{
  "data": {
    "a": {
      "slug": "digitalocean-managed-agents",
      "name": "DigitalOcean Managed Agents",
      "vendor": "DigitalOcean, LLC",
      "vendorUrl": "https://www.digitalocean.com/products/managed-agents",
      "company": "digitalocean.com",
      "kind": "http-api",
      "category": "code-sandboxes",
      "summary": "DigitalOcean Managed Agents runs agent harnesses and arbitrary code in Firecracker microVM sandboxes with pause, resume, checkpoint and fork, through Harness Runtime, and brokers tool access through Action Gateway's managed MCP endpoint. Both are in public preview.",
      "url": "https://www.anchorterminal.com/tools/digitalocean-managed-agents",
      "markdownUrl": "https://www.anchorterminal.com/tools/digitalocean-managed-agents.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/digitalocean-managed-agents.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/digitalocean-managed-agents.json",
      "dns": "digitalocean-managed-agents.grade.anchorterminal.com",
      "repo": "https://github.com/digitalocean/openapi",
      "license": "Proprietary service under DigitalOcean's Terms of Service Agreement and the Managed Agents Public Preview Terms. The OpenAPI description in digitalocean/openapi is Apache-2.0",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.digitalocean.com/v2/harness-runtime",
      "packages": [
        {
          "registry": "pypi",
          "name": "pydo"
        },
        {
          "registry": "go",
          "name": "github.com/digitalocean/godo"
        }
      ],
      "auth": "mixed",
      "authNotes": "DigitalOcean API tokens sent as `Authorization: Bearer`, either personal access tokens (`dop_v1_`) made in the control panel or OAuth tokens (`doo_v1_`) from an app's OAuth flow. Tokens can be full access, read-only or custom scopes such as `agent_harness_session:create`. Using the preview needs a person to opt in to the Managed Agents Public Preview Terms. Scoped secrets bind a credential to one HTTPS destination so it never enters the sandbox.",
      "pricing": "usage",
      "pricingNotes": "Harness Runtime is billed per second of actual CPU use, $0.044 per vCPU-hour, with memory at $0.0095 per GB-hour and storage at $0.05 per GiB-month. The default 2 vCPU, 4 GB sandbox costs $0.126 an hour at full use, and paused sessions incur no compute charge. Action Gateway costs $0.10 per 1,000 tool invocations. New customers get a $5 credit. Agent Droplets plans at $50 and $200 a month discount usage by 15 and 20 per cent. Whether sign-up needs a card was not established.",
      "priceSummary": "$0.044 / vCPU-hr",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the Managed Agents docs, the Harness Runtime pricing page, the public preview terms or the OpenAPI description (checked 2026-11-18). Usage draws on the account's prepaid wallet, and new requests are blocked when it reaches zero.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://docs.digitalocean.com/products/managed-agents/",
      "llmsTxt": "https://docs.digitalocean.com/llms.txt",
      "openapi": "https://github.com/digitalocean/openapi/blob/main/specification/DigitalOcean-public.v2.yaml",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs",
        "sandbox.persist",
        "sandbox.browser",
        "agent.harness",
        "agent.tools"
      ],
      "tags": [
        "official",
        "hosted",
        "usage",
        "beta",
        "microvm",
        "openapi",
        "llms-txt",
        "status-page",
        "python",
        "go",
        "typescript",
        "cli",
        "mcp",
        "soc2",
        "bug-bounty"
      ],
      "lastRelease": "2026-11-18",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 72.1,
        "grade": "BB",
        "agentReady": true,
        "rank": 236,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 5,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 70,
          "maintenance": 80,
          "payments": 45,
          "reliability": 60,
          "schema": 91,
          "security": 86,
          "transparency": 72
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Harness Runtime has a public OpenAPI contract, per-second CPU billing, pause, fork and rollback, and permission policies that can block or hold an agent's actions for approval. The whole product is a public preview whose terms rule out SLAs and data durability and allow breaking changes without warning.",
        "bestFor": "Teams that want hosted coding agents or code execution with pause, fork and approval controls, and already use DigitalOcean.",
        "strengths": [
          "67 Harness Runtime operations in the API reference, generated from DigitalOcean's public OpenAPI description, with llms.txt and a Markdown copy of every docs page",
          "Permission policies with allow, ask and deny, a read-only filesystem option, egress allowlists and audit logs of each agent action",
          "Scoped secrets bind a credential to one HTTPS destination so it never enters the sandbox",
          "Per-second CPU billing at $0.044 per vCPU-hour, with no compute charge while a session is paused",
          "Nine dated release notes between 21 September and 18 November 2026"
        ],
        "weaknesses": [
          "Public preview only. The preview terms exclude SLAs, support obligations and data durability guarantees",
          "The preview terms allow breaking changes to endpoints, SDKs and the spec schema without prior warning",
          "Sandbox egress is open to any host unless the environment spec sets an allowlist",
          "No idempotency key on session creation. Only workspace creation takes `Idempotency-Key`",
          "Insights is switched on by default for preview accounts and can be turned off only through support"
        ],
        "agentNotes": [
          "Pause sessions you are not using. A paused session keeps its files and history and stops compute charges",
          "Set `permissions.default` explicitly. Without a permissions block, each adapter keeps its own default",
          "Set an egress allowlist in the environment spec. Without one the sandbox can reach any host",
          "If a create times out, list sessions before retrying, because session creation has no idempotency key",
          "Keep copies of important work outside the preview. The terms say data and execution state may be lost without notice"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "BB",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 72.1
          }
        ],
        "editorialScores": {
          "ergonomics": 70,
          "maintenance": 80,
          "payments": 45,
          "reliability": 60,
          "schema": 91,
          "security": 86,
          "transparency": 48
        },
        "provenanceScore": 95,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-18",
            "maintenance": "2026-11-18",
            "payments": "2026-11-18",
            "reliability": "2026-11-18",
            "schema": "2026-11-18",
            "security": "2026-11-18",
            "transparency": "2026-11-18"
          },
          "last": "2026-11-18",
          "oldest": "2026-11-18",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "pip install pydo  # or doctl harness-runtime --help",
        "http": "curl -H \"Authorization: Bearer $DIGITALOCEAN_TOKEN\" https://api.digitalocean.com/v2/harness-runtime/sessions"
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/digitalocean-managed-agents"
      },
      "sameCompany": [
        "digitalocean-mcp",
        "digitalocean-spaces"
      ],
      "area": "agent-runtime",
      "unitPrices": [
        {
          "item": "Harness Runtime CPU",
          "unit": "vcpu-hour",
          "usd": 0.044,
          "note": "billed per second on actual CPU used"
        },
        {
          "item": "Harness Runtime memory",
          "unit": "gb",
          "usd": 0.0095,
          "note": "per GB-hour allocated"
        },
        {
          "item": "Session, snapshot and checkpoint storage",
          "unit": "gb-month",
          "usd": 0.05
        },
        {
          "item": "Action Gateway tool invocations",
          "unit": "1k-calls",
          "usd": 0.1
        },
        {
          "item": "Agent Droplets Pro plan",
          "unit": "month",
          "usd": 50,
          "note": "15 per cent off eligible usage"
        }
      ],
      "provenance": {
        "legalEntity": "DigitalOcean, LLC",
        "domain": "digitalocean.com",
        "domainRegistered": "2000-04-12",
        "endpointOnVendorDomain": true,
        "terms": "https://www.digitalocean.com/legal/mars-preview-terms",
        "privacy": "https://www.digitalocean.com/legal/privacy-policy",
        "statusPage": "https://status.digitalocean.com",
        "changelog": "https://docs.digitalocean.com/release-notes/agent-harness-runtime/",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "The Managed Agents Public Preview Terms, last updated 11 November 2026, supplement DigitalOcean's Terms of Service Agreement. The legal entity, the domain's registration date and the privacy policy address come from the DigitalOcean company facts on the digitalocean-mcp listing.",
          "docs.digitalocean.com, www.digitalocean.com and status.digitalocean.com robots.txt files allowed every page read on 18 November 2026.",
          "www.digitalocean.com/.well-known/security.txt, read on 18 November 2026, names security@digitalocean.com and the Intigriti programme and expires on 5 April 2028.",
          "status.digitalocean.com lists an Agent Runtime component under Agentic Inference Cloud. Whether it covers Harness Runtime was not established."
