You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Issue draft: Evaluate Impeccable as first-class website design rail
Summary
A Hermes/VPS setup conversation raised whether Impeccable should become a first-class Main Branch design-quality rail, especially for lightweight website repos.
Public-safe external verification on 2026-05-22:
GitHub repo: pbakaus/impeccable
Description: "The design language that makes your AI harness better at design."
Issue draft: Define repo profiles for lightweight website repos (Repology)
Summary
A Hermes/VPS setup conversation raised a larger Main Branch architecture question: Main Branch already has hub/child repo topology, but it does not yet have a small, CLI-owned repo typing contract that tells mb whether the current checkout is a full business brain, a lightweight website repo, a product/code repo, a private source repo, or an integration sidecar.
Internal nickname from the conversation: Repology. Public-facing product copy should probably call this "repo profile" or "repo type" unless maintainers deliberately adopt the Repology name.
This issue should turn the existing topology work into an actionable minimal repo-type schema and CLI behavior, especially for lightweight website repos.
How to run Hermes Agent 24/7 on a VPS — Steven's Setup Guide
How to Run Hermes Agent 24/7 on a VPS — Steven's Setup Guide
This guide is for anyone who wants to run Hermes Agent always-on without keeping their personal computer on. It's written for beginners — you don't need to know Linux or sysadmin work to get this working.
What Is Hermes Agent?
Hermes is an open-source AI agent from Nous Research. It runs on a server (or VPS), connects to your messaging apps (Telegram, Discord, etc.), and can execute tasks, browse the web, manage files, and more — 24 hours a day, 7 days a week.
The heavy AI processing happens via external API (OpenRouter, OpenAI, etc.) — the VPS just runs the coordinator.