Hermes AgentLives In The Cloud

Hermes Cloud runs your own hosted Hermes Agent on a dedicated cloud instance that stays always on, with its own workspace and dashboard. Pick a size, deploy in seconds, and it's billed daily from your Nous credit based on actual usage.

Your instance is billed from your Nous credit once each day (UTC), in arrears, based on what it actually used that day:

• Running: compute — metered to the second of actual uptime — plus storage.
• Stopped: storage only, so your data and setup persist between sessions.

Charges usually appear within a day or two, once our hosting provider finalizes the day's usage. Inference and tool usage are billed separately, on top of the instance price.

Pick the size that fits your workload. You can change size later. Prices are per day and exclude inference and tool usage.

• MediumRunning $0.56/day · Stopped $0.03/day
  10 concurrent sessions, 2GB RAM, 4 vCPUs
• LargeRunning $1.09/day · Stopped $0.03/day
  20 concurrent sessions, 4GB RAM, 8 vCPUs

We pick the location closest to you that has availability. Possible locations are:

• Amsterdam
• Stockholm
• Mumbai
• Paris
• Dallas
• Frankfurt
• Los Angeles
• London
• Tokyo
• Chicago
• Singapore
• San Jose
• Sydney
• Toronto

Setup takes two clicks and about 60 seconds:

1. Sign in to the portal and add credit to your balance (the current minimum is shown on the deploy screen and the Cloud landing).
2. Open Cloud, give your agent a name, and choose a model and size.
3. Deploy. Once provisioning finishes, your agent's dashboard is ready to use.

Here's a short video going through the setup.

Once your agent is deployed, open its dashboard from the portal to chat with it directly in your browser. You can also connect messaging channels such as Telegram and Discord to reach it from your own apps. Everything is managed from the agent's dashboard.

Yes. You can change your instance size at any time from your agent's controls, and the price adjusts to the new size.

Yes. Your agent has its own dedicated, persistent workspace, so its files, memory, and configuration stay with it and build up over time, whether it is running or stopped.

Stopping pauses the agent so it is not using compute, which drops you to the lower stopped (storage-only) rate. Start it again whenever you need it.