep, from python fundamentals to LLMs, agents and production AI. skip the random tutorials 1. Python-100-Days - a 100 day path through fundamentals, data analysis, web dev ↳ 2. Generative AI for Beginners - LLM basics, prompting,... RAG, agents, fine-tuning ↳ 3. LLMs from Scratch - build one yourself: tokenization, attention, transformers, training ↳ 4. ML for Beginners - 12 weeks, 26 lessons of classical ML ↳ 5. OpenAI Cookbook - working examples to go from learning to building ↳ 6. Stable Diffusion - the original implementation and research code ↳ 7. AI Agents for Beginners - tool use, RAG, agent frameworks, multi-agent systems ↳ 8. AI for Beginners - 12 weeks, 24 lessons: neural nets, vision, NLP ↳ 9. LLM App - RAG pipelines, enterprise search, real-time data, vector search ↳ 10. Segment Anything - Meta's foundation model for image segmentation ↳ pick by where you are: > python -> Python-100-Days > ML -> ML-For-Beginners > LLMs -> LLMs-from-scratch > agents -> AI-Agents-for-Beginners > building -> OpenAI Cookbook, LLM App > vision -> Segment Anything pick one, build something, then move to the nextshow more

hmm thats for sure

LLMs from scratch is the one that actually matters here, building attention and training yourself is the difference between knowing what a token is and knowing why context length costs what it does.

@polydao love that Python-100-Days is on this list. I hit a wall with fundamentals when building my own stuff. This would've saved me so much time.

The gap most of these repos leave is the boring part: what an agent is allowed to spend, sign, or call. Model code you can learn in a weekend. Permission and settlement design is where the r

10 repos saving all rn

Curated lists are convenient, but deep understanding beats saving repos. How many of these have you actually used in production?

这份比收藏夹里那堆教程清单靠谱多了

This is exactly why AI literacy matters in 2025 🤖 More insights like this → @@notreal_dreams

These repos are absolute gold for anyone building with AI. Thanks for curating this list! 🧠

next time i will use your information for my work as well

Strong list. One gap worth noting: most of these stop at building. Production work also needs data lineage, PII handling, and evaluation tooling, which are rarely taught alongside model code.

saving this gem

Honestly, filtering out the noise is the hardest part of learning right now. This is a solid list to actually build something real with.

saving

saved this instantly, absolute alpha list right here

A 100-day path is a solid foundation, but AI engineering is about messy problems. Which repo here forces you to debug real failures?