~/ai
Fine-Tuning Open-Source Models with LoRA: Fast, Domain-Specific Adaptation in a Guardrail-Ridden Ecosystem
A practical deep dive into fine-tuning open source models with LoRA — real examples, comparisons, and setup guides.
~/self-hosting
Self-hosted Media Server in the Age of Claude Fable 5: A Practical Jellyfin Setup
A practical deep dive into setting up a media server with Jellyfin — real examples, comparisons, and setup guides.
~/self-hosting
Backup strategies for self-hosted services in a privacy-first era
A practical deep dive into backup strategies for self-hosted services — real examples, comparisons, and setup guides.
~/devops
Infrastructure as Code with Ansible in the Lathe Era: Learn Domains, Not Skim Past Them
A practical deep dive into Infrastructure as Code with Ansible — real examples, comparisons, and setup guides.
~/ai
Reclaiming Control: Running Local LLMs on Consumer Hardware in the GenAI Hype Era
A practical deep dive into running local LLMs on consumer hardware — real examples, comparisons, and setup guides.
~/self-hosting
Reclaiming Control: Self-Hosted Alternatives to Popular Cloud Services in a World of Mega Cloud Moves
A practical deep dive into self-hosted alternatives to popular cloud services — real examples, comparisons, and setup guides.
~/privacy
Gmail Thinks I’m Stupid, So I Segmented My Home Lab—and Here’s Why You Should Too
A practical deep dive into network segmentation for home lab security — real examples, comparisons, and setup guides.
~/ai
How to Set Up Rag Pipelines With Local Models
A practical deep dive into RAG pipelines with local models — real examples, comparisons, and setup guides.
~/devops
How to Set Up Gitops With Flux Vs Argocd
A practical deep dive into GitOps with Flux vs ArgoCD — real examples, comparisons, and setup guides.
~/open-source
In-Depth Look at N8N For Workflow Automation
A practical deep dive into n8n for workflow automation — real examples, comparisons, and setup guides.
Setting Up A Media Server With Jellyfin
Setting up a media server with Jellyfin: a practical, self-hosted solution Jellyfin is an open-source alternative to Plex and Emby
~/local-llms-ai-ollama-self-hosting-hardware
The Self-Hosted AI Stack in 2026: MoE Models, Ollama v0.22, and the Hardware That Actually Runs Them
MoE architectures have made frontier-class open-weight models runnable on a single GPU. Here's your complete guide to the 2026 local AI landscape — from Ollama v0.22 setup and model selection to honest hardware sizing and the full self-hosted stack.