Hermes Agent: first login & setup
Use this after your Hermes VPS is running and you have the server IP from your email or Dashboard → Servers. The VM runs the official installer in the background; then you configure models and tools on the server over SSH.
What you need
- Your server public IPv4 (from the “server ready” email or Dashboard → Servers).
- The private SSH key that matches the public key you added in the dashboard before the server was created.
- Optional: API keys for your chosen LLM provider—Hermes can use many backends. Configure them on the server with
hermes modelor the setup wizard (see below). Keys are never stored in the AgenticHosting dashboard.
1. SSH into the server
Replace YOUR_SERVER_IP with your public IPv4. The default SSH user is agentic (same as in your email).
ssh agentic@YOUR_SERVER_IP
2. Background install
First boot runs the official Hermes installer as your login user. It can take several minutes (downloads dependencies and tools).
sudo /opt/hermes/health-check.sh— quick statussudo tail -f /var/log/agentichosting-hermes-install.log— live install logsudo journalctl -u hermes-install.service -f— systemd unit log (optional)
When the health check reports the CLI is ready, continue. If the unit failed, use the log paths above and contact support with the last lines (redact any secrets).
3. First commands
Reload your shell if hermes is not found yet (source ~/.bashrc or log out and SSH back in).
Interactive setup (recommended)
hermes setup
Choose provider and model
hermes model
Start the TUI
hermes
Official quickstart and full reference: Hermes documentation · upstream repo: NousResearch/hermes-agent.
4. LLM API keys on the VM
Follow the Hermes section in our LLM setup guide for provider console links and safety tips:
5. Troubleshooting
hermes doctor— upstream diagnostics (run after install).- Confirm Docker is up if you use Docker-backed tools:
sudo systemctl status docker. - Re-read the install log if the health check shows FAILED or UNKNOWN.