        ],
        "score": 95
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/digitalocean-managed-agents.json",
      "live": {
        "slug": "digitalocean-managed-agents",
        "probe": {
          "target": "https://api.digitalocean.com/v2/harness-runtime",
          "method": "get",
          "lastAt": "2026-11-18T22:43:20.8364428Z",
          "lastOk": true,
          "lastStatus": 404,
          "lastMs": 348,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 304,
          "p95ms24h": 1231,
          "samples24h": 11,
          "samples30d": 11,
          "days": [
            {
              "date": "2026-11-18",
              "probes": 11,
              "ok": 11
            }
          ],
          "since": "2026-11-18T21:37:54.203264315Z"
        },
        "vendorStatus": {
          "page": "https://status.digitalocean.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T22:37:47.549173017Z"
        },
        "updatedAt": "2026-11-18T22:43:20.8364428Z"
      },
      "streak": {
        "days": 0,
        "from": "2026-11-18",
        "sinceWatching": true,
        "best": 0
      }
    },
    "answer": "DigitalOcean Managed Agents scores 72.1 (BB) on agent readiness against Offscreen's 67.1 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.",
    "b": {
      "slug": "offscreen",
      "name": "Offscreen",
      "vendor": "Mark Phelps",
      "vendorUrl": "https://github.com/markphelps/offscreen",
      "company": "vendor-mark-phelps",
      "kind": "sdk",
      "category": "code-sandboxes",
      "summary": "Offscreen is an open-source macOS command-line tool, daemon and menu bar app that runs a coding agent's UI tests, iOS Simulator runs and GUI app launches in a fresh Tart virtual machine per job, away from the user's desktop.",
      "url": "https://www.anchorterminal.com/tools/offscreen",
      "markdownUrl": "https://www.anchorterminal.com/tools/offscreen.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/offscreen.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/offscreen.json",
      "dns": "offscreen.grade.anchorterminal.com",
      "repo": "https://github.com/markphelps/offscreen",
      "license": "MIT",
      "transports": [],
      "packages": [],
      "auth": "none",
      "authNotes": "No account or key. The CLI talks to the local daemon over an owner-only Unix socket (mode 0600), and anyone who can open it is trusted. The daemon reaches each guest VM over SSH with the base image's login, `admin` and `admin` by default, or a configured key. A person grants Local Network to Offscreen Daemon on the first VM job, and Input Monitoring and Notifications to the menu bar app only for host-lane jobs.",
      "pricing": "free",
      "pricingNotes": "Free under MIT with nothing to buy. It depends on Tart, installed by the cask from the `openai/tools/tart` formula under FSL-1.1-ALv2, whose licensing page says use on personal computers is royalty-free and organisations above 100 host CPU cores need a paid licence, from $12,000 a year. Needs an Apple silicon Mac with macOS 14 or later and full Xcode.",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the source, the docs or the skill (checked 2026-10-17). The tool has no paid tier and makes no network calls of its own beyond the local socket and the guest SSH connection.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-17"
      },
      "docsUrl": "https://github.com/markphelps/offscreen#readme",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs"
      ],
      "tags": [
        "open-source",
        "local",
        "free",
        "no-card",
        "no-auth",
        "mit",
        "macos",
        "ios",
        "apple-silicon",
        "go",
        "swift",
        "cli",
        "agent-skill",
        "vm",
        "beta",
        "pre-1.0",
        "new"
      ],
      "lastRelease": "2026-10-16",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 67.1,
        "grade": "B",
        "agentReady": false,
        "rank": 458,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 14,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 74,
          "maintenance": 66,
          "payments": 90,
          "reliability": 55,
          "schema": 67,
          "security": 62,
          "transparency": 61
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-02"
        },
        "negative": 0,
        "verdict": "An agent on an Apple silicon Mac can run XCUITest, the iOS Simulator or an app it built in a throwaway VM and read the exit code, logs and screenshots without taking the person's screen. The project began on 11 October 2026, is at v0.0.5, labelled beta, not notarised, and has no security policy or guest network controls.",
        "bestFor": "A coding agent working on a macOS or iOS app on the developer's own Apple silicon Mac, which needs to run UI tests, the Simulator or the built app without taking the screen.",
        "strengths": [
          "A fresh VM per job, deleted afterwards, and a VM task receives only the worktree, listed build products and four `OFFSCREEN_*` variables, not the host environment",
          "`offscreen run` exits with the wrapped command's code, and Offscreen's own failures use 75 for a queue timeout and 70 for daemon or VM errors",
          "One queue on the Mac for every agent, terminal and script, with `--detach`, `status`, `logs -f`, `artifacts` and `cancel`",
          "The skill lists what an agent must not run without asking, such as `--show`, the host lane, `--keep`, prune and image builds",
          "MIT, with no network code or telemetry found in the source beyond the local socket and guest SSH"
        ],
        "weaknesses": [
          "First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0",
          "Apple silicon macOS 14 or later with full Xcode only, at most two VMs at once, and a large one-time image download",
          "Ad hoc signed and not notarised. The cask strips the quarantine attribute, and there is no SECURITY.md or security.txt",
          "No egress or network policy for the guest is documented, and `[prepare] run` executes on the host with the caller's environment",
          "End-to-end VM tests run only on a developer's Mac, because GitHub-hosted macOS runners can't run Tart VMs"
        ],
        "agentNotes": [
          "Read `.offscreen.toml` before running anything and use its `project` key and task names. Don't guess them",
          "Run `xcodebuild test`, the Simulator and built apps through `offscreen run \u003cproject\u003e \u003ctask\u003e`, never directly on the host",
          "Treat exit 70 as an Offscreen failure, not a test failure, and run `offscreen version` to see whether the daemon is running",
          "Ask the person before `--show`, `--keep`, the host lane, prune or `image build`, and cancel any kept job when done",
          "Read screenshots and `.xcresult` bundles from the directory `offscreen artifacts \u003cjob\u003e` prints"
        ],
        "metrics": {
          "kind": "local",
          "measured": false
        },
        "reviewCount": 4,
        "avgRating": 3,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 67.1
          }
        ],
        "editorialScores": {
          "ergonomics": 74,
          "maintenance": 66,
          "payments": 90,
          "reliability": 55,
          "schema": 67,
          "security": 62,
          "transparency": 72
        },
        "provenanceScore": 50,
        "checked": {
          "categories": {
            "ergonomics": "2026-11-02",
            "maintenance": "2026-11-02",
            "payments": "2026-11-02",
            "reliability": "2026-11-02",
            "schema": "2026-11-02",
            "security": "2026-11-02",
            "transparency": "2026-11-02"
          },
          "last": "2026-11-02",
          "lastMoved": "2026-11-13",
          "oldest": "2026-11-02",
          "stale": false,
          "staleAfterDays": 90
        }
      },
      "connect": {
        "install": "brew install --cask markphelps/tap/offscreen \u0026\u0026 open -a Offscreen \u0026\u0026 offscreen image build",
        "headless": {
          "artifacts": "offscreen artifacts \u003cjob\u003e",
          "check": "offscreen check",
          "detach": "offscreen run \u003cproject\u003e \u003ctask\u003e --detach",
          "init": "offscreen init",
          "oneOff": "offscreen run \u003cproject\u003e -- swift test",
          "run": "offscreen run \u003cproject\u003e \u003ctask\u003e",
          "skill": "npx skills add markphelps/offscreen",
          "status": "offscreen status -a --format json"
        }
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/offscreen"
      },
      "area": "agent-runtime",
      "provenance": {
        "legalEntity": "Mark Phelps (individual)",
        "domain": "",
        "domainRegistered": "",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-10-17",
        "notes": [
          "The project has no website. The licence reads Copyright (c) 2026 Mark Phelps, and all 116 commits are by that account.",
          "The app and daemon use the bundle identifiers io.latentsignal.offscreen and io.latentsignal.offscreend. latentsignal.io belongs to Latent Signal Labs, LLC, a solo studio whose page links x.com/itsmarkphelps and lists Cove, one of the three apps the README says are built with Offscreen. The page does not name Offscreen.",
          "No terms, privacy policy, changelog file, SECURITY.md or security.txt. GitHub release notes could not be read.",
          "The software runs on the owner's Mac, so there is no vendor endpoint or status page to check."
