Hermes Agent can now use Vercel AI Gateway as its inference layer and run its agent commands in an isolated Vercel Sandbox microVM. Access 200+ models through AI Gateway at no markup on tokens, and every request appears in your AI Gateway dashboard with the rest of your usage and spend.

Copy link to heading Setup

Install Hermes, then pick Vercel AI Gateway in the setup wizard:

# Install Hermes

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

# In the setup wizard: pick Vercel AI Gateway, paste your key

# Pick Vercel Sandbox to run each agent command in a microVM

# Already have Hermes? Update first, then switch either one:

hermes update

hermes setup model # pick Vercel AI Gateway

hermes setup terminal # pick Vercel Sandbox

# Verify

hermes doctor

The picker pulls live model availability and current pricing from AI Gateway. For the full walkthrough, see Configuring Hermes .

Copy link to heading Running commands in Vercel Sandbox

The Vercel Sandbox backend is opt-in.…