# Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent

> Source: <https://vercel.com/changelog/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent>
> Published: 2026-08-07 19:00:00+00:00

[Hermes Agent](https://hermes-agent.nousresearch.com/) can now use [Vercel AI Gateway](https://vercel.com/ai-gateway) as its inference layer and run its agent commands in an isolated [Vercel Sandbox](https://vercel.com/docs/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.

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](https://vercel.com/docs/ai-gateway/coding-agents/hermes#configuring-hermes).

The [Vercel Sandbox](https://vercel.com/docs/sandbox) backend is opt-in. Commands run locally until you set `terminal.backend`

to `vercel_sandbox`

; with it enabled, agent commands run in a cloud microVM with a workspace root of `/vercel/sandbox`

instead of on your machine. The backend supports `node24`

(default), `node22`

, and `python3.13`

runtimes. For [local development](https://vercel.com/docs/sandbox/concepts/authentication), use `VERCEL_OIDC_TOKEN`

. Run `vercel link`

and `vercel env pull`

to get a development token.

To get started, read the [Hermes documentation](https://vercel.com/docs/ai-gateway/coding-agents/hermes) and the [Vercel Sandbox documentation](https://vercel.com/docs/sandbox), or [browse AI Gateway models](https://vercel.com/ai-gateway/models).