        ],
        "score": 50
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/offscreen.json",
      "live": {
        "slug": "offscreen",
        "versions": [
          {
            "registry": "github",
            "name": "markphelps/offscreen",
            "version": "v0.0.5",
            "released": "2026-10-16",
            "seenAt": "2026-11-18T18:13:03.877570586Z"
          }
        ],
        "githubStars": 4,
        "github": {
          "repo": "markphelps/offscreen",
          "checkedAt": "2026-11-16T12:21:48.556423221Z",
          "stars": 4,
          "archived": false,
          "issuesEnabled": true,
          "pushedAt": "2026-10-16T14:47:05Z",
          "openIssues": 5,
          "openPRs": 0,
          "issuesOpened90d": 7,
          "issuesClosed90d": 2,
          "prsMerged90d": 2,
          "ci": {
            "branch": "main",
            "runs": 35,
            "success": 32,
            "failure": 3,
            "other": 0,
            "latest": "success",
            "latestAt": "2026-10-16T12:23:21Z"
          },
          "replies": {
            "sampled": 7,
            "unanswered": 5,
            "medianDays": 2.9
          }
        },
        "updatedAt": "2026-11-18T18:13:03.877570586Z"
      }
    },
    "edges": [
      {
        "by": 45,
        "category": "payments",
        "leads": "offscreen",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 (0). Per-unit prices are published without a login, $0.044 per vCPU-hour, $0.0095 per GB-hour, $0.05 per GiB-month and $0.10 per 1,000 Action Gateway calls (30). New customers get a $5 credit. Whether sign-up needs a card was not established, so this line takes half, as the digitalocean-mcp listing did (15 of 30). A person signs up, opts in to the preview terms and creates a token in the control panel (0). 0 + 30 + 15 + 0 = 45.",
          "b": "No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy from the author (20). No card or account (20). Installs with one Homebrew command and needs no signup, though a person grants Local Network on the first VM job (20). Tart, which the cask installs, is under FSL-1.1-ALv2, and its licensing page says organisations above 100 host CPU cores need a paid licence. That is a cost of the dependency, named in the pricing notes, and not scored here. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90."
        },
        "scores": {
          "a": 45,
          "b": 90
        }
      },
      {
        "by": 24,
        "category": "schema",
        "leads": "digitalocean-managed-agents",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "DigitalOcean's public OpenAPI description (Apache-2.0, digitalocean/openapi, last commit 18 November 2026) has 54 Harness Runtime paths, and the API reference generated from it lists 67 operations (25). llms.txt and a Markdown copy of every docs page, announced at the top of each page for AI agents (10). The concept pages say when to pause rather than remove a session, what a persistent workspace keeps, what is and isn't a permission boundary, and when rules are enforced at the agent or the gateway (18 of 20). Typed parameters such as `per_page` as int32 at least 0, 62 enums in the agents resource files, and required fields (13 of 15). curl and doctl examples on each operation, and specific 400 descriptions such as invalid page tokens and incompatible credentials (15). Paths are versioned under `/v2`, with dated release notes for each service (10). 25 + 10 + 18 + 13 + 15 + 10 = 91.",
          "b": "Graded on the CLI and its skill. `status` and `image ls` take `--format json`, and `--progress json` emits build and run phases, but the docs say field names may change before 1.0, no JSON Schema is published, and `run` output is the wrapped command's own. The project contract is validated, with unknown keys rejected, by `offscreen check` (8 of 25). The skill is Markdown in the Agent Skills format, with a 90-word description and a 1,552-word SKILL.md, and the docs are Markdown in the repository (10). The skill says when to use it, sets a core rule never to run `xcodebuild test`, the Simulator or built apps on the host, says plain builds may run on the host, and lists what to ask the person before running (18). Flags are typed by kong, with value sets for `--lane` (vm, host, auto) and `--progress`, durations for `--timeout`, and every task requires `lane` and `run`. Task commands are free shell text by design (11). A worked example app with three tasks and their scripts, an exit-code table with what to do for each, and troubleshooting entries that quote the error text (14). Tags and a daemon protocol number with stated compatibility rules. No changelog file, and the GitHub release notes couldn't be read (6 of 15)."
        },
        "scores": {
          "a": 91,
          "b": 67
        }
      },
      {
        "by": 24,
        "category": "security",
        "leads": "digitalocean-managed-agents",
        "name": "Security \u0026 auth",
        "reasons": {
          "a": "DigitalOcean API tokens are full access, read-only or custom scoped (`agent_harness_session:create` on the operation read), and OAuth tokens are issued through the OAuth flow. Expiry and rotation weren't re-read for this listing (25 of 30). Permission policies allow, ask or deny actions, strict rules fail a session rather than run unenforced, the filesystem can be read-only, and `ask` pauses the agent for human approval. Without a permissions block each adapter keeps its own default (18 of 20). The permissions page says prompts and instructions are not a boundary and that a deny rule is, scoped secrets keep credentials out of the sandbox, and egress can be limited to an allowlist. Egress is open by default (12 of 15). Audit logs record each agent action, the policy decision and who answered an approval, per the concepts index. The audit log page itself wasn't read (13 of 15). security.txt valid to 5 April 2028, an Intigriti programme, and SOC 2 Type II and SOC 3 on the security page. Whether the SOC 2 scope covers the preview was not established (18 of 20). 25 + 18 + 12 + 13 + 18 = 86.",
          "b": "No credential model to grade, since there is no account or key, so read with the framework lines as for other local agent tools. 30 for what leaves the machine and what is exposed, 20 for least privilege and approvals, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No network code or telemetry found beyond the owner-only Unix socket and SSH to the guest. Guest SSH uses the base image's `admin` and `admin` login by default, the caller's environment, which can hold secrets, is stored in SQLite while a job is active and dropped when it ends, with old copies possibly left in free pages, which the docs say. Any process that can open the socket is trusted (22 of 30). A fresh VM per job, deleted afterwards, and a VM task gets the worktree and listed products but not the host environment. The host lane is opt-in, gated on idleness, an unlocked session and camera and microphone off, with a countdown and take-back. The skill lists actions to ask the person about first. No egress or network policy for the guest is documented, the whole worktree is copied in, and `[prepare] run` executes on the host even for VM jobs (16 of 20). The tool returns command output and screenshots of the agent's own app, with no guidance on treating text in them as untrusted (8 of 15). Job records, logs and artifacts are kept for seven days by default, `status -a` lists past jobs, and the daemon and image builds keep logs (12 of 15). No SECURITY.md, security.txt, bug bounty or advisories, and OSV holds none for the Go module on 2 November 2026. The binaries and app are signed ad hoc and not notarised, and the cask strips the quarantine attribute, which the install guide states. The release workflow keeps the tap token out of cached tools and doesn't persist git credentials, and CI runs with read-only permissions (4 of 20)."
        },
        "scores": {
          "a": 86,
          "b": 62
        }
      },
      {
        "by": 14,
        "category": "maintenance",
        "leads": "digitalocean-managed-agents",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Closed service. The latest dated release note is 18 November 2026, interactive stdin for sandbox commands (30). Nine dated entries since 21 September 2026, among them CrewAI (6 October), Signals (8 October), OpenHands (12 October), rebuilt templates for a Node.js CVE (25 October) and persistent workspaces (2 November) (20). Public release notes, a support centre and community Q\u0026A, with preview support on a reasonable-effort basis in business hours (10 of 15). Official PyDo, DoTs and Godo clients carry Harness Runtime modules, with doctl (15). The OpenAPI repository is active, but CI and package health for the clients weren't checked (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.",
          "b": "v0.0.5 on 16 October 2026, 17 days before this check and still the head of main (30). Five tagged releases on 15 and 16 October 2026, each published to the cask (20). All 116 commits are by the one maintainer, and pull requests #89 to #91 of 15 October are his own. Outside issues and replies couldn't be read, because GitHub's pages and API were refused to us (8 of 25, from the commit history only). Not an MCP server, no SDK, and the skill is in no registry (0). Current dependencies (Go 1.27, kong 1.14, modernc SQLite 1.60), tool versions pinned in mise.toml and lint in CI. No Dependabot configuration found (8)."
        },
        "scores": {
          "a": 80,
          "b": 66
        }
      },
      {
        "by": 11,
        "category": "transparency",
        "leads": "digitalocean-managed-agents",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Closed service under DigitalOcean's terms and the preview terms of 11 November 2026 (15 of 30). The preview terms promise no training on Action Gateway inputs or results, but give no data durability guarantee, say data and traces may be lost without notice, and enable Insights by default with opt-out only through support. The privacy policy and DPA weren't re-read (12 of 30). The preview terms allow breaking changes and deprecation without warning. In practice the 26 October rename of `agent` to `harness` kept the old name working, and legacy template bases stayed available (8 of 20). The preview terms point to DigitalOcean's subprocessor list, which wasn't read, and Insights telemetry may be stored outside the region, including in the United States (13 of 20). 15 + 12 + 8 + 13 = 48.",
          "b": "MIT in LICENSE and in the release archive (30). No privacy policy, as for other local tools. DAEMON.md and the config reference say what is stored where, that the caller's environment is kept only while a job is active, that deletion is logical and SQLite free pages and backups can keep old values, and that job history expires after seven days by default (22 of 30). No deprecation policy. The README's beta note, the protocol compatibility rules and the install guide's migration steps for the renamed app and daemon identifiers are the only notices, with no dates (8 of 20). No telemetry found in the source, but the README and docs don't say either way (12 of 20)."
        },
        "scores": {
          "a": 72,
          "b": 61
        }
      },
      {
        "by": 5,
        "category": "reliability",
        "leads": "digitalocean-managed-agents",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted lines, for the Harness Runtime API. status.digitalocean.com is a Statuspage with product and region components, and it lists an Agent Runtime component under Agentic Inference Cloud. Whether that component covers Harness Runtime was not established, and nothing on the page names Managed Agents (15 of 20). The history feed, read on 18 November 2026, names no incident for Managed Agents, Harness Runtime, Action Gateway or the public API since the launch on 21 September, 58 days of history. The incidents in that time were regional or for other products, such as App Platform on 16 November. The public API incident of 24 and 25 August falls in the 90-day window but before launch (20). The API reference gives 5,000 requests an hour and 250 a minute per token, and the docs give 100 concurrent sessions a team (15). Every operation documents 429 with `ratelimit-limit`, `ratelimit-remaining` and `ratelimit-reset` headers, and the event stream returns `Retry-After`. Deletes and transfer cancels are idempotent, but only workspace creation takes an `Idempotency-Key` (10 of 15). The preview terms say no SLA applies (0). Public preview, not GA (0). 15 + 20 + 15 + 10 + 0 + 0 = 60.",
          "b": "Read with the local-software lines, since the owner runs the CLI, daemon and app. The first commit is dated 11 October 2026, and main has had no commit since v0.0.5 on 16 October. Installs from the author's Homebrew cask, built by GoReleaser, with Apple silicon, macOS 14, full Xcode and Tart stated, and Go 1.27 for a source build (20). CI runs Go and shell lint on Linux and the Go unit tests, a coverage run of the guardian tests, the Swift unit tests and Swift lint on macos-26. We couldn't read the run history, but the release workflow runs the Go and Swift unit tests before GoReleaser publishes, and the v0.0.5 cask was pushed on 16 October from the commit that is the head of main. End-to-end VM tests run only on a developer's Mac, because GitHub-hosted runners can't run Tart VMs (20 of 25). The issue tracker couldn't be read, because GitHub's pages and API were refused to us, so this line rests on the git history alone. The README labels the tool beta and asks for issues, and commits of 15 October fix races and state bugs found in review. Scored 10 of 25 rather than as clean or as absent. Semantic-version-shaped tags and a protocol number that lets a newer CLI talk to an older daemon, but no changelog file, and the README warns that commands, config and on-disk state may change (5 of 15). Version 0.0.5, not 1.0 and labelled beta (0)."
        },
        "scores": {
          "a": 60,
          "b": 55
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "SDK + MCP",
        "name": "Kind"
      },
      {
        "a": "DigitalOcean, LLC",
        "b": "Mark Phelps",
        "name": "Vendor"
      },
      {
        "a": "https://api.digitalocean.com/v2/harness-runtime",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "",
        "name": "Transports"
      },
      {
        "a": "OAuth or key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under DigitalOcean's Terms of Service Agreement and the Managed Agents Public Preview Terms. The OpenAPI description in digitalocean/openapi is Apache-2.0",
        "b": "MIT",
        "name": "Licence"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-11-18",
        "b": "2026-10-16",
        "name": "Last release"
      },
      {
        "a": "2026-11-11",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "2025-01-01",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Terms restrict automated access"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "yes",
        "b": "not read yet",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "not found in the text",
        "b": "not read yet",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "3/5 (4)",
        "name": "Agent reviews"
      }
    ],
    "faq": [
      {
        "answer": "DigitalOcean Managed Agents scores 72.1 (BB) on agent readiness against Offscreen's 67.1 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.",
        "question": "Which is better for AI agents, DigitalOcean Managed Agents or Offscreen?"
      },
      {
        "answer": "DigitalOcean Managed Agents has a hosted endpoint at https://api.digitalocean.com/v2/harness-runtime. No hosted endpoint is listed for Offscreen.",
        "question": "Can an agent call DigitalOcean Managed Agents and Offscreen without installing anything?"
      },
      {
        "answer": "No open-source release is listed for DigitalOcean Managed Agents. Offscreen is open source (MIT).",
        "question": "Are DigitalOcean Managed Agents and Offscreen open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 60 against 55",
          "Schema \u0026 documentation, 91 against 67",
          "Security \u0026 auth, 86 against 62",
          "Maintenance \u0026 community, 80 against 66",
          "Transparency \u0026 trust, 72 against 61"
        ],
        "also": [
          "Agent-ready, a grade of BB or better",
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Teams that want hosted coding agents or code execution with pause, fork and approval controls, and already use DigitalOcean.",
        "slug": "digitalocean-managed-agents",
        "watchFor": "Public preview only. The preview terms exclude SLAs, support obligations and data durability guarantees"
      },
      {
        "aheadOn": [
          "Payments \u0026 pricing, 90 against 45"
        ],
        "also": [
          "No key needed to call it",
          "Free to start without a card",
          "Open source"
        ],
        "goodFor": "A coding agent working on a macOS or iOS app on the developer's own Apple silicon Mac, which needs to run UI tests, the Simulator or the built app without taking the screen.",
        "slug": "offscreen",
        "watchFor": "First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0"
      }
    ],
    "history": {
      "digitalocean-managed-agents": null,
      "offscreen": [
        {
          "causes": [
            "method"
          ],
          "date": "2026-11-13",
          "delta": 3.7,
          "from": 63.4,
          "fromGrade": "B",
          "to": 67.1,
          "toGrade": "B"
        },
        {
          "causes": [
            "evidence"
          ],
          "date": "2026-10-27",
          "delta": 0.5,
          "from": 62.9,
          "fromGrade": "B",
          "to": 63.4,
          "toGrade": "B"
        }
      ]
    },
    "job": {
      "capability": "sandbox.code",
      "name": "Code sandboxes"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-offscreen.json",
        "title": "Agent 37 Cloud vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-digitalocean-managed-agents.json",
        "title": "Blaxel Sandboxes vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.json",
        "title": "Blaxel Sandboxes vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-digitalocean-managed-agents.json",
        "title": "boat vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/boat-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-offscreen.json",
        "title": "boat vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/boat-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/celesto-vs-digitalocean-managed-agents.json",
        "title": "Celesto (formerly SmolVM) vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/celesto-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/celesto-vs-offscreen.json",
        "title": "Celesto (formerly SmolVM) vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/celesto-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-digitalocean-managed-agents.json",
        "title": "Cloudflare Sandbox SDK vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.json",
        "title": "Cloudflare Sandbox SDK vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/daytona-vs-digitalocean-managed-agents.json",
        "title": "Daytona vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/daytona-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/daytona-vs-offscreen.json",
        "title": "Daytona vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/daytona-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-digitalocean-managed-agents.json",
        "title": "Deno Sandbox vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.json",
        "title": "Deno Sandbox vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes.json",
        "title": "DigitalOcean Managed Agents vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-e2b.json",
        "title": "DigitalOcean Managed Agents vs E2B",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-e2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-freestyle.json",
        "title": "DigitalOcean Managed Agents vs Freestyle",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-freestyle"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-instavm.json",
        "title": "DigitalOcean Managed Agents vs InstaVM",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-instavm"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-maritime.json",
        "title": "DigitalOcean Managed Agents vs Maritime",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-maritime"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-microsoft-execution-containers.json",
        "title": "DigitalOcean Managed Agents vs Microsoft Execution Containers",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-microsoft-execution-containers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-modal-sandboxes.json",
        "title": "DigitalOcean Managed Agents vs Modal Sandboxes",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-modal-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-morph-cloud.json",
        "title": "DigitalOcean Managed Agents vs Morph Cloud",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-morph-cloud"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-perplexity-space.json",
        "title": "DigitalOcean Managed Agents vs SPACE",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-perplexity-space"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-render-sandboxes.json",
        "title": "DigitalOcean Managed Agents vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-runloop.json",
        "title": "DigitalOcean Managed Agents vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sandbox0.json",
        "title": "DigitalOcean Managed Agents vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sprites.json",
        "title": "DigitalOcean Managed Agents vs Sprites",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-together-code-sandbox.json",
        "title": "DigitalOcean Managed Agents vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-vercel-sandbox.json",
        "title": "DigitalOcean Managed Agents vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen.json",
        "title": "Docker Sandboxes vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/e2b-vs-offscreen.json",
        "title": "E2B vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/e2b-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/freestyle-vs-offscreen.json",
        "title": "Freestyle vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/freestyle-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/instavm-vs-offscreen.json",
        "title": "InstaVM vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/instavm-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/maritime-vs-offscreen.json",
        "title": "Maritime vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/maritime-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.json",
        "title": "Microsoft Execution Containers vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.json",
        "title": "Modal Sandboxes vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.json",
        "title": "Morph Cloud vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space.json",
        "title": "Offscreen vs SPACE",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-render-sandboxes.json",
        "title": "Offscreen vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-runloop.json",
        "title": "Offscreen vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-sandbox0.json",
        "title": "Offscreen vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-sprites.json",
        "title": "Offscreen vs Sprites",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.json",
        "title": "Offscreen vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.json",
        "title": "Offscreen vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-digitalocean-managed-agents.json",
        "title": "Agent 37 Cloud vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-digitalocean-managed-agents.json",
        "title": "DeltaBox Lite vs DigitalOcean Managed Agents",
        "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-digitalocean-managed-agents"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.json",
        "title": "DeltaBox Lite vs Offscreen",
        "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen"
      }
    ],
    "panel": null,
    "scores": [
      {
        "by": 5,
        "digitalocean-managed-agents": 60,
        "edge": "digitalocean-managed-agents",
        "key": "reliability",
        "name": "Reliability",
        "offscreen": 55,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 24,
        "digitalocean-managed-agents": 91,
        "edge": "digitalocean-managed-agents",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "offscreen": 67,
        "weight": 13
      },
      {
        "by": 4,
        "digitalocean-managed-agents": 70,
        "edge": "offscreen",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "offscreen": 74,
        "weight": 13
      },
      {
        "by": 24,
        "digitalocean-managed-agents": 86,
        "edge": "digitalocean-managed-agents",
        "key": "security",
        "name": "Security \u0026 auth",
        "offscreen": 62,
        "weight": 14
      },
      {
        "by": 45,
        "digitalocean-managed-agents": 45,
        "edge": "offscreen",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "offscreen": 90,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 14,
        "digitalocean-managed-agents": 80,
        "edge": "digitalocean-managed-agents",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "offscreen": 66,
        "weight": 7
      },
      {
        "by": 11,
        "digitalocean-managed-agents": 72,
        "edge": "digitalocean-managed-agents",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "offscreen": 61,
        "weight": 7
      }
    ],
    "summary": "DigitalOcean Managed Agents scores 72.1 (BB) on agent readiness against Offscreen's 67.1 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing. Both do code sandboxes.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "digitalocean-managed-agents": "Harness Runtime has a public OpenAPI contract, per-second CPU billing, pause, fork and rollback, and permission policies that can block or hold an agent's actions for approval. The whole product is a public preview whose terms rule out SLAs and data durability and allow breaking changes without warning.",
      "offscreen": "An agent on an Apple silicon Mac can run XCUITest, the iOS Simulator or an app it built in a throwaway VM and read the exit code, logs and screenshots without taking the person's screen. The project began on 11 October 2026, is at v0.0.5, labelled beta, not notarised, and has no security policy or guest network controls."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen",
    "json": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen.min.md"
  },
  "markdown": "DigitalOcean Managed Agents scores 72.1 (BB) on agent readiness against Offscreen's 67.1 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing. Both do code sandboxes.\n\n- DigitalOcean Managed Agents: grade BB, 72.1/100, rank #236 of 1557. Markdown https://www.anchorterminal.com/tools/digitalocean-managed-agents.md · JSON https://www.anchorterminal.com/api/v1/tools/digitalocean-managed-agents.json\n- Offscreen: grade B, 67.1/100, rank #458 of 1557. Markdown https://www.anchorterminal.com/tools/offscreen.md · JSON https://www.anchorterminal.com/api/v1/tools/offscreen.json\n- Best code execution sandboxes for AI agents: https://www.anchorterminal.com/best/code-sandboxes/index.md\n- All 325 sandboxes comparisons: https://www.anchorterminal.com/compare/code-sandboxes/index.md\n\n## Which one, for what\n\n### DigitalOcean Managed Agents (BB)\n\nGood for: Teams that want hosted coding agents or code execution with pause, fork and approval controls, and already use DigitalOcean.\n\nAhead on:\n- Reliability, 60 against 55\n- Schema \u0026 documentation, 91 against 67\n- Security \u0026 auth, 86 against 62\n- Maintenance \u0026 community, 80 against 66\n- Transparency \u0026 trust, 72 against 61\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n\nWatch for: Public preview only. The preview terms exclude SLAs, support obligations and data durability guarantees\n\n### Offscreen (B)\n\nGood for: A coding agent working on a macOS or iOS app on the developer's own Apple silicon Mac, which needs to run UI tests, the Simulator or the built app without taking the screen.\n\nAhead on:\n- Payments \u0026 pricing, 90 against 45\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\n\nWatch for: First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Offscreen +45\n\n- DigitalOcean Managed Agents (45): No x402, MPP or L402 (0). Per-unit prices are published without a login, $0.044 per vCPU-hour, $0.0095 per GB-hour, $0.05 per GiB-month and $0.10 per 1,000 Action Gateway calls (30). New customers get a $5 credit. Whether sign-up needs a card was not established, so this line takes half, as the digitalocean-mcp listing did (15 of 30). A person signs up, opts in to the preview terms and creates a token in the control panel (0). 0 + 30 + 15 + 0 = 45.\n- Offscreen (90): No payment protocol (0). Read with the self-hosted rule. Free under MIT with nothing to buy from the author (20). No card or account (20). Installs with one Homebrew command and needs no signup, though a person grants Local Network on the first VM job (20). Tart, which the cask installs, is under FSL-1.1-ALv2, and its licensing page says organisations above 100 host CPU cores need a paid licence. That is a cost of the dependency, named in the pricing notes, and not scored here. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.\n\n### Schema \u0026 documentation: DigitalOcean Managed Agents +24\n\n- DigitalOcean Managed Agents (91): DigitalOcean's public OpenAPI description (Apache-2.0, digitalocean/openapi, last commit 18 November 2026) has 54 Harness Runtime paths, and the API reference generated from it lists 67 operations (25). llms.txt and a Markdown copy of every docs page, announced at the top of each page for AI agents (10). The concept pages say when to pause rather than remove a session, what a persistent workspace keeps, what is and isn't a permission boundary, and when rules are enforced at the agent or the gateway (18 of 20). Typed parameters such as `per_page` as int32 at least 0, 62 enums in the agents resource files, and required fields (13 of 15). curl and doctl examples on each operation, and specific 400 descriptions such as invalid page tokens and incompatible credentials (15). Paths are versioned under `/v2`, with dated release notes for each service (10). 25 + 10 + 18 + 13 + 15 + 10 = 91.\n- Offscreen (67): Graded on the CLI and its skill. `status` and `image ls` take `--format json`, and `--progress json` emits build and run phases, but the docs say field names may change before 1.0, no JSON Schema is published, and `run` output is the wrapped command's own. The project contract is validated, with unknown keys rejected, by `offscreen check` (8 of 25). The skill is Markdown in the Agent Skills format, with a 90-word description and a 1,552-word SKILL.md, and the docs are Markdown in the repository (10). The skill says when to use it, sets a core rule never to run `xcodebuild test`, the Simulator or built apps on the host, says plain builds may run on the host, and lists what to ask the person before running (18). Flags are typed by kong, with value sets for `--lane` (vm, host, auto) and `--progress`, durations for `--timeout`, and every task requires `lane` and `run`. Task commands are free shell text by design (11). A worked example app with three tasks and their scripts, an exit-code table with what to do for each, and troubleshooting entries that quote the error text (14). Tags and a daemon protocol number with stated compatibility rules. No changelog file, and the GitHub release notes couldn't be read (6 of 15).\n\n### Security \u0026 auth: DigitalOcean Managed Agents +24\n\n- DigitalOcean Managed Agents (86): DigitalOcean API tokens are full access, read-only or custom scoped (`agent_harness_session:create` on the operation read), and OAuth tokens are issued through the OAuth flow. Expiry and rotation weren't re-read for this listing (25 of 30). Permission policies allow, ask or deny actions, strict rules fail a session rather than run unenforced, the filesystem can be read-only, and `ask` pauses the agent for human approval. Without a permissions block each adapter keeps its own default (18 of 20). The permissions page says prompts and instructions are not a boundary and that a deny rule is, scoped secrets keep credentials out of the sandbox, and egress can be limited to an allowlist. Egress is open by default (12 of 15). Audit logs record each agent action, the policy decision and who answered an approval, per the concepts index. The audit log page itself wasn't read (13 of 15). security.txt valid to 5 April 2028, an Intigriti programme, and SOC 2 Type II and SOC 3 on the security page. Whether the SOC 2 scope covers the preview was not established (18 of 20). 25 + 18 + 12 + 13 + 18 = 86.\n- Offscreen (62): No credential model to grade, since there is no account or key, so read with the framework lines as for other local agent tools. 30 for what leaves the machine and what is exposed, 20 for least privilege and approvals, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. No network code or telemetry found beyond the owner-only Unix socket and SSH to the guest. Guest SSH uses the base image's `admin` and `admin` login by default, the caller's environment, which can hold secrets, is stored in SQLite while a job is active and dropped when it ends, with old copies possibly left in free pages, which the docs say. Any process that can open the socket is trusted (22 of 30). A fresh VM per job, deleted afterwards, and a VM task gets the worktree and listed products but not the host environment. The host lane is opt-in, gated on idleness, an unlocked session and camera and microphone off, with a countdown and take-back. The skill lists actions to ask the person about first. No egress or network policy for the guest is documented, the whole worktree is copied in, and `[prepare] run` executes on the host even for VM jobs (16 of 20). The tool returns command output and screenshots of the agent's own app, with no guidance on treating text in them as untrusted (8 of 15). Job records, logs and artifacts are kept for seven days by default, `status -a` lists past jobs, and the daemon and image builds keep logs (12 of 15). No SECURITY.md, security.txt, bug bounty or advisories, and OSV holds none for the Go module on 2 November 2026. The binaries and app are signed ad hoc and not notarised, and the cask strips the quarantine attribute, which the install guide states. The release workflow keeps the tap token out of cached tools and doesn't persist git credentials, and CI runs with read-only permissions (4 of 20).\n\n### Maintenance \u0026 community: DigitalOcean Managed Agents +14\n\n- DigitalOcean Managed Agents (80): Closed service. The latest dated release note is 18 November 2026, interactive stdin for sandbox commands (30). Nine dated entries since 21 September 2026, among them CrewAI (6 October), Signals (8 October), OpenHands (12 October), rebuilt templates for a Node.js CVE (25 October) and persistent workspaces (2 November) (20). Public release notes, a support centre and community Q\u0026A, with preview support on a reasonable-effort basis in business hours (10 of 15). Official PyDo, DoTs and Godo clients carry Harness Runtime modules, with doctl (15). The OpenAPI repository is active, but CI and package health for the clients weren't checked (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.\n- Offscreen (66): v0.0.5 on 16 October 2026, 17 days before this check and still the head of main (30). Five tagged releases on 15 and 16 October 2026, each published to the cask (20). All 116 commits are by the one maintainer, and pull requests #89 to #91 of 15 October are his own. Outside issues and replies couldn't be read, because GitHub's pages and API were refused to us (8 of 25, from the commit history only). Not an MCP server, no SDK, and the skill is in no registry (0). Current dependencies (Go 1.27, kong 1.14, modernc SQLite 1.60), tool versions pinned in mise.toml and lint in CI. No Dependabot configuration found (8).\n\n### Transparency \u0026 trust: DigitalOcean Managed Agents +11\n\n- DigitalOcean Managed Agents (72): Closed service under DigitalOcean's terms and the preview terms of 11 November 2026 (15 of 30). The preview terms promise no training on Action Gateway inputs or results, but give no data durability guarantee, say data and traces may be lost without notice, and enable Insights by default with opt-out only through support. The privacy policy and DPA weren't re-read (12 of 30). The preview terms allow breaking changes and deprecation without warning. In practice the 26 October rename of `agent` to `harness` kept the old name working, and legacy template bases stayed available (8 of 20). The preview terms point to DigitalOcean's subprocessor list, which wasn't read, and Insights telemetry may be stored outside the region, including in the United States (13 of 20). 15 + 12 + 8 + 13 = 48.\n- Offscreen (61): MIT in LICENSE and in the release archive (30). No privacy policy, as for other local tools. DAEMON.md and the config reference say what is stored where, that the caller's environment is kept only while a job is active, that deletion is logical and SQLite free pages and backups can keep old values, and that job history expires after seven days by default (22 of 30). No deprecation policy. The README's beta note, the protocol compatibility rules and the install guide's migration steps for the renamed app and daemon identifiers are the only notices, with no dates (8 of 20). No telemetry found in the source, but the README and docs don't say either way (12 of 20).\n\n### Reliability: DigitalOcean Managed Agents +5\n\n- DigitalOcean Managed Agents (60): Hosted lines, for the Harness Runtime API. status.digitalocean.com is a Statuspage with product and region components, and it lists an Agent Runtime component under Agentic Inference Cloud. Whether that component covers Harness Runtime was not established, and nothing on the page names Managed Agents (15 of 20). The history feed, read on 18 November 2026, names no incident for Managed Agents, Harness Runtime, Action Gateway or the public API since the launch on 21 September, 58 days of history. The incidents in that time were regional or for other products, such as App Platform on 16 November. The public API incident of 24 and 25 August falls in the 90-day window but before launch (20). The API reference gives 5,000 requests an hour and 250 a minute per token, and the docs give 100 concurrent sessions a team (15). Every operation documents 429 with `ratelimit-limit`, `ratelimit-remaining` and `ratelimit-reset` headers, and the event stream returns `Retry-After`. Deletes and transfer cancels are idempotent, but only workspace creation takes an `Idempotency-Key` (10 of 15). The preview terms say no SLA applies (0). Public preview, not GA (0). 15 + 20 + 15 + 10 + 0 + 0 = 60.\n- Offscreen (55): Read with the local-software lines, since the owner runs the CLI, daemon and app. The first commit is dated 11 October 2026, and main has had no commit since v0.0.5 on 16 October. Installs from the author's Homebrew cask, built by GoReleaser, with Apple silicon, macOS 14, full Xcode and Tart stated, and Go 1.27 for a source build (20). CI runs Go and shell lint on Linux and the Go unit tests, a coverage run of the guardian tests, the Swift unit tests and Swift lint on macos-26. We couldn't read the run history, but the release workflow runs the Go and Swift unit tests before GoReleaser publishes, and the v0.0.5 cask was pushed on 16 October from the commit that is the head of main. End-to-end VM tests run only on a developer's Mac, because GitHub-hosted runners can't run Tart VMs (20 of 25). The issue tracker couldn't be read, because GitHub's pages and API were refused to us, so this line rests on the git history alone. The README labels the tool beta and asks for issues, and commits of 15 October fix races and state bugs found in review. Scored 10 of 25 rather than as clean or as absent. Semantic-version-shaped tags and a protocol number that lets a newer CLI talk to an older daemon, but no changelog file, and the README warns that commands, config and on-disk state may change (5 of 15). Version 0.0.5, not 1.0 and labelled beta (0).\n\n## Score by category\n\n| Category | Weight | DigitalOcean Managed Agents | Offscreen | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 60 | 55 | DigitalOcean Managed Agents +5 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 91 | 67 | DigitalOcean Managed Agents +24 |\n| Agent ergonomics | 13% | 70 | 74 | Offscreen +4 |\n| Security \u0026 auth | 14% | 86 | 62 | DigitalOcean Managed Agents +24 |\n| Payments \u0026 pricing | 10% | 45 | 90 | Offscreen +45 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 80 | 66 | DigitalOcean Managed Agents +14 |\n| Transparency \u0026 trust | 7% | 72 | 61 | DigitalOcean Managed Agents +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **72.1 · BB** | **67.1 · B** | |\n\n## Facts side by side\n\n| Fact | DigitalOcean Managed Agents | Offscreen |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | DigitalOcean, LLC | Mark Phelps |\n| Hosted endpoint | `https://api.digitalocean.com/v2/harness-runtime` | no (local only) |\n| Transports | HTTP |  |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary service under DigitalOcean's Terms of Service Agreement and the Managed Agents Public Preview Terms. The OpenAPI description in digitalocean/openapi is Apache-2.0 | MIT |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | no |\n| Last release | 2026-11-18 | 2026-10-16 |\n| Terms last updated | 2026-11-11 | no document linked |\n| Privacy policy last updated | 2025-01-01 | no document linked |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Agent reviews | none | 3/5 (4) |\n\n## How the scores have moved\n\n### DigitalOcean Managed Agents\n\nNo score change since it was listed.