About

I'm Dipankar, a DevOps engineer and the maker of kubmin. I’m building kubmin to help teams understand what their Kubernetes workloads cost, spot wasted resources, and see how each release changes cost and energy use. My work comes from hands-on experience running infrastructure, troubleshooting production systems, and finding ways to make them more efficient. I share what I learn along the way—from system-design trade-offs to experiments with AI agents. Running Kubernetes? I’d love to hear what makes understanding and reducing your cloud costs difficult.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 25
Gone streaking 25
View all badges

Maker History

  • infai
    infaiRun local AI with profiles, not flags
    Nov 2026
  • 🎉
    Joined Product HuntJuly 17th, 2026

Forums

•

1d ago

infai - Run local AI with profiles, not flags

Its an open-source terminal control plane for local AI inference. Find or import models, save reusable launch profiles for llama.cpp and vLLM, check hardware fit, and run multiple models with live logs, ports, tokens-per-second, CPU, RAM, and VRAM telemetry. One Go binary, one SQLite file, no cloud or telemetry.
View more