{
  "data": {
    "a": {
      "slug": "boat",
      "name": "boat",
      "vendor": "Dedale AI, Corp.",
      "vendorUrl": "https://boat.dev",
      "company": "boat.dev",
      "kind": "http-api",
      "category": "code-sandboxes",
      "summary": "boat runs persistent Ubuntu virtual machines for AI agents, with SSH, Docker, a desktop, snapshots and forking, in data centres in Germany, Finland and France. It is driven through a REST API, Python and TypeScript SDKs and a CLI.",
      "url": "https://www.anchorterminal.com/tools/boat",
      "markdownUrl": "https://www.anchorterminal.com/tools/boat.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/boat.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/boat.json",
      "dns": "boat.grade.anchorterminal.com",
      "license": "Proprietary service under boat's terms. The TypeScript SDK `@boatdev/sdk` is MIT",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "boat-sdk"
        },
        {
          "registry": "npm",
          "name": "@boatdev/sdk"
        }
      ],
      "auth": "api-key",
      "authNotes": "Bearer API keys starting `boat_`, created with `boat api-key create` or in the dashboard after sign-up. Keys take scopes or presets (`read-only`, `full-sandbox`, `ci`, `admin`), a TTL and an optional single-sandbox limit, and can be rotated and revoked. An agent can register itself through boat.dev/auth.md, but a person must claim it before it can create sandboxes.",
      "pricing": "usage",
      "pricingNotes": "$0.036 an hour for the default 4 vCPU, 8 GB sandbox, billed per second, from $0.018 (small) to $0.20 (xlarge). Plans from $20 a month return their price as compute and set start and concurrency limits. The 7-day trial (25 compute hours) needs a card.",
      "priceSummary": "$0.036 / unit",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the API overview, OpenAPI file, pricing summary or agent sign-up docs (checked 2026-11-18). Payment is a Stripe subscription and a prepaid wallet.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://docs.boat.dev",
      "llmsTxt": "https://docs.boat.dev/llms.txt",
      "openapi": "https://docs.boat.dev/openapi/boat-v1.yaml",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs",
        "sandbox.persist",
        "sandbox.browser"
      ],
      "tags": [
        "hosted",
        "usage",
        "vm",
        "openapi",
        "llms-txt",
        "python",
        "typescript",
        "cli",
        "eu",
        "idempotency",
        "webhooks",
        "yc"
      ],
      "lastRelease": "2026-10-28",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 71.8,
        "grade": "BB",
        "agentReady": true,
        "rank": 255,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 7,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 93,
          "maintenance": 76,
          "payments": 45,
          "reliability": 60,
          "schema": 90,
          "security": 67,
          "transparency": 69
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "boat publishes an OpenAPI 3.1 contract with 123 operations, per-hour prices, scoped expiring keys and idempotent creates for full Ubuntu VMs in the EU. It has no security.txt, SLA or readable incident history, SOC 2 is in progress, and the trial needs a card.",
        "bestFor": "Long-lived, full Ubuntu VMs with Docker, a desktop and Chrome for coding agents, evals and products that give each user a sandbox, hosted in the EU.",
        "strengths": [
          "Public OpenAPI 3.1 file with 123 operations, llms.txt and a Markdown copy of every docs page",
          "Per-hour prices from $0.018 to $0.20 by size and start limits per plan, published without login",
          "Scoped API keys with presets, expiry and per-sandbox limits",
          "`Idempotency-Key` on create and fork, and every 429 carries `Retry-After`",
          "Dated `Deprecation` and `Sunset` headers on the old Box surfaces after the rename"
        ],
        "weaknesses": [
          "No security.txt or bug bounty, and SOC 2 is in progress",
          "No SLA, and the status page history could not be read",
          "The free trial needs a card, and agent sign-up still needs a person to claim the account",
          "Outbound network access is open by default, with no API setting for network rules",
          "No public changelog for the API or SDKs"
        ],
        "agentNotes": [
          "Send an `Idempotency-Key` on every create and fork, and resend the same key and body after a timeout or 5xx",
          "Check `GET /limits` before a batch of starts. A retry loop does not help once the hour or day start limit is full",
          "Set `detached: true` for any command that may run past 30 seconds, then attach to its stream",
