Claude Code + Local AI
Learn to connect Claude Code with Ollama, local models, vector databases and desktop workflows you can run without sending every task to the cloud.
What you will be able to do
- Choose and run local models
- Connect tools through Ollama or LM Studio
- Build and publish private applications
A working local AI application using RAG, voice, PDF, or productivity tools.
Makers and developers who need privacy and local control.
- • Basic terminal use
- • 8 GB RAM minimum; 16 GB recommended
Syllabus
module 01 / Foundations
11 lessons- 1The Terminal Without Fear (CLI)
- 2How to Work with Your Projects
- 3Writing good prompts for local AI
- 4Local AI: choose your model
- 5Ollama from Scratch
- 6GGUF Quantization: Q4, Q5, and Q8
- 7Connect Claude Code to Your Local AI
- 8Fix Ollama Errors
- 9Ollama Caps Context at 4K or 32K? Check What It Actually Loaded
- 10Ollama Not Using GPU on Windows? NVIDIA, AMD & WSL2 Fixes
- 11Debug and protect your work
module 02 / Advanced local AI
11 lessons- 12Minimum Hardware for Local AI in 2026
- 13Ollama, vLLM, SGLang, and MLX: What to Use
- 14Windows/WSL2 vs Mac M4 for Local AI
- 15AI Homelab with Used RTX 3090s
- 16Quantization and models for coding
- 17Local code agents with Ollama
- 18Local coding agent with Hermes and Ollama
- 19Advanced Hermes with Gemma and MLX
- 20Tool calling with local models
- 21Open WebUI + Ollama + Qdrant
- 22Open WebUI troubleshooting and lightweight production
module 03 / Build your tools
11 lessonsmodule 04 / Ship it
1 lessonmodule 05 / Advanced appendix
1 lessonComplete Aulafy map
How all courses connect
This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.
- 1Understand
- 2Apply or build
- 3Operate with confidence
Choose an application
Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.
Continue into the technical branch when you need to maintain code, data, or infrastructure.
Build with code
Prepare your environment, work with coding agents, and run models while keeping control of your projects.
This branch prepares you to design and operate reliable AI systems.
Take systems to production
Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.
You do not need every course: choose the component your system needs and return as it grows.