ai-engineering-hub and AI-Bootcamp

These are complementary resources that address different depths of the same learning path: the first provides foundational bootcamp-style training across ML basics and multiple frameworks (LangChain, LangGraph, CrewAI), while the second offers in-depth, production-focused tutorials on the advanced topics (LLMs, RAGs, AI agents) that the bootcamp introduces.

ai-engineering-hub
69
Established
AI-Bootcamp
71
Verified
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 23/25
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 31,862
Forks: 5,209
Downloads:
Commits (30d): 8
Language: Jupyter Notebook
License: MIT
Stars: 830
Forks: 266
Downloads:
Commits (30d): 6
Language: Jupyter Notebook
License: MIT
No Package No Dependents
No Package No Dependents

About ai-engineering-hub

patchy631/ai-engineering-hub

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

# Technical Summary Curates 93+ production-ready projects across beginner-to-advanced difficulty levels, with implementations spanning OCR, multimodal RAG, voice agents, and agentic workflows using frameworks like CrewAI, LlamaIndex, and AutoGen. Projects demonstrate integration with local models (Llama, DeepSeek, Qwen) alongside cloud APIs, with emphasis on practical patterns like streaming chatbots, MCP (Model Context Protocol) integration, and real-time voice pipelines. Includes structured learning paths from single-component basics to enterprise deployment patterns with vector databases (Qdrant, Milvus) and memory systems.

About AI-Bootcamp

curiousily/AI-Bootcamp

Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen, Gemma, Llama, Gemini)

The curriculum spans three progressive tracks: foundational ML engineering (Python, math, PyTorch), production systems (data pipelines with DVC, experiment tracking with MLflow, cloud deployment via AWS), and LLM-native applications (local inference with Ollama, retrieval-augmented generation, agentic workflows). Content integrates hands-on Jupyter notebooks with video tutorials and Discord community support, emphasizing reproducible, production-ready implementations across the full AI stack from training to deployment.

Scores updated daily from GitHub, PyPI, and npm data. How scores work