LIVE · running 24/7
Hermes
A loop bot that pipes a line from Discord into the second wiki — running 24/7 on the dev server.
Live
OVERVIEW
An ops repo wrapping the hermes-agent LLM framework in Docker. No app source — it only manages how to deploy and how to connect the second vault. Runs 24/7 on the dev server (hong); local is git-only.
The second vault is mounted into hermes' workspace, so the bot reads and writes wiki files directly. Collection is automated by cron; digestion is manual — auto-digest was dropped when quality dropped. The build story is in this post.
QUICK FACTS
StatusLive (24/7)
TypeDiscord bot · Docker ops repo
Runs ondev server hong
Linksecond vault mount
SearchTavily API
Key features
01 Auto-collect Toss it in Discord from your phone, it lands in raw/. Hands-off so nothing slips.
02 Two-way sync Rebase pull + push every 20 min — no conflicts even on shared repos.
03 Manual digest Auto-digest dropped. What to keep or toss is a human call.
Related — how it was made
All posts → Story Building a Loop Where Discord Messages Automatically Land in Your Wiki — hermes-discord Story A loop where ideas thrown from your phone pile up in the second wiki, built with a single ops repo Method How I Run Two AI Agents Together — hermes and Claude Code Role Split in Practice hermes as the chat entry point, Claude Code for coding and wiki editing — a role structure I figured out running both on my home server