{
  "schema_version": "1.1",
  "id": "archive:https://vercel.com/changelog/give-every-agent-in-herdr-its-own-vercel-sandbox",
  "slug": "give-every-agent-in-herdr-its-own-vercel-sandbox-1p4i553",
  "url": "https://feed7.dev/p/give-every-agent-in-herdr-its-own-vercel-sandbox-1p4i553",
  "title": "Give every agent in Herdr its own Vercel Sandbox",
  "why_included": "Herdr can place each terminal coding agent in a separate Vercel Sandbox, then return its work as an opt-in Git patch instead of letting remote edits touch the local checkout.",
  "summary": "Herdr’s Vercel plugin gives Claude Code, Codex, and OpenCode **one isolated Sandbox per agent**. It uploads the project, installs the agent, opens a connected pane, and exposes every action as **JSON**.",
  "practical_implication": "Use the first invocation to inspect the complete upload set, then run it again to create the environment. Parallel agents stay off the local machine, and completed changes return as a **Git patch** that you choose whether to apply.",
  "agent_context": "Herdr’s Vercel plugin gives Claude Code, Codex, and OpenCode **one isolated Sandbox per agent**. It uploads the project, installs the agent, opens a connected pane, and exposes every action as **JSON**.\n\nUse the first invocation to inspect the complete upload set, then run it again to create the environment. Parallel agents stay off the local machine, and completed changes return as a **Git patch** that you choose whether to apply.\n\nIsolation does not remove trust decisions: project files are uploaded to Vercel, applying remote work remains your responsibility, and usage incurs **standard Sandbox rates**. Permanent deletion still requires a typed confirmation.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/give-every-agent-in-herdr-its-own-vercel-sandbox",
    "published_at": "2026-08-06T23:01:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "infra",
  "domains": [
    "coding",
    "security"
  ],
  "topics": [
    "sandboxing",
    "cloud-agents",
    "multi-agent"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Isolation does not remove trust decisions: project files are uploaded to Vercel, applying remote work remains your responsibility, and usage incurs **standard Sandbox rates**. Permanent deletion still requires a typed confirmation."
  ],
  "connected_context": {
    "meaning": "This packages per-agent cloud isolation into a usable local workflow with inspectable uploads, JSON action records, and reviewable Git patches. It strengthens the case for parallel agents without local contention, while making the trust boundary explicit: code leaves the machine, remote output is not accepted automatically, and separate sandboxes carry stronger isolation and cost implications than user separation inside one sandbox.",
    "corpus_size": 419,
    "generated_at": "2026-08-12T10:04:22.973Z",
    "connections": [
      {
        "title": "Run multiple isolated agents in a single Sandbox",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/run-multiple-isolated-agents-in-a-single-sandbox",
        "feed7_url": "https://feed7.dev/p/run-multiple-isolated-agents-in-a-single-sandbox-03i3r7u",
        "reason": "This is a direct architectural contrast: Herdr assigns a sandbox to each agent, whereas the earlier approach separates agents as Linux users within one sandbox, trading a stronger boundary for potentially simpler sharing."
      },
      {
        "title": "From fork() to Fleet: Designing an Agent Sandbox Cloud — Abhishek Bhardwaj, OpenAI",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=OqM67QG_Ikk",
        "feed7_url": "https://feed7.dev/p/from-fork-to-fleet-designing-an-agent-sandbox-cloud-abhishek-bhardwaj-op-0np9ki3",
        "reason": "The sandbox-cloud design explains why per-agent isolated environments matter for long-running coding work and adds recovery and branching concerns beyond Herdr’s upload-and-patch workflow."
      },
      {
        "title": "Multiplayer agentic engineering — Arjun Singh, Superconductor",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=OL7kfezynJM",
        "feed7_url": "https://feed7.dev/p/multiplayer-agentic-engineering-arjun-singh-superconductor-01w4k91",
        "reason": "Superconductor independently reinforces the same team pattern of visible parallel sessions in isolated cloud environments, while emphasizing repository-specific evaluation and human review."
      },
      {
        "title": "Scaling Managed Agents: Decoupling the brain from the hands",
        "source_name": "Anthropic",
        "source_url": "https://www.anthropic.com/engineering/managed-agents",
        "feed7_url": "https://feed7.dev/p/managed-agents-00zpz67",
        "reason": "Anthropic’s separation of stateless agent harnesses from replaceable containers provides a broader service architecture for the per-agent sandbox boundary that Herdr exposes as a developer plugin."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-06T23:01:00.000Z",
  "modified_at": "2026-08-06T23:01:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/give-every-agent-in-herdr-its-own-vercel-sandbox-1p4i553",
    "json": "https://feed7.dev/p/give-every-agent-in-herdr-its-own-vercel-sandbox-1p4i553.json",
    "markdown": "https://feed7.dev/p/give-every-agent-in-herdr-its-own-vercel-sandbox-1p4i553.md"
  }
}