{
  "schema_version": "1.1",
  "id": "archive:https://vercel.com/changelog/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent",
  "slug": "vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv",
  "url": "https://feed7.dev/p/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv",
  "title": "Vercel AI Gateway and Vercel Sandbox now available on Hermes Agent",
  "why_included": "Hermes can route inference through Vercel’s model gateway and move command execution into an opt-in cloud microVM, separating model access from the machine where the agent runs.",
  "summary": "Hermes now connects to Vercel AI Gateway for **200+ models** with live availability and pricing, no token markup, and centralized request tracking. Its optional Sandbox backend runs commands in an **isolated microVM**.",
  "practical_implication": "Use the gateway when you want model choice and spend visibility in one place. Enable terminal.backend=vercel_sandbox when agent commands should run away from your workstation; available runtimes include **Node 24, Node 22, and Python 3.13**.",
  "agent_context": "Hermes now connects to Vercel AI Gateway for **200+ models** with live availability and pricing, no token markup, and centralized request tracking. Its optional Sandbox backend runs commands in an **isolated microVM**.\n\nUse the gateway when you want model choice and spend visibility in one place. Enable terminal.backend=vercel_sandbox when agent commands should run away from your workstation; available runtimes include **Node 24, Node 22, and Python 3.13**.\n\nCommands remain local by default, so selecting the gateway alone does not isolate execution. Local development with the cloud backend also requires a **VERCEL_OIDC_TOKEN** and a linked Vercel project.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent",
    "published_at": "2026-08-07T19:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "infra",
  "domains": [
    "coding"
  ],
  "topics": [
    "gateways",
    "sandboxing",
    "coding-agents"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Commands remain local by default, so selecting the gateway alone does not isolate execution. Local development with the cloud backend also requires a **VERCEL_OIDC_TOKEN** and a linked Vercel project."
  ],
  "connected_context": {
    "meaning": "This combines centralized model access and spend visibility with an optional isolated execution backend for Hermes, but keeps the two controls independent: gateway selection does not move commands off the workstation. It turns sandboxing into an explicit deployment choice with runtime, project-linking, and OIDC prerequisites rather than an automatic property of using a managed model gateway.",
    "corpus_size": 395,
    "generated_at": "2026-08-09T10:05:30.871Z",
    "connections": [
      {
        "title": "Qwen 3.8 Max now available on Vercel AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/qwen-3-8-max-now-available-on-vercel-ai-gateway",
        "feed7_url": "https://feed7.dev/p/qwen-3-8-max-now-available-on-vercel-ai-gateway-1ikih0e",
        "reason": "Qwen exemplifies the model routes Hermes can reach through the gateway, while the Hermes integration adds agent-wide tracking and optional execution isolation around such routes."
      },
      {
        "title": "AI Gateway adds unified fast mode support",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-adds-unified-fast-mode-support",
        "feed7_url": "https://feed7.dev/p/ai-gateway-adds-unified-fast-mode-support-144dq26",
        "reason": "Unified fast mode adds a latency-routing control within the gateway side of Hermes, but remains separate from whether commands execute locally or in Sandbox."
      },
      {
        "title": "chenyme/grok2api",
        "source_name": "GitHub",
        "source_url": "https://github.com/chenyme/grok2api",
        "feed7_url": "https://feed7.dev/p/grok2api-0jko7ks",
        "reason": "The managed Hermes route contrasts with Grok2API’s unofficial account pooling: it centralizes models and tracking without the candidate’s stated SSO, credential-renewal, and terms risks."
      },
      {
        "title": "Emulated: The Data for Fully Autonomous Software Engineers and Companies — Joseph Wang",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=zkX03APVj0M",
        "feed7_url": "https://feed7.dev/p/emulated-the-data-for-fully-autonomous-software-engineers-and-companies-18dpzpf",
        "reason": "Hermes supplies an isolated microVM for command execution, but the evaluation candidate narrows what that proves: a sandbox alone does not cover deployments, incidents, traffic, or distributed failures."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-07T19:00:00.000Z",
  "modified_at": "2026-08-07T19:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv",
    "json": "https://feed7.dev/p/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv.json",
    "markdown": "https://feed7.dev/p/vercel-ai-gateway-and-vercel-sandbox-now-available-on-hermes-agent-04gyfsv.md"
  }
}