# jamwithai/production-agentic-rag-course

> A hands-on course for building a production-grade RAG system: from infrastructure and an arXiv ingestion pipeline to hybrid search, agentic RAG with LangGraph, and a Telegram bot.

- Magnitude: 4.4 out of 10 — Breakout
- Stars: 9,318 total · +84 stars today, ≈ 137 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2025-08-06 · Last push: 2026-06-05
- GitHub: https://github.com/jamwithai/production-agentic-rag-course · Page: https://gitnova.dev/en/r/jamwithai/production-agentic-rag-course

## Useful for

- Deploy the full RAG stack via Docker Compose with FastAPI, PostgreSQL, OpenSearch, and Airflow
- Build a pipeline to fetch and parse papers from arXiv
- Implement hybrid BM25 and semantic search with chunking

## Why it’s here

- 84 stars so far today, about 137 expected by the end of the day. The usual pace is 10 per day, so that's 14× as much.
- Over the last two days the pace is 17× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- GitHub Trending today: #17, +192 stars.
- GitHub Trending Python today: #3, +192 stars.
- About 31 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,061
- Issues and pull requests: 50
- Watchers: 85
- Average over the last week: 64 per day
- Usual pace: 10 per day
- Stars in the last hour (measured): 18
- Latest release: week7.0 (2025-11-26)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-04 … 2026-10-03: 10, 7, 3, 117, 131, 29, 7, 14, 19, 9, 14, 3, 4, 3, 4, 2, 4, 3, 2, 3, 2, 3, 3, 6, 4, 6, 64, 57, 170, 84

## Spotted in now

- GitHub Trending today: #17, +192 stars
- GitHub Trending Python today: #3, +192 stars

## More in this category

1. **Niko1221/Strata** — 8.5 · Breakout · Language models · C++ · +908 stars today, ≈ 1,496 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md
2. **StayLameBro/backburner** — 5.4 · Early signal · Language models · Objective-C++ · +59 stars today, ≈ 97 by evening
   A llama.cpp fork that plugs an iPhone into a Mac over USB-C and splits the work: the Mac runs layers 1-40, the iPhone runs 41-64 on its GPU, speeding up prefill and allowing context up to 196k-229k tokens. Aimed at people running…
   Full card: https://gitnova.dev/en/r/StayLameBro/backburner.md
3. **Kutuyyy/Leaked-System-Prompt-AI** — 5.0 · Early signal · Language models · +28 stars today, ≈ 51 by evening
   A repository that collects and documents system prompts, instructions, and tool definitions of major AI models and agent platforms (OpenAI, Anthropic, Google, Cursor, Devin, etc.) for studying their behavior.
   Full card: https://gitnova.dev/en/r/Kutuyyy/Leaked-System-Prompt-AI.md
4. **Vibra-Ingenn/Janus** — 4.8 · Early signal · Language models · Go · +8 stars today, ≈ 17 by evening
   Local LLM server in Go: runs .gguf models via llama.cpp (Vulkan or CPU) and exposes an OpenAI-compatible API with a web UI and built-in tools.
   Full card: https://gitnova.dev/en/r/Vibra-Ingenn/Janus.md
5. **Edge0-AI/Edge0** — 4.7 · Breakout · Language models · Python · +111 stars today, ≈ 181 by evening
   An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-03 15:15 UTC, updated every 30 minutes.