Show HN: A minimalist proxy for your local LLM cluster (~1100 lines)

Source: Github.com· snowy_robolamp· July 30, 2026
Show HN: A minimalist proxy for your local LLM cluster (~1100 lines)

Hi all!I made this small proxy when I built a small GPU cluster at home and wanted to share it with friends while keeping speed limits and token accounting.I also put a lot of effort in making it work as quick as possible, and IMO the result is worth sharing!…

This story was reported by Github.com. Read the full original article:
Read on Github.com

More in Products & Launches

View all