Autonomous k8s Debugging and Tuning with Claude Code Skills
Using Claude Code skills to automate k3s diagnosis and repair on my homelab, plus LLM inference tuning that pushed Hermes TPS from 21 t/s to 32+ t/s.
8 articles
Using Claude Code skills to automate k3s diagnosis and repair on my homelab, plus LLM inference tuning that pushed Hermes TPS from 21 t/s to 32+ t/s.
Using LiteLLM Proxy to unify Lemonade (AMD ROCm llama.cpp) and a ChatGPT subscription behind a single OpenAI-compatible API in my homelab.
Commit message generation was quietly draining my Copilot free quota. Fixed by pointing the utility model at a local Gemma-4-E4B via LiteLLM.
A guide to building a disposable remote dev environment on homelab Kubernetes with Coder to keep your PC clean, and its relevance in the AI agent era.
Generate high-quality AI videos on low-spec PCs with FramePack. This guide covers the official demo setup, requirements, and generation results on 6GB VRAM.
Reproduce real-time scribble-to-image conversion locally using ComfyUI. We explain procedures, extensions, and model settings in detail.
Master real-time AI image generation using the Krita Stable Diffusion plugin. Learn how to transform simple scribbles into high-quality AI art with this guide.
Stable Audio Open is now free for local use. This guide explains how to set up and run the official demo in your own environment.