Credentials. The bot token and model key live on the server; anyone who can message an unrestricted bot can use your agent and your tokens.
Who it is forSomeone who wants an agent that keeps running when the laptop is closed.
The problemA local agent stops the moment you close the lid, and you cannot check on it away from the desk.
The outcomeHermes on a server, reachable from Telegram, Discord, Slack, WhatsApp or Signal, with conversations continuing across platforms.
What you need first
- macOS, Linux, WSL2 or Windows
- An account or API key for a model provider (Nous Portal, OpenRouter, OpenAI or a custom endpoint)
- Optional: bot tokens for the messaging apps you connect
Steps
- Install Hermes on a VPS or cloud VM
- Run
hermes setupand add the bot token for your messaging app - Start the gateway with
hermes gateway - Message the bot; voice memos are transcribed and the conversation continues across platforms
Prompt for your agent
Set up NousResearch/hermes-agent on my server, configure the Telegram gateway with my bot token from an environment variable, start hermes gateway, and tell me how to restrict who can message the bot.
Caveat.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for NousResearch/hermes-agent and "Talk to Hermes from Telegram while it works on a server"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer