#1313th of 18 in Learning and cookbooks
ai-engineering-hub
Collection of 93 runnable AI tutorials on RAG, agents, MCP and fine-tuning
- Stars
- 38.3k
- License
- MIT
- Last commit
- Oct 2026
- Language
- Jupyter Notebook
32,193 on 25 Mar 202638,323 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A monorepo of about 93 example projects, mostly Jupyter notebooks and small apps, grouped into beginner, intermediate and advanced tiers. Topics include local OCR, RAG with LlamaIndex and Ollama, CrewAI and AutoGen agents, MCP servers, voice agents, model comparisons and fine-tuning with Unsloth. Each project sits in its own folder with its own dependencies.
Who it is for: Engineers learning to build RAG, agent and MCP apps from worked examples
Strengths
- Roughly 93 self-contained projects, each in its own folder
- Wide coverage: RAG, agents, MCP, voice, OCR, fine-tuning, evaluation
- Projects sorted into beginner, intermediate and advanced tiers
- MIT license; many examples run locally with Ollama and open models
Weaknesses
- No single install; each project has its own dependencies and setup
- Many examples need third-party API keys such as Firecrawl or AssemblyAI
- Example code, not a maintained library; 'production-ready' claim is unsupported
- No releases or versioning; project freshness and quality vary
What it needs
- Needs Ollama, LlamaIndex, CrewAI, Qdrant, Milvus, Firecrawl, AssemblyAI, Opik
- Models: Llama 3.2, Llama 3.3, Llama 4, DeepSeek-R1, Qwen3
Also in Learning and cookbooks
See all 18| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on curriculum for building AI systems from math to agents | 83 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 76 out of 100 |
| #4 | hello-agentsChinese-language course on building LLM agents from scratch | 76 out of 100 |
| #5 | ml-for-beginners12-week, 26-lesson classic machine learning course using Scikit-learn | 75 out of 100 |