{"version":"v1","licence":"CC-BY-4.0","id":"ai-engineering-hub","name":"AI Engineering Hub","repo":"patchy631/ai-engineering-hub","repository_url":"https://github.com/patchy631/ai-engineering-hub","docs_url":"https://github.com/patchy631/ai-engineering-hub#readme","description":"A collection of 90+ hands-on AI projects and tutorials covering LLM apps, RAG, AI agents, MCP servers and fine-tuning, mostly in Python.","summary":"AI Engineering Hub (~41k stars, no tagged releases, updated Nov 2026) is a GitHub collection of 93+ example projects sorted into beginner, intermediate and advanced, from local OCR and chat apps to RAG pipelines, multi-agent systems, MCP servers and fine-tuning notebooks. The code is MIT. Each project is set up separately with Python; some run fully on your computer with Ollama models, while many need API keys for hosted services such as OpenAI, Gemini, AssemblyAI or Firecrawl. It is learning material, not one app, and the READMEs promote the authors' newsletter.","capabilities":["learning"],"tags":["Tutorials","Example projects","LLMs","RAG","AI agents","MCP","Ollama","Python","Fine-tuning"],"alternatives":[],"facts":{"runs_locally":{"status":"partial","value":"Varies by project; some run fully locally with Ollama models, many call hosted AI APIs","source_url":"https://github.com/patchy631/ai-engineering-hub#readme","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","modes":["local","hosted"],"untrusted_source_quote":"100% local OCR app with Llama 3.2 and Streamlit"},"code_license":{"status":"yes","value":"MIT","source_url":"https://github.com/patchy631/ai-engineering-hub/blob/main/LICENSE","checked_at":"2026-11-03","confidence":"high","validation":"documentation_review","spdx":"MIT","untrusted_source_quote":"Permission is hereby granted, free of charge, to any person obtaining a copy"},"model_license":{"status":"partial","value":"No weights in the repo; projects pull third-party models (Llama, Gemma, DeepSeek, Qwen and others) under their own licences, or call hosted APIs","source_url":"https://github.com/patchy631/ai-engineering-hub#readme","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","spdx":null,"applies":true,"untrusted_source_quote":"Local OCR with structured text extraction using Gemma-3"},"commercial_use":{"status":"partial","value":"The code is MIT, so commercial use is allowed; the models and hosted services each project uses have their own terms","source_url":"https://github.com/patchy631/ai-engineering-hub/blob/main/LICENSE","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","untrusted_source_quote":"including without limitation the rights to use, copy, modify, merge"},"paid_services":{"status":"partial","value":"Varies by project; local Ollama projects need none, but many need API keys for hosted services such as OpenAI, Gemini, AssemblyAI, Firecrawl, Zep, Bright Data or Linkup","source_url":"https://github.com/patchy631/ai-engineering-hub/tree/main/notebook-lm-clone","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","required":[],"optional":["OpenAI API","Google Gemini API","AssemblyAI","Firecrawl","Zep","Bright Data","Linkup"],"untrusted_source_quote":"Create a .env file with your API keys as specified in .env.example file"},"hardware":{"status":"unknown","value":"Not documented (checked the main README and the llama-ocr, simple-rag-workflow, video-rag-gemini and notebook-lm-clone READMEs); varies by project and by model size","source_url":"https://github.com/patchy631/ai-engineering-hub#readme","checked_at":"2026-11-03","confidence":"low","validation":"documentation_review","cpu_ok":null,"min_vram_gb":null,"min_ram_gb":null},"platforms":{"status":"partial","value":"Python projects; many READMEs give Windows and macOS/Linux setup steps, but not every project covers every system","source_url":"https://github.com/patchy631/ai-engineering-hub/tree/main/notebook-lm-clone","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","windows":"yes","macos":"yes","linux":"yes","untrusted_source_quote":"powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\""},"setup":{"status":"partial","value":"Medium effort, done per project; install Python packages, often Ollama or API keys, then run a Streamlit app or notebook","source_url":"https://github.com/patchy631/ai-engineering-hub/tree/main/llama-ocr","checked_at":"2026-11-03","confidence":"medium","validation":"documentation_review","level":"medium","untrusted_source_quote":"Ensure you have Python 3.11 or later installed."}},"metrics":{"stars":40949,"forks":6542,"contributors":17,"archived":false,"last_push_at":"2026-11-01T04:39:16Z","latest_release":null,"fetched_at":"2026-11-03T01:20:55.050Z"},"url":"https://repoquarry.dev/projects/ai-engineering-hub","note":"Installation guidance: follow docs_url. This service never installs or runs code."}