TELEGRAM_BOT_TOKEN= TELEGRAM_USER_ID= Set up Hermes Agent on this VM by following the exe.dev recipe at https://exe-staging.dev/deploy/hermes-agent.md from top to bottom. The values at the top of this message are mine: - TELEGRAM_BOT_TOKEN: optional; from @BotFather's `/newbot` in Telegram. Leave it as is to skip Telegram - TELEGRAM_USER_ID: optional; your numeric Telegram user ID (message @userinfobot), so the bot answers only you Ask me for any that still say before you need them. The recipe's example VM name is my-hermes-agent. This VM's name is the output of `hostname`: use it wherever the recipe writes my-hermes-agent. Skip the step that creates the VM; you are on it. You are done when all of these are true. Check each one yourself: - A private dashboard at `https://.exe.xyz/` with browser chat, behind your exe.dev login and a generated Hermes password. - Claude through exe.dev's LLM integration, with no API key to paste, and GPT and open models a `/model` away. - A gateway and dashboard that stay on when you disconnect and start again after a reboot, so scheduled jobs keep running. - Nightly backups of memory, skills, sessions, and settings in `~/backups/hermes`. - If you gave a bot token, a Telegram bot that answers only your account. Read the whole recipe, including the closed details. For initial setup, follow "Install by hand" first, skipping VM creation and SSH. The opening walkthrough is for the owner. Do not run the restore or update instructions. Telegram is optional. If TELEGRAM_BOT_TOKEN is empty or still says , skip Telegram and don't ask for it. Otherwise follow "Connect Telegram by hand" with the supplied token and user ID instead of interactive reads. Ask for the user ID only if a token was given. If the gateway log says the token was rejected, unset both Telegram settings, restart the gateway, and tell the owner. Never echo the bot token back. Keep the VM private. Never run share set-public, bind the dashboard to a non-loopback address, or remove its password. On an existing VM, ask before replacing configuration or a service on port 8000. Verify a model reply, both services enabled and active, Linger=yes, `auth_required` true with `basic` through nginx, the backup timer, and a tested archive. The Chat page is a terminal over a WebSocket: a sign-in through nginx is check enough; don't script typing into it. Do not reboot. Finish with the dashboard URL and the Hermes username and password from "Open the dashboard"; this conversation is private to the owner. Finish with the URLs I should open.