          "If a 502 `sandbox_direct_failed` has `retryable` false, check the command's effect before you run it again",
          "Use a `read-only` or per-sandbox key with a short TTL for anything that does not create sandboxes"
        ],
        "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": 71.8
          }
        ],
        "editorialScores": {
          "ergonomics": 93,
          "maintenance": 76,
          "payments": 45,
          "reliability": 60,
          "schema": 90,
          "security": 67,
          "transparency": 74
        },
        "provenanceScore": 64,
        "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 boat-sdk  # or npm install @boatdev/sdk, or curl -fsSL https://boat.dev/install | sh",
        "http": "curl -sS -X POST https://boat.dev/api/v1/sandboxes -H \"Authorization: Bearer $BOAT_API_KEY\" -H \"Idempotency-Key: $(uuidgen)\" -H \"Content-Type: application/json\" -d '{\"ttlSeconds\":3600}'"
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/boat"
      },
      "area": "agent-runtime",
      "unitPrices": [
        {
          "item": "Default sandbox (4 vCPU, 8 GB)",
          "unit": "compute-unit",
          "usd": 0.036,
          "note": "Per hour while running, billed per second. Other sizes from $0.018 (small) to $0.20 (xlarge)"
        },
        {
          "item": "Extra start above plan limits",
          "unit": "tx",
          "usd": 0.03,
          "note": "Up to 1.5 times the limit, then $0.05 and $0.07"
        }
      ],
      "provenance": {
        "legalEntity": "Dedale AI, Corp.",
        "domain": "boat.dev",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://boat.dev/terms",
        "privacy": "https://boat.dev/privacy",
        "statusPage": "https://status.ascii.dev",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-11-18",
        "notes": [
          "boat.dev/robots.txt allows all agents except /oauth2/ and /agent/. docs.boat.dev/robots.txt allows all but /cdn-cgi/ and /_next/ and sets `Content-Signal: ai-train=yes, search=yes, ai-input=yes`. status.ascii.dev/robots.txt answered 404.",
          "The terms (effective 12 October 2026) name Dedale AI, Corp., a Delaware corporation at 1111B S Governors Avenue, Dover, under Delaware law with AAA arbitration. The terms forbid automated signup to obtain extra trials.",
          "The privacy policy (effective 12 October 2026) names OVH, Hetzner, Stripe, GitHub and Google among processors and says sandbox content is not used to train foundation models.",
          "boat.dev/.well-known/security.txt answered 404. Security reports go to support.",
          "The domain's registration date was not looked up."
        ],
        "score": 64
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/boat.json",
      "live": {
        "slug": "boat",
        "vendorStatus": {
          "page": "https://status.ascii.dev",
          "indicator": "unknown",
          "summary": "no machine-readable status found",
          "checkedAt": "2026-11-18T21:39:27.388224385Z"
        },
        "updatedAt": "2026-11-18T21:39:27.388224385Z"
      }
    },
    "answer": "boat scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 4 of 7 scored categories. Render Sandboxes leads on reliability, maintenance \u0026 community and transparency \u0026 trust.",
    "b": {
      "slug": "render-sandboxes",
      "name": "Render Sandboxes",
      "vendor": "Render Services, Inc.",
      "vendorUrl": "https://render.com/sandboxes",
      "company": "render.com",
      "kind": "sdk",
      "category": "code-sandboxes",
      "summary": "Render Sandboxes runs isolated Linux environments in Firecracker microVMs for AI agents and untrusted code, created and controlled through the Render CLI and the TypeScript and Python SDKs. It is in public beta, in the Oregon region.",
      "url": "https://www.anchorterminal.com/tools/render-sandboxes",
      "markdownUrl": "https://www.anchorterminal.com/tools/render-sandboxes.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/render-sandboxes.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/render-sandboxes.json",
      "dns": "render-sandboxes.grade.anchorterminal.com",
      "repo": "https://github.com/render-oss/sdk",
      "license": "The service is proprietary under Render's terms. The SDK is MIT (TypeScript `@renderinc/sdk`) and Apache-2.0 (Python `render`)",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "npm",
          "name": "@renderinc/sdk"
        },
        {
          "registry": "pypi",
          "name": "render"
        }
      ],
      "auth": "api-key",
      "authNotes": "A Render API key (`rnd_...`) created by a person in the dashboard's Account Settings, sent with the workspace ID (`RENDER_WORKSPACE_ID`). The key reaches every workspace its owner belongs to. Scoped API keys are listed as a beta limitation, not yet generally available. Rate limits apply per user across all of that user's keys.",
