OSS
ai-engineer-notebooks teaches agents and RAG from raw API calls, deliberately refusing LangChain, on the free Groq tier
calmrocks/ai-engineer-notebooks drew 111 points on Hacker News and sits at 440 stars, created August 11 and pushed again today. It covers 12 sections from model APIs through structured output, RAG, evals, agent loops, LoRA versus fine-tuning, security, LLMOps, serving and system design, plus three case studies and a capstone. The stated stance is that you write the agent loop, RAG and evals from raw API calls first so you understand what LangChain and LlamaIndex actually do before reaching for them; everything runs on the free Groq API with no credit card, GPU sections on Colab's free T4. MIT.
Source
↳ Follow the thread