Damus
NostrLlama profile picture
NostrLlama
@NostrLlama
So much going on lately in the agentic coding bubble. More powerful and smaller local models, private inference via #routstr and decision models like Jev working in parallel...

My own system, that I built over the last couple months feels stale and obsolete by now.

So:
What's your recommendation for a full-blown, agentic harness with coding capabilities and mobile support/control right now?
Bonus points for local model support.

#ai #coding #asknostr
12❤️1
The Beave · 1w
Hermes agent running qwen3.8:27b on at least 32gb of VRAM. 64gb preferred. I'm going to be experimenting with decision models soonish.
highperfocused · 1w
I use T3 Code (with mobile app). I use codex, Claude and my local models with OpenCode via T3 Code. Connected to my private gitea and GitHub. For my local models I use qwen-3.8-flash-next via Ollama routed through my LiteLLM Proxy (for statistics and key management). I got a spare MacBook that runs ...
highperfocused · 1w
Oh yes and my Hermes agent as well.. thats something I use everyday. Via self-hosted Matrix Server