10 MCP, RAG and AI Agents Projects
...for AI Engineers.
10 MCP, RAG, and AI Agents Projects
~6 months back, we launched the AI Engineering Hub repo, and today, it crossed 10k+ stars on GitHub:
Here, we publish the code for the hands-on AI engineering newsletter issues. This repository is dedicated to:
In-depth tutorials on LLMs, MCPs, and RAGs.
Real-world AI agent applications.
Examples to implement, adapt, and scale in your projects.
It’s 100% open-source, packed with 70+ hands-on tutorials.
Today, we want to show you some of the best real-world projects we have published so far in this GitHub repo.
A small ask: If you love what we do, we would really appreciate it if you starred us on GitHub here: ​AI Engineering Hub​.
Won’t take more than 2 seconds. Thank you so much for your support.
#1) MCP-powered RAG over videos
Learn how to build a video RAG that ingests a video and lets you chat with it. It also fetches the exact video chunk where an event occurred.
#2) Corrective RAG
Corrective RAG improves RAG systems by introducing a self-assessment step on the retrieved documents to feed relevant context to the LLM during generation.
#3) Flight Finder
Most of the internet isn’t accessible via APIs. That’s why Agents need browsers to search, click, and reason on the web. Learn how to build a multi-agent best flight finder app powered by a browser.
#4) Agentic RAG
Build a RAG pipeline with agentic capabilities that can dynamically fetch context from different sources, like a vector DB and the internet.
#5) Human-like memory for Agents
If a memory-less AI Agent is deployed in production, every interaction with the Agent will be a blank slate. Learn how to build an AI Agent with human-like memory to solve this.
#6) Voice RAG Agent
Real-time voice interactions are becoming more and more popular in AI apps. Learn how to build a real-time Voice RAG Agent, step-by-step.
#7) Build the Fastest RAG stack
Make your RAG 40x faster and memory efficient using Binary Quantitation. It can query 36M+ vectors in less than 15 ms and generate a response at 430 t/s.
#8) Build your reasoning model
In this project, learn how to train your reasoning model like DeepSeek-R1.
#9) Multimodal RAG application
Build a 100% local RAG over complex real-world docs with images, tables, text, and complex layouts. Powered by DeepSeek Janus-Pro.
#10) MCP-powered deep researcher
ChatGPT has a deep research feature. It helps you get detailed insights on any topic. Learn how you can build a 100% local alternative to it.
There are many more of them (70+), and you can find them in the GitHub repo.
Check here: AI Engineering Hub (and do star it).
If you love what we do, we would really appreciate it if you starred us on GitHub here:Â AI Engineering Hub.
Won’t take more than 2 seconds. Thank you so much for your support.
👉 Over to you: What other projects would you like us to cover next?
Thanks for reading!