{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-09-21T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/google-ax",
  "type": "tool",
  "slug": "google-ax",
  "canonical_url": "https://gtmstacker.com/registry/tool/google-ax/",
  "title": "Google AX",
  "description": "Apache-2.0 agentic orchestrator from Google (Go) for running autonomous agent workloads at scale. You declare an agent task in a YAML manifest, its workspace and its gateway, and AX sandboxes the task, wires up the workspace, fences its network, and runs it, on Kubernetes, through a control plane. It integrates with LLM providers you supply, so it handles the isolation and scale-out while you bring the model. Early observers describe it as Kubernetes for agent executions.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "mcp-agents",
    "orchestration",
    "self-hostable",
    "sandboxing"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "3219d88e427e1ba70d717b496b157980bb5882e66b3fd7bbb0e946d8dc0bb2a9",
  "date_published": "2026-09-21T00:00:00Z",
  "date_modified": "2026-09-21T00:00:00Z",
  "source": {
    "name": "github · google/ax",
    "url": "https://github.com/google/ax"
  },
  "license": "Apache-2.0",
  "one_liner": "Google AX is an Apache-2.0 orchestrator that runs declarative agent tasks in sandboxed, network-fenced workspaces at scale on Kubernetes.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_model": "free",
  "who_its_for": "A team that has moved past one agent on a laptop and needs to run many agent tasks reliably, each sandboxed and network-fenced, on infrastructure it controls, rather than trusting an agent loose on a shared machine.",
  "aliases": [
    "google-ax",
    "AX",
    "Google AX"
  ],
  "alternatives": [
    "octop",
    "harnessrouter"
  ],
  "secondary_categories": [
    "mcp-agents",
    "integration-orchestration"
  ],
  "last_verified": "2026-09-21",
  "evidence": {
    "claim_type": "mixed",
    "source_id": "https://github.com/google/ax",
    "note": "Apache-2.0, Go, ~4.8k stars, ~625 commits, and the declare-sandbox-fence-run model on Kubernetes confirmed on the repo (WebFetch 2026-09-21, published under the google org). Self-hostable but assumes a Kubernetes cluster and your own LLM provider, so 'free' means the software, not the infrastructure. The 'Kubernetes for agents' framing is an observer's first impression, not a benchmark."
  },
  "caveats": "This is infrastructure, not a one-command install: it wants a Kubernetes cluster and a control plane, so the real cost is operational. The sandboxing and network fencing are the point, but you still supply and pay for the models, and the project is young for something this ambitious. Read it as a platform to pilot, not a drop-in.",
  "lead": "Apache-2.0 agentic orchestrator from Google (Go) for running autonomous agent workloads at scale. You declare an agent task in a YAML manifest, its workspace and its gateway, and AX sandboxes the task, wires up the workspace, fences its network, and runs it on Kubernetes through a control plane. It integrates…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 118,
      "text": "Apache-2.0 agentic orchestrator from Google (Go) for running autonomous agent workloads at scale. You declare an agent task in a YAML manifest, its workspace and its gateway, and AX sandboxes the task, wires up the workspace, fences its network, and runs it on Kubernetes through a control plane. It integrates with LLM providers you supply, so it handles isolation and scale-out while you bring the model. Early observers describe it as Kubernetes for agent executions."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 186,
      "text": "its gateway, and AX sandboxes the task, wires up the workspace, fences its network, and runs it on Kubernetes through a control plane. It integrates with LLM providers you supply, so it handles isolation and scale-out while you bring the model. Early observers describe it as Kubernetes for agent executions.\n\n- Apache-2.0, Go, ~4.8k stars, ~625 commits, and the declarative sandbox-and-fence orchestration model independently WebFetch-verified on the repo 2026-09-21 (github.com/google/ax).\n- Surfaced via the 2026-09-21 viral-posts brief (a credible engineer's \"Google open-sourced AX, feels like Kubernetes for agent executions\").\n- Curated from the GTM Stacker signal registry (2026-09-21 pass); license independently verified 2026-09-21."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 293,
      "text": "~4.8k stars, ~625 commits, and the declarative sandbox-and-fence orchestration model independently WebFetch-verified on the repo 2026-09-21 (github.com/google/ax). - Surfaced via the 2026-09-21 viral-posts brief (a credible engineer's \"Google open-sourced AX, feels like Kubernetes for agent executions\"). - Curated from the GTM Stacker signal registry (2026-09-21 pass); license independently verified 2026-09-21.\n\nOnce agents graduate from a demo to doing real work across a team, the problem stops being the prompt and becomes operations: how do you run twenty agent tasks without one of them wandering out onto the network or trampling a shared machine. AX is Google's answer, declare the task, and it runs sandboxed and network-fenced, at scale, on infrastructure you own. For a GTM or RevOps team that wants agents touching real systems with a blast radius you can set, that isolation is the feature. The honest read: it assumes Kubernetes and a control plane, so this is platform work, not a weekend install, and you still bring and pay for the models. As the piece that makes running many agents an operational discipline instead of a hope, it is worth the pilot."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/google-ax/index.md",
    "html": "https://gtmstacker.com/registry/tool/google-ax/",
    "json": "https://gtmstacker.com/registry/tool/google-ax/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/google-ax/server.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "description": "The growth-systems practice of Theo Popov: AI-native enrichment, outbound, content engines and internal tooling for startups and venture programs. Its agent-native media property, the GTM Stacker Agent Registry, maintains a daily-updated catalog of open-source go-to-market and RevOps tools that both people and AI engines can discover, compare, and cite.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Growth Operations & GTM Systems",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "sameAs": [
          "https://www.linkedin.com/company/gtmstacker",
          "https://www.youtube.com/@gtmstacker",
          "https://www.instagram.com/gtmstacker/",
          "https://www.tiktok.com/@gtmstacker"
        ],
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "SoftwareApplication",
        "@id": "https://gtmstacker.com/registry/tool/google-ax/#software",
        "name": "Google AX",
        "identifier": "io.github.google/ax",
        "description": "Apache-2.0 agentic orchestrator from Google (Go) for running autonomous agent workloads at scale. You declare an agent task in a YAML manifest, its workspace and its gateway, and AX sandboxes the task, wires up the workspace, fences its network, and runs it, on Kubernetes, through a control plane. It integrates with LLM providers you supply, so it handles the isolation and scale-out while you bring the model. Early observers describe it as Kubernetes for agent executions.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/google-ax/",
        "datePublished": "2026-09-21T00:00:00Z",
        "dateModified": "2026-09-21T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/Apache-2.0.html",
        "codeRepository": "https://github.com/google/ax",
        "keywords": "ai-infrastructure, mcp-agents, integration-orchestration, orchestration, self-hostable, sandboxing",
        "author": {
          "@type": "Organization",
          "name": "google",
          "url": "https://github.com/google",
          "sameAs": [
            "https://github.com/google/ax"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        },
        "isSimilarTo": [
          {
            "@type": "SoftwareApplication",
            "name": "Octop",
            "url": "https://gtmstacker.com/registry/tool/octop/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          },
          {
            "@type": "SoftwareApplication",
            "name": "HarnessRouter",
            "url": "https://gtmstacker.com/registry/tool/harnessrouter/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          }
        ]
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/google-ax/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Google AX",
            "item": "https://gtmstacker.com/registry/tool/google-ax/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.google/ax",
    "repository": {
      "url": "https://github.com/google/ax",
      "source": "github"
    }
  }
}