Stop Running a Separate Vector DB: PostgreSQL + pgvector Is All You Need for RAG
PostgreSQL pgvector handles RAG without separate vector databases. Learn index tuning, production gotchas, when to scale, and why it works.
LLM
Build a Kubernetes Operator That Manages Your LLMs: CRDs, Controllers, and Full Lifecycle Automation
Build a Kubernetes LLM operator with lifecycle automation. Deploy, serve, and destroy models using kubectl. Learn CRDs, controllers, and kubebuilder in Go.
Your Home Server, on Autopilot: Building an Autonomous Maintenance Agent with Cron + Claude CLI
Build an autonomous agent that monitors your home server, detects issues, and fixes them automatically. Production-ready with Claude and Cron.
Private ChatGPT for Your Team in a Day: Open WebUI + Ollama + LDAP Auth
Host a secure, self-hosted ChatGPT for your team using Open WebUI, Ollama, and LDAP authentication. Keep data private, control models, and deploy in one day.
Self-Hosted LLM Cost Engineering: Token Economics, Prefix Caching, and KV-Cache Sizing
Learn self-hosted LLM cost optimization: token economics, prefix caching, KV-cache sizing, and GPU efficiency techniques with real-world numbers.
Stop Paying Per Token: Build a Continuous LoRA Fine-Tuning Pipeline on Your Local GPU
Learn to fine-tune models locally using LoRA on your GPU. Create an automated pipeline for domain-specific adaptation without per-token costs.