Vibecoder_
Re:Anyone using llama.cpp willing to test LlamaRack?
on Saturday September 05, 2026 @03:24PM (#49579782)
I keep ending up with the same problem when running llama.cpp: multiple models, multiple instances, different GPU allocations, ports, flags, and a growing pile of scripts to keep it all manageable.
LlamaRack is my attempt at making that less annoying.
It manages llama.cpp instances, models, GPU assignment and runtime settings, with an OpenAI-compatible API on top.
It works well enough on my own setup now, but I’d really like to find a few other llama.cpp users willing to try it on different hardware and workflows.
Not looking for promotion or reviews - mostly bugs, rough edges, “why does it work like this?” and things I’ve completely overlooked.
Show HN: Assist Debug Card for Home Assistant
Hi all, I'm playing round with Assist, testing different LLM's, tools, etc. What i was missing from HA is a card which shows the past conversations, including processing times and such.After a bit of experimenting i got a working PoC and then expanded on it.Current features:Features:- Shows Assist pipeline debug runs end-to-end (STT → intent → TTS) with timings and status.- Browse recent runs,...
Show HN: Airwave synced music streaming from YouTube/Spotify links
https://github.com/76696265636f646572/Airwave
Airwave is a small self-hosted project that uses yt-dlp + ffmpeg to create a single live MP3 stream from supported sources.All listeners connect to the same stream endpoint, which avoids drift entirely.Supports YouTube, SoundCloud, Mixcloud, and Sonos.Curious what people think about the approach.
Re:Ask HN: Do you yell at your AI agents?
on Tuesday March 31, 2026 @09:06AM (#47586804)
Only when they delete the whole project again