{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "820",
  "slug": "agent-developer-stack-around-the-model",
  "edition": "2026-10-30T00",
  "url": "https://hangingcontext.com/stories/2026-10-30/agent-developer-stack-around-the-model/",
  "newsroom": "artificial-intelligence",
  "beat": "infrastructure",
  "newsroom_title": "Artificial Intelligence",
  "angle": "The launches around the model — security, inference, interfaces and sandboxes — are now the agent story.",
  "headline": "The Agent Stack Around the Model Gets Its Own Launches",
  "dek": "Endor Labs joined Google Antigravity for secure coding, Baseten partnered with Postman on agent inference, Google shipped a generative-interface standard, and Daytona argued agents need their own runtime.",
  "published_at": "2026-10-30T00:56:31Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 4 sources",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 4,
  "publishers": [
    "baseten-blog",
    "daytona-dotfiles-blog",
    "endor-labs-blog",
    "google-developers-ai"
  ],
  "key_facts": [
    {
      "text": "Endor Labs joined the Google Antigravity Plugin marketplace, with AURI Agents reported 2.8x faster on security tasks and using 12x fewer tokens than general-purpose agents without Endor context.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793311030212350824",
          "claim_ids": [
            "1793311378307721597",
            "1793311378314167645",
            "1793311378316379356"
          ]
        }
      ]
    },
    {
      "text": "Baseten is the recommended inference partner for Postman's enterprise agents, pooling GPU capacity across clouds.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793303920908924786",
          "claim_ids": [
            "1793304160977281216",
            "1793304160987609517"
          ]
        }
      ]
    },
    {
      "text": "Google's A2UI is a framework-agnostic open standard for generative UI, describing an interface as data for runtime rendering.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793304439841845239",
          "claim_ids": [
            "1793304820384531468",
            "1793304820391545405"
          ]
        }
      ]
    },
    {
      "text": "Daytona provisions Firecracker microVMs in less than 90 ms, against Kubernetes setups that Daytona says need custom controllers for agent lifecycles.",
      "self_reported": true,
      "cites": [
        {
          "manifest_id": "1793308893607994999",
          "claim_ids": [
            "1793309204826658843",
            "1793309204820822439"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "Security inside the coding agent",
      "paragraphs": [
        {
          "markdown": "Endor Labs is a launch partner for the Plugin marketplace in Google Antigravity, bringing its AURI Agents and its MCP server into that coding environment.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378307721597",
                "1793311378311788501"
              ]
            }
          ]
        },
        {
          "markdown": "Google was already a launch partner for Endor Labs Agent Governance in May 2026, according to Endor, so the Antigravity marketplace listing extends an existing relationship rather than starting one from scratch.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378331093746"
              ]
            }
          ]
        },
        {
          "markdown": "The company says AURI Agents complete security tasks 2.8 times faster than general-purpose agents without Endor Labs context, and use 12 times fewer tokens, and its MCP server can scan projects for security flaws and exposed secrets during code generation.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378314167645",
                "1793311378316379356",
                "1793311378320448020"
              ]
            }
          ]
        },
        {
          "markdown": "The MCP server also allows agents to check dependencies for vulnerabilities before installation, and agents run on user infrastructure using their own language-model keys and source-control credentials, with most agents read-only by default.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378324611756",
                "1793311378328854926",
                "1793311378329354400"
              ]
            }
          ]
        },
        {
          "markdown": "Endor's agents also include software-composition remediation agents that can open pull requests with evidence attached, triage agents that confirm true positives and generate patches, a helper that gives guidance on package installation, and an explainer that translates vulnerability identifiers into plain-language remediation advice.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378321734292",
                "1793311378323442992",
                "1793311378324611756",
                "1793311378326664169"
              ]
            }
          ]
        },
        {
          "markdown": "Endor puts the need in stark terms, saying only about 10 percent of AI-generated code is both functionally correct and secure, which is the gap its in-workflow scanning is aimed at closing.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378312038869"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Inference and interfaces for agents",
      "paragraphs": [
        {
          "markdown": "Baseten is the recommended inference partner for Postman's enterprise agents, providing multi-cloud capacity management to pool graphics-processor capacity across clouds, plus training infrastructure to post-train open models for specific tasks.",
          "cites": [
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160977281216",
                "1793304160987609517",
                "1793304160991875751"
              ]
            }
          ]
        },
        {
          "markdown": "Postman's platform is used by more than 40 million developers and by 98 percent of the Fortune 500, according to the announcement, which makes the partnership a distribution route for Baseten's inference as much as a technical one.",
          "cites": [
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160981099185",
                "1793304160983970899"
              ]
            }
          ]
        },
        {
          "markdown": "That scale is the point of the partnership from Baseten's side: becoming the recommended inference partner puts its capacity pooling and post-training infrastructure in front of the developer audience that already builds with Postman, rather than requiring those developers to find a separate inference vendor.",
          "cites": [
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160977281216",
                "1793304160987609517",
                "1793304160991875751"
              ]
            }
          ]
        },
        {
          "markdown": "Postman's Agent Stack includes Passport, Fabric, Astropods and Fern, Baseten has zero data retention by default, and Baseten cites Harvey post-training a 27-billion-parameter open model to match closed-source frontier performance on legal benchmarks as an example of its training infrastructure in use.",
          "cites": [
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160985603218",
                "1793304160989687002",
                "1793304160992357933"
              ]
            }
          ]
        },
        {
          "markdown": "Baseten also says its model APIs ranked among the top two providers on Artificial Analysis for throughput and latency in 2026, a claim buyers can weigh alongside the partnership itself.",
          "cites": [
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160994301862"
              ]
            }
          ]
        },
        {
          "markdown": "Google launched A2UI, a framework-agnostic open standard for generative interfaces, which describes an interface as data for application rendering so agents can build interfaces at runtime based on what a request needs.",
          "cites": [
            {
              "manifest_id": "1793304439841845239",
              "claim_ids": [
                "1793304820384531468",
                "1793304820391545405",
                "1793304820378627565"
              ]
            }
          ]
        },
        {
          "markdown": "CopilotKit provides the agent-integration stack for building user-facing agentic apps, and it supports integration with LangChain, among other frameworks named in the announcement.",
          "cites": [
            {
              "manifest_id": "1793304439841845239",
              "claim_ids": [
                "1793304820397532351",
                "1793304820399643797"
              ]
            }
          ]
        },
        {
          "markdown": "Google frames the need plainly: agent-user interactions are evolving from text exchanges to rich interfaces, and CopilotKit provides a toolkit including a chat surface and runtime for A2UI, with support for React and Angular rendering and custom renderers for Vue and Slack.",
          "cites": [
            {
              "manifest_id": "1793304439841845239",
              "claim_ids": [
                "1793304820365207567",
                "1793304820407479672",
                "1793304820411827169",
                "1793304820415887632"
              ]
            }
          ]
        },
        {
          "markdown": "CopilotKit also supports integration with AWS Strands and Google ADK in addition to LangChain, so the standard is pitched as portable across agent frameworks rather than tied to one stack.",
          "cites": [
            {
              "manifest_id": "1793304439841845239",
              "claim_ids": [
                "1793304820403521951",
                "1793304820404370374"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "A runtime built for short-lived work",
      "paragraphs": [
        {
          "markdown": "Daytona argues that Kubernetes is designed for long-running microservices where instances are interchangeable, while AI agents require short-lived, task-specific environments that adapt in real time.",
          "cites": [
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204816685356",
                "1793309204819301854"
              ]
            }
          ]
        },
        {
          "markdown": "Running agents on Kubernetes requires teams to build custom controllers for lifecycle management and provisioning, according to Daytona, which provisions Firecracker microVMs in less than 90 milliseconds.",
          "cites": [
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204820822439",
                "1793309204826658843"
              ]
            }
          ]
        },
        {
          "markdown": "Daytona cites customer examples including AfterQuery, which reduced sandbox creation times by 86 percent, and Trajectory, which saves more than 15 hours each month by using Daytona instead of stitching together Kubernetes solutions.",
          "cites": [
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204828041981",
                "1793309204834951483"
              ]
            }
          ]
        },
        {
          "markdown": "Daytona cites further examples: the Laude Institute increased experiment throughput by 100 times using its stateful environments, Athena Intelligence consolidated six specialized sandbox environments into a single runtime layer, and WolfBench minimizes idle compute costs by scheduling sandboxes across cloud infrastructure, virtual machines and bare-metal servers.",
          "cites": [
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204831313399",
                "1793309204829022916",
                "1793309204833833915"
              ]
            }
          ]
        },
        {
          "markdown": "Daytona also argues against the alternatives on their own terms, saying Kata Containers increases baseline resource consumption compared with other isolation methods, and that gVisor creates potential escape paths through exploitable interface boundaries and kernel vulnerabilities.",
          "cites": [
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204822393351",
                "1793309204824011142"
              ]
            }
          ]
        },
        {
          "markdown": "Put together, the four launches cover the unglamorous middle of agent development: keeping code safe, keeping inference available and affordable, giving agents a way to show their work, and giving them somewhere safe to run.",
          "cites": [
            {
              "manifest_id": "1793311030212350824",
              "claim_ids": [
                "1793311378320448020"
              ]
            },
            {
              "manifest_id": "1793303920908924786",
              "claim_ids": [
                "1793304160977281216"
              ]
            },
            {
              "manifest_id": "1793304439841845239",
              "claim_ids": [
                "1793304820384531468"
              ]
            },
            {
              "manifest_id": "1793308893607994999",
              "claim_ids": [
                "1793309204826658843"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Endor's speed and token figures are company comparisons against general-purpose agents, with no independent test in the cited material.",
    "No pricing is given for Baseten's inference partnership or for Daytona in the cited material.",
    "How widely A2UI is adopted beyond the named frameworks is not shown in the cited material."
  ],
  "decision_card": {
    "useful_for": [
      "Developers building production agents who need security, inference and runtime tooling",
      "Teams moving agents off generic container setups"
    ],
    "not_for": [
      "Teams that only need a single model call with no agent workflow",
      "Buyers looking for model capability comparisons"
    ],
    "compare_against": [
      "Running agents on standard Kubernetes with custom controllers",
      "General-purpose agents without security context"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-10-30T00"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1793311030212350824",
    "1793303920908924786",
    "1793304439841845239",
    "1793308893607994999"
  ],
  "manifests": [
    {
      "manifest_id": "1793311030212350824",
      "title": "Endor Labs + Google Antigravity: Secure code by default in agentic workflows",
      "source_name": "endor-labs-blog",
      "source_url": "https://endorlabs.com/learn/endor-labs-google-antigravity-secure-code-by-default-in-agentic-workflows",
      "published_date": "2026-10-29"
    },
    {
      "manifest_id": "1793303920908924786",
      "title": "Baseten and Postman: Building reliable, cost-efficient agents for the enterprise",
      "source_name": "baseten-blog",
      "source_url": "https://baseten.co/blog/baseten-postman-building-agents-for-enterprise",
      "published_date": "2026-10-29"
    },
    {
      "manifest_id": "1793304439841845239",
      "title": "Build Generative UI Apps with A2UI & CopilotKit Agents",
      "source_name": "google-developers-ai",
      "source_url": "https://developers.googleblog.com/build-generative-ui-apps-with-a2ui-copilotkit-agents",
      "published_date": "2026-10-29"
    },
    {
      "manifest_id": "1793308893607994999",
      "title": "Daytona2: Agent Infrastructure Requires More Than Kubernetes",
      "source_name": "daytona-dotfiles-blog",
      "source_url": "https://daytona.io/dotfiles/daytona2-agent-infrastructure-requires-more-than-kubernetes",
      "published_date": "2026-10-29"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1793311030212350824",
      "1793303920908924786",
      "1793304439841845239",
      "1793308893607994999"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1793311030212350824",
      "all": "for id in 1793311030212350824 1793303920908924786 1793304439841845239 1793308893607994999; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-10-30/agent-developer-stack-around-the-model/",
    "json": "https://hangingcontext.com/stories/2026-10-30/agent-developer-stack-around-the-model/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-10-30/agent-developer-stack-around-the-model/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-10-30T00/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/specialized-models-pick-one-job/",
      "headline": "Three New Models Skip the General Race and Pick One Job",
      "slug": "specialized-models-pick-one-job"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/science-agents-checked-against-evidence/",
      "headline": "Science Agents Are Being Built to Show Their Work, Not Just Their Answers",
      "slug": "science-agents-checked-against-evidence"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/reasoning-models-learn-to-ask-better-questions/",
      "headline": "Reasoning Models Are Learning to Ask Better Questions Before They Answer",
      "slug": "reasoning-models-learn-to-ask-better-questions"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/podcasts-agents-need-oversight/",
      "headline": "This Week's AI Podcasts Agree on One Thing: Agents Need Supervision",
      "slug": "podcasts-agents-need-oversight"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Ask what Synorb covers",
    "text": "The MCP tool synorb-stream-search answers questions like \"do you have this publisher?\" without using any Manifest allowance.",
    "cta": {
      "label": "Connect and ask",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-10-30/agent-developer-stack-around-the-model/"
  }
}