      "pricing": "usage",
      "pricingNotes": "$0.12 per CPU-hour of CPU used, plus $0.019 per GB-hour of provisioned memory, billed per second and not while suspended. Four plans from `1c-2g` ($0.038 an hour of memory) to `8c-16g`. No free sandbox allowance was found. Hobby workspaces get 100 concurrent sandboxes a group, Pro 1,000.",
      "priceSummary": "$0.12 / vCPU-hr",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the sandboxes documentation bundle, the limits and pricing page or the SDK source (checked 2026-11-18). Billing is through a Render workspace.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 27,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-11-18"
      },
      "docsUrl": "https://render.com/docs/sandboxes",
      "llmsTxt": "https://render.com/llms.txt",
      "capabilities": [
        "sandbox.code",
        "sandbox.fs",
        "sandbox.persist"
      ],
      "tags": [
        "hosted",
        "usage",
        "beta",
        "microvm",
        "typescript",
        "python",
        "cli",
        "llms-txt",
        "status-page",
        "soc2"
      ],
      "lastRelease": "2026-11-16",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 67.5,
        "grade": "B",
        "agentReady": false,
        "rank": 441,
        "ranked": true,
        "rankOf": 1557,
        "categoryRank": 12,
        "methodology": "1.0",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 73,
          "maintenance": 85,
          "payments": 30,
          "reliability": 68,
          "schema": 79,
          "security": 63,
          "transparency": 80
        },
        "assessment": {
          "confidence": "medium",
          "date": "2026-11-18"
        },
        "negative": 0,
        "verdict": "Render Sandboxes has per-operation rate limits, per-second prices and typed SDKs in three languages, with sandboxes that suspend when idle and resume from snapshots. It is a public beta in one region, with no public REST API, no idempotency on create and API keys that reach every workspace.",
        "bestFor": "Teams already on Render that want agent sandboxes beside their services, or anyone who needs long-running sandboxes with idle suspension and process snapshots.",
        "strengths": [
          "Prices published per CPU-hour, minute and second, with CPU billed on use and nothing billed while suspended",
          "Rate limits published per operation, and per-group concurrency caps of 100 (Hobby) or 1,000 (Pro)",
          "Typed SDKs in TypeScript, Python and Go, with 18 named error types and a dated semver changelog",
          "Filesystem and process snapshots, idle suspension and runtime timeouts up to 30 days or none",
          "SOC 2 Type 2, ISO 27001, a HackerOne programme and a valid security.txt"
        ],
        "weaknesses": [
          "Public beta since 4 November 2026, with one region (Oregon) and no SLA outside Enterprise",
          "No public REST API or OpenAPI document. The CLI and SDKs are the only documented interfaces",
          "API keys reach every workspace of their owner, and scoped keys are not yet generally available",
          "Outbound network access is open by default, and credential brokering is alpha",
          "No free sandbox allowance, and no idempotency key for creating sandboxes"
        ],
        "agentNotes": [
          "Set `timeoutSeconds` when you create a sandbox. A disabled timeout keeps the sandbox, and its billing, running until you terminate it",
          "Pass `networkPolicy` with an allowlist or deny-all at creation, since the default allows outbound traffic to any destination",
          "Check the exit event's `exit_code` after `exec`. A nonzero exit code does not raise an error in the SDK",
          "If create returns 429, check whether the group is at its concurrency cap before you retry. Rate and concurrency limits share the same code",
          "Use `ttlSeconds` on snapshots with SDK 1.9.0 or later. The `expiresAt` option was removed in 1.9.0"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "1.0",
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 67.5
          }
        ],
        "editorialScores": {
          "ergonomics": 73,
          "maintenance": 85,
          "payments": 30,
          "reliability": 68,
          "schema": 79,
          "security": 63,
          "transparency": 63
        },
        "provenanceScore": 97,
        "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": "npm install @renderinc/sdk  # or pip install render, or brew install render"
      },
      "letme": {
        "capability": "https://letme.dev/sandbox.code",
        "tool": "https://letme.dev/render-sandboxes"
      },
      "sameCompany": [
        "render-mcp-server"
      ],
      "area": "agent-runtime",
      "unitPrices": [
        {
          "item": "Sandbox CPU",
          "unit": "vcpu-hour",
          "usd": 0.12,
          "note": "Billed on CPU used. Memory is extra at $0.019 per GB-hour of provisioned RAM"
        }
      ],
      "provenance": {
        "legalEntity": "Render Services, Inc.",
        "domain": "render.com",
        "domainRegistered": "1998-10-01",
        "endpointOnVendorDomain": true,
        "terms": "https://render.com/terms",
        "privacy": "https://render.com/privacy",
        "statusPage": "https://status.render.com",
        "changelog": "https://render.com/changelog",
        "securityTxt": "valid",
        "checked": "2026-11-18",
        "notes": [
          "The terms, last modified 10 July 2026, were re-read on 18 November 2026. Legal entity, address and domain date are carried from render-mcp-server (checked 8 October 2026).",
          "render.com/robots.txt allows all agents except /contact-sales, /newsletters/ and /lp/, names ClaudeBot and Claude-User, and sets `Content-Signal: ai-train=yes, search=yes, ai-input=yes`. status.render.com disallows /api/ and /embed/ only.",
          "render.com/.well-known/security.txt names security@render.com and the HackerOne programme and expires on 3 October 2027 (read 18 November 2026).",
          "status.render.com has no Sandboxes component. Its components cover the website, the Platform API, the REST API and services by region.",
          "The changelog entry for the beta is dated 11 November 2026, a week after the 4 November blog post."
        ],
        "score": 97
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/render-sandboxes.json",
      "live": {
        "slug": "render-sandboxes",
        "vendorStatus": {
          "page": "https://status.render.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-11-18T22:38:49.26685015Z"
        },
        "updatedAt": "2026-11-18T22:38:49.26685015Z"
      }
    },
    "edges": [
      {
        "by": 20,
        "category": "ergonomics",
        "leads": "boat",
        "name": "Agent ergonomics",
        "reasons": {
          "a": "Lists take `limit` from 1 to 200, commands can stream or detach, and a file read above 5 MiB returns `413` with a pointer to a signed download URL (20). Cursor pagination with `hasMore` and filters by name, name prefix, label and state (20). A stable error envelope with `code`, `message`, `details` and `requestId`, and a per-status table of what to do (20). `Idempotency-Key` on create and fork, kept 24 hours, with `409 idempotency_in_progress` and `409 idempotency_key_reused`, and per-code guidance on whether a command may have run (18). `ttlSeconds` defaults to one hour, the body of a create can be empty, and SDKs exist in Python and TypeScript beside the CLI with `--json` on every command (15). 20+20+20+18+15 = 93.",
          "b": "Downloads take `maxSizeBytes` (256 MiB default since 1.8.0), exec streams output as events, and lists take a limit (15). `list` filters by status and name with cursor pagination, and snapshots and images list by name and status (18). Typed errors for each known API code since 1.9.0, such as `SandboxGroupSuspendedError` and `SandboxEndedError` with the sandbox's status, and 429 for both rate and concurrency caps. A nonzero exit code does not raise, which the docs state (17). No idempotency key for creating sandboxes or snapshots. The CLI previews stop and delete without `--confirm` (8 of 20). Sensible defaults (`1c-2g`, the default group) with few required parameters, SDKs in TypeScript, Python and Go plus the CLI (15). 15+18+17+8+15 = 73."
        },
        "scores": {
          "a": 93,
          "b": 73
        }
      },
      {
        "by": 15,
        "category": "payments",
        "leads": "boat",
        "name": "Payments \u0026 pricing",
        "reasons": {
          "a": "No x402, MPP or L402 (0). Per-hour prices for each size published without login, from $0.018 an hour for `small` to $0.20 for `xlarge`, with overage and start prices (30). The 7-day trial (25 compute hours) needs a card in Stripe Checkout (0). An agent can register itself through the auth.md agent registration protocol or AgentID, but a person has to claim the agent or verify the AgentMail organisation and enter a card before a sandbox can start (15 of 30). 0+30+0+15 = 45.",
          "b": "No x402, MPP or L402 (0). Per-unit prices published without login, $0.12 per CPU-hour used and $0.019 per GB-hour of memory, also given per minute and per second (30). No free sandbox allowance was found. Hobby workspaces cost $0 but sandbox compute is billed from the first second, and whether a payment method is needed first was not stated (0). A person signs up and creates the API key in the dashboard (0). 0+30+0+0 = 30."
        },
        "scores": {
          "a": 45,
          "b": 30
        }
      },
      {
        "by": 11,
        "category": "schema",
        "leads": "boat",
        "name": "Schema \u0026 documentation",
        "reasons": {
          "a": "A public OpenAPI 3.1 file, docs.boat.dev/openapi/boat-v1.yaml, with 123 operations, each with an operationId and a summary (25). llms.txt indexing every page and a Markdown copy of each (10). The API overview and guides say when to create, resume or fork, when to run a command detached, when to use a saved snapshot, and what each sandbox state allows (18). 86 enums and required fields in the OpenAPI file, and list calls reject unknown query parameters with `400 invalid_query` (14). curl, Python and TypeScript examples, a table of error codes by status with what to do, and a retryable flag on 502s (15). Paths versioned under `/v1`, but no changelog was found (8 of 15). 25+10+18+14+15+8 = 90.",
          "b": "No public REST API or OpenAPI document for sandboxes, and the SDK README lists the REST API as \"Soon\". The SDKs are typed and generated from Render's API schema, and the TypeScript and Python references document every method, which we count as 15 of 25 for an SDK, the reading modal-sandboxes was given (15). render.com/llms.txt, a Markdown twin of every page and a single sandboxes bundle at /docs/sandboxes/all (10). The guides say when to use idle suspension, runtime timeouts, filesystem or process snapshots and sandbox groups, and what a deleted snapshot breaks (15). Typed SDK inputs with a plan enum, a network policy type and documented bounds such as a 64-character snapshot name (12). Examples in CLI, TypeScript and both Python styles on every page, and 18 named error types with when each is thrown. No list of API error codes (14). Semver SDK changelog with dates and Render's product changelog. The 1.9.0 breaking change came in a minor version, called out in the changelog (13). 15+10+15+12+14+13 = 79."
        },
        "scores": {
          "a": 90,
          "b": 79
        }
      },
      {
        "by": 11,
        "category": "transparency",
        "leads": "render-sandboxes",
        "name": "Transparency \u0026 trust",
        "reasons": {
          "a": "Closed service under terms of 12 October 2026 from Dedale AI, Corp., a Delaware corporation (15). The terms, privacy policy and docs agree on retention. A stopped sandbox's disk is kept at least 14 days, saved snapshots have no scheduled expiry, and zero data retention can be turned on. The terms say the cleanup job does not yet delete in production. A DPA is available on request (25 of 30). The Box to boat rename on 15 September 2026 put `Deprecation` and `Sunset` headers on old surfaces with a dated sunset of 31 October 2026, and deprecated endpoints are marked in the reference (18 of 20). Infrastructure hosts (OVH, Hetzner) and other processors are named, sandboxes run in Germany, Finland and France, and snapshot copies can be stored outside the EU (16 of 20). 15+25+18+16 = 74.",
          "b": "The service is closed, under terms last modified 10 July 2026. The SDKs are open source (MIT and Apache-2.0) (20 of 30). A privacy policy and DPA, plus stated lifetimes for sandbox data. The filesystem is deleted on termination, suspended sandboxes stay resumable 30 days, and snapshots expire 30 days after last use unless the TTL is changed (20 of 30). The docs warn that APIs, defaults and limits might change during the beta, and the SDK changelog marks breaking changes with migration steps, but no deprecation policy or notice period was found (8 of 20). Eight sub-processors with countries on render.com/security, and the region (Oregon) is stated (15 of 20). 20+20+8+15 = 63."
