Free GitHub "AI university" ships a 7-week path from Docker to production RAG and LangGraph agents
mdancho84 · x · 2026-11-19
mdancho highlights a free "AI university" built on GitHub — not tutorials or theory, but step-by-step construction of full real-world AI systems:
- Week 1: Docker, FastAPI, PostgreSQL, OpenSearch, Airflow infrastructure
- Week 2: automated pipelines fetching and parsing arXiv papers
- Week 3: build your own BM25 search engine
- Week 4: hybrid search combining semantic and keyword retrieval
- Week 5: full RAG system with local LLM, streaming responses, Gradio UI
- Week 6: production-ready with Langfuse monitoring and Redis caching
- Week 7: agentic RAG with LangGraph plus a Telegram bot
The curriculum uses an "arXiv Paper Curator" as the running project, covering ingestion, storage, retrieval, and observability with architecture diagrams. The post ends with a promo for the author's free workshop (500 seats).
More from coding & agent
- AI Engineer summit: the job shifted to managing agent sessions and hidden assumptions — TheTuringPost · 2026-11-19
- HF boosts Qwen3.8-27B from 39% to 65% on SWE-bench Pro with RL and one small LoRA — TheTuringPost · 2026-11-19
- Are agents bad at software design because human software is bad? — hargup13 · 2026-11-19
- VS Code docs: how to manage agent sessions in Chat view and Agents window — adnan_hashmi · 2026-11-19
- One prompt built a full Call of Duty clone — thisdudelikesAI · 2026-11-19
- Affordance open-sourced: an agent harness that runs agents like a browser renders web pages — cneuralnetwork · 2026-11-19