can now use as its inference layer and run its agent commands in an isolated 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. Hermes AgentVercel AI GatewayVercel Sandbox Install Hermes, then pick Vercel AI Gateway in the setup wizard: The picker pulls live model availability and current pricing from AI Gateway. For the full walkthrough, see .Configuring Hermes The backend is opt-in. Commands run locally until you set to ; with it enabled, agent commands run in a cloud microVM with a workspace root of instead of on your machine.

The backend supports (default), , and runtimes. For , use . Run and to get a development token.Vercel Sandboxlocal developmentterminal.backendvercel_sandbox/vercel/sandboxnode24node22python3.13VERCEL_OIDC_TOKENvercel linkvercel env pull To get started, read the and the , or .Hermes documentationVercel Sandbox documentationbrowse AI Gateway models Read more Setup Running commands in Vercel Sandbox