Running more than one AI agent on a VPS does not have to mean building a large orchestration platform. A simpler pattern is to run separate agent runtimes, give each one a clear responsibility, and route requests to the right worker.

This post documents the current Hermes and OpenClaw arrangement …

When Hermes runs on a VPS, it cannot directly reach a browser session running on your local machine.

If you want Hermes to control your local Edge or Chrome browser, the most reliable approach is:

1. start the browser with remote debugging enabled
2. expose that local debugging port through an SSH …