Free "AI University" on GitHub: 7 weeks from Docker to agentic RAG
mdancho84 · x · 2026-10-22
A free "AI university" on GitHub teaches real-world AI systems by building one step by step over 7 weeks: Docker/FastAPI/PostgreSQL/OpenSearch/Airflow infrastructure, automated arXiv data pipelines, a from-scratch BM25 search engine, chunking + hybrid semantic/keyword retrieval, a full RAG system with local LLM and Gradio UI, production hardening with Langfuse tracing and Redis caching, and finally agentic RAG with LangGraph plus a Telegram bot. The capstone is an arXiv paper curator. Note the post also plugs the author's free workshop (promo).
More from coding & agent
- From loops to graphs: why complex agent systems need Graph Engineering over agentic loops — Pavan_Belagatti · 2026-10-23
- Investor Matt Slotnick lays out three startup theses, led by an app server for agent apps — matt_slotnick · 2026-10-23
- Reward-Rate Policy Gradient: RL that optimizes MLE agents' reward per unit time — sherryyangML · 2026-10-23
- MLE-World Learns From Past ML Experiment Traces, Gaining 19% on MLE-bench Lite — sherryyangML · 2026-10-23
- You don't need frontier models: open-weight LLMs easily find code vulnerabilities — DanielLockyer · 2026-10-23
- SwiftUI voice assistant demo chains Gemini STT, LLM and TTS models in one pipeline — amos_gyamfi · 2026-10-23