people keep asking which agent harness i run my local models through, and the answer has…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
people keep asking which agent harness i run my local models through, and the answer has not changed since the day i found hermes agent. my gpu rigs stopped being computers i sit at. they are servers now, the desktop app on my laptop streams from them over tailscale so cleanly that the box under the tv and the box across the room are just endpoints in a picker, and my telegram talks to the same gateway, so the same agent answers my phone from a tmux session while i am out. tokens have streamed without a single issue since day one on every path. it is local first and takes any openai style en
Posted by Sudo su (36.2k followers) 5 days ago · 72 likes · 4.9k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Hallmark has been installed 50k+ times! — @nutlope
- Your AI coding agents need a workflow, not more babysitting. — @DanKornas
- Register by October 7 and save >> https://bit.ly/4vkntyD — @linuxfoundation
- Nimble is able to process images! — @madiator
- Your agent already solved this. Finding the session is the problem. — @DanKornas
- Trains your own large language model from scratch using plain PyTorch. — @tom_doerr
- gpt 5.6 terra = gpt 6 astra — @notjazii
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.