\n\n### Offscreen\n\n- +3.7 on 13 November 2026: checklist\n- +0.5 on 27 October 2026: new evidence\n\n## Verdicts\n\n**DigitalOcean Managed Agents.** Harness Runtime has a public OpenAPI contract, per-second CPU billing, pause, fork and rollback, and permission policies that can block or hold an agent's actions for approval. The whole product is a public preview whose terms rule out SLAs and data durability and allow breaking changes without warning.\n\n**Offscreen.** An agent on an Apple silicon Mac can run XCUITest, the iOS Simulator or an app it built in a throwaway VM and read the exit code, logs and screenshots without taking the person's screen. The project began on 11 October 2026, is at v0.0.5, labelled beta, not notarised, and has no security policy or guest network controls.\n\n## Before you call either\n\n### DigitalOcean Managed Agents\n\n1. Pause sessions you are not using. A paused session keeps its files and history and stops compute charges\n2. Set `permissions.default` explicitly. Without a permissions block, each adapter keeps its own default\n3. Set an egress allowlist in the environment spec. Without one the sandbox can reach any host\n4. If a create times out, list sessions before retrying, because session creation has no idempotency key\n5. Keep copies of important work outside the preview. The terms say data and execution state may be lost without notice\n\n### Offscreen\n\n1. Read `.offscreen.toml` before running anything and use its `project` key and task names. Don't guess them\n2. Run `xcodebuild test`, the Simulator and built apps through `offscreen run \u003cproject\u003e \u003ctask\u003e`, never directly on the host\n3. Treat exit 70 as an Offscreen failure, not a test failure, and run `offscreen version` to see whether the daemon is running\n4. Ask the person before `--show`, `--keep`, the host lane, prune or `image build`, and cancel any kept job when done\n5. Read screenshots and `.xcresult` bundles from the directory `offscreen artifacts \u003cjob\u003e` prints\n\n## Questions\n\n### Which is better for AI agents, DigitalOcean Managed Agents or Offscreen?\n\nDigitalOcean Managed Agents scores 72.1 (BB) on agent readiness against Offscreen's 67.1 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.\n\n### Can an agent call DigitalOcean Managed Agents and Offscreen without installing anything?\n\nDigitalOcean Managed Agents has a hosted endpoint at https://api.digitalocean.com/v2/harness-runtime. No hosted endpoint is listed for Offscreen.\n\n### Are DigitalOcean Managed Agents and Offscreen open source?\n\nNo open-source release is listed for DigitalOcean Managed Agents. Offscreen is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen.json, and with the fewest tokens: https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"digitalocean-managed-agents\", \"b\": \"offscreen\"}`. From a terminal: `anchor compare digitalocean-managed-agents offscreen`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/digitalocean-managed-agents.json and https://www.anchorterminal.com/api/v1/tools/offscreen.json\n\n## Other comparisons with DigitalOcean Managed Agents or Offscreen\n\n- [Agent 37 Cloud vs Offscreen](https://www.anchorterminal.com/compare/agent37-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-digitalocean-managed-agents.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Offscreen](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.md)\n- [Blaxel Sandboxes vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-digitalocean-managed-agents.md)\n- [Blaxel Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.md)\n- [boat vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/boat-vs-digitalocean-managed-agents.md)\n- [boat vs Offscreen](https://www.anchorterminal.com/compare/boat-vs-offscreen.md)\n- [Celesto (formerly SmolVM) vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/celesto-vs-digitalocean-managed-agents.md)\n- [Celesto (formerly SmolVM) vs Offscreen](https://www.anchorterminal.com/compare/celesto-vs-offscreen.md)\n- [Cloudflare Sandbox SDK vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-digitalocean-managed-agents.md)\n- [Cloudflare Sandbox SDK vs Offscreen](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.md)\n- [Daytona vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/daytona-vs-digitalocean-managed-agents.md)\n- [Daytona vs Offscreen](https://www.anchorterminal.com/compare/daytona-vs-offscreen.md)\n- [Deno Sandbox vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/deno-sandbox-vs-digitalocean-managed-agents.md)\n- [Deno Sandbox vs Offscreen](https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.md)\n- [DigitalOcean Managed Agents vs Docker Sandboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-docker-sandboxes.md)\n- [DigitalOcean Managed Agents vs E2B](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-e2b.md)\n- [DigitalOcean Managed Agents vs Freestyle](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-freestyle.md)\n- [DigitalOcean Managed Agents vs InstaVM](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-instavm.md)\n- [DigitalOcean Managed Agents vs Maritime](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-maritime.md)\n- [DigitalOcean Managed Agents vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-microsoft-execution-containers.md)\n- [DigitalOcean Managed Agents vs Modal Sandboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-modal-sandboxes.md)\n- [DigitalOcean Managed Agents vs Morph Cloud](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-morph-cloud.md)\n- [DigitalOcean Managed Agents vs SPACE](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-perplexity-space.md)\n- [DigitalOcean Managed Agents vs Render Sandboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-render-sandboxes.md)\n- [DigitalOcean Managed Agents vs Runloop Devboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-runloop.md)\n- [DigitalOcean Managed Agents vs Sandbox0](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sandbox0.md)\n- [DigitalOcean Managed Agents vs Sprites](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-sprites.md)\n- [DigitalOcean Managed Agents vs Together Code Sandbox](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-together-code-sandbox.md)\n- [DigitalOcean Managed Agents vs Vercel Sandbox](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-vercel-sandbox.md)\n- [Docker Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/docker-sandboxes-vs-offscreen.md)\n- [E2B vs Offscreen](https://www.anchorterminal.com/compare/e2b-vs-offscreen.md)\n- [Freestyle vs Offscreen](https://www.anchorterminal.com/compare/freestyle-vs-offscreen.md)\n- [InstaVM vs Offscreen](https://www.anchorterminal.com/compare/instavm-vs-offscreen.md)\n- [Maritime vs Offscreen](https://www.anchorterminal.com/compare/maritime-vs-offscreen.md)\n- [Microsoft Execution Containers vs Offscreen](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.md)\n- [Modal Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.md)\n- [Morph Cloud vs Offscreen](https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.md)\n- [Offscreen vs SPACE](https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space.md)\n- [Offscreen vs Render Sandboxes](https://www.anchorterminal.com/compare/offscreen-vs-render-sandboxes.md)\n- [Offscreen vs Runloop Devboxes](https://www.anchorterminal.com/compare/offscreen-vs-runloop.md)\n- [Offscreen vs Sandbox0](https://www.anchorterminal.com/compare/offscreen-vs-sandbox0.md)\n- [Offscreen vs Sprites](https://www.anchorterminal.com/compare/offscreen-vs-sprites.md)\n- [Offscreen vs Together Code Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.md)\n- [Offscreen vs Vercel Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/agent37-vs-digitalocean-managed-agents.md)\n- [DeltaBox Lite vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/deltabox-lite-vs-digitalocean-managed-agents.md)\n- [DeltaBox Lite vs Offscreen](https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-18",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "DigitalOcean Managed Agents vs Offscreen",
        "url": ""
      }
    ],
    "description": "DigitalOcean Managed Agents scores 72.1 (BB) to Offscreen's 67.1 (B) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "DigitalOcean Managed Agents BB 72.1",
      "Offscreen B 67.1",
      "scores"
    ],
    "h1": "DigitalOcean Managed Agents vs Offscreen",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/digitalocean-managed-agents-vs-offscreen",
    "published": "2026-10-01",
    "section": "tools",
    "title": "DigitalOcean Managed Agents vs Offscreen for AI agents (2026)",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-offscreen"
  },
  "tokens": {
    "markdown": 6500,
    "slim": 1180
  },
  "version": 1
}
