With 15+ years of experience, I specialize in self-hosting, AI automation, and Vibe Coding – building applications using AI-powered tools like Google Antigravity, Dyad, and Cline. From homelabs to enterprise solutions.
Technical notes, walkthroughs, and troubleshooting write-ups focused on self-hosting, automation, networking, and developer tooling.
Why I Built a Local Math Proof Assistant I've been running local LLMs for about a year now, mostly for text processing and code generation. But I kept...
Why I'm Running Multiple LLMs at Once I run several LLM workflows on my home server. Some handle code generation, others process documentation, and a few...
Why I Started Looking Into This I run Ollama on my Proxmox server with a passthrough NVIDIA GPU. It handles various automation tasks through n8n—summarizing...
# Implementing Semantic Caching for LLM APIs: Using Vector Embeddings to Match Similar Queries and Reduce Inference Costs Why I Built This I run several...
# Running Multiple Quantization Levels of the Same Model: Dynamic VRAM Allocation in Ollama for Speed vs Quality Tradeoffs Why I Started Running Multiple...
# Building AI-Assisted Code Review Pipelines: Using Local LLMs to Validate Pull Requests Before Human Review ## Why I Built This I maintain several projects...
Why I Benchmarked the RTX 5090 Against My 4090 I've been running local LLMs on my RTX 4090 for over a year now. My setup includes Ollama for quick CLI...
Why I Built Custom Health Gates Instead of Using depends_on I run several containerized services on my Proxmox homelab that depend on PostgreSQL and MariaDB....
# Fixing Docker Bridge Network MTU Mismatches in Nested Virtualization: Resolving Packet Loss Between Proxmox VMs and Container Networks Why I Had to Fix This...
© Vipin PG 2026 | All Rights Reserved