        },
        "scores": {
          "a": 69,
          "b": 80
        }
      },
      {
        "by": 9,
        "category": "maintenance",
        "leads": "render-sandboxes",
        "name": "Maintenance \u0026 community",
        "reasons": {
          "a": "Python SDK `boat-sdk` 1.13.0 on 28 October 2026 (30). 25 SDK releases from 1.0.0 on 16 September to 1.13.0 on 28 October 2026 on PyPI (20). Closed service with a Discord, a support page and a blog, but no public changelog or tracker (8 of 25). Official SDKs in Python and TypeScript (`@boatdev/sdk` 1.13.0) generated from the OpenAPI file (15). No public source repository or CI for the SDKs was found (3 of 10). 30+20+8+15+3 = 76.",
          "b": "SDK 1.9.0 on 16 November 2026 (30). Eight SDK releases in the 90 days, from 1.1.0 on 10 September to 1.9.0, five of them since 17 October (20). 118 commits since 18 October from Render staff and release bots, the last on 18 November. Two open pull requests. The issue list draws in a script and could not be read, so responsiveness is not established (10 of 25). Official SDKs in TypeScript, Python and Go, current with the docs (15). CI for both languages with pinned actions, Dependabot configured. The result of the latest run was not seen (10). 30+20+10+15+10 = 85."
        },
        "scores": {
          "a": 76,
          "b": 85
        }
      },
      {
        "by": 8,
        "category": "reliability",
        "leads": "render-sandboxes",
        "name": "Reliability",
        "reasons": {
          "a": "Hosted reading. A status page at status.ascii.dev, linked from the docs, draws its system status and metrics in a script our reader could not run, so component history was not confirmed (15 of 20). No readable incident history (5). Limits published per plan with numbers, from 12 starts a minute and 100 sandboxes at once on the $20 plan to 90 a minute and 2,000 on the $2,000 plan, plus 10,000 requests a minute per IP (15). Every 429 sends `Retry-After`, `RateLimit` headers carry the remaining starts, 503s carry `retryAfterSeconds`, the docs give a backoff example, and create and fork take an `Idempotency-Key` (15). No SLA found. The docs cite a measured 99.95% sandbox uptime, and the terms disclaim uptime warranties (0). The API is v1 with no beta label (10). 15+5+15+15+0+10 = 60.",
          "b": "Scored on the hosted checklist, since sandboxes run on Render's infrastructure and the SDKs and CLI are clients of its API, the reading given to modal-sandboxes and vercel-sandbox. status.render.com is a Statuspage with incident history, though it has no Sandboxes component (20). Its history feed, read on 18 November 2026, has no incident naming sandboxes. Since the 4 November beta it lists API performance issues on 11 November for 18 minutes (13:17 to 13:35 UTC, dashboard and API requests) and a maintenance window announced on 10 November, with the REST API down for up to 30 minutes on 18 November. Earlier in the 90 days, builds and deploys did not start in any region on 14 October. Minor for this surface (20). Rate limits per operation with numbers, such as 100 creates and 1,000 execs a minute per user, and per-group concurrency caps (15). The docs say limits return 429, and the API schema in the SDK source documents `Retry-After` and `RateLimit-*` headers, but there is no backoff guidance in the sandbox docs and no idempotency key on create (8 of 15). The pricing page lists contractual uptime SLAs for Enterprise without publishing their terms (5 of 10). Public beta, not generally available (0). 20+20+15+8+5+0 = 68."
        },
        "scores": {
          "a": 60,
          "b": 68
        }
      }
    ],
    "facts": [
      {
        "a": "HTTP API",
        "b": "SDK + MCP",
        "name": "Kind"
      },
      {
        "a": "Dedale AI, Corp.",
        "b": "Render Services, Inc.",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Proprietary service under boat's terms. The TypeScript SDK `@boatdev/sdk` is MIT",
        "b": "The service is proprietary under Render's terms. The SDK is MIT (TypeScript `@renderinc/sdk`) and Apache-2.0 (Python `render`)",
        "name": "Licence"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-28",
        "b": "2026-11-16",
        "name": "Last release"
      },
      {
        "a": "no date given",
        "b": "2026-07-10",
        "name": "Terms last updated"
      },
      {
        "a": "no date given",
        "b": "2026-07-10",
        "name": "Privacy policy last updated"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Customer content may train models"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict automated access"
      },
      {
        "a": "not found in the text",
        "b": "not found in the text",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "not found in the text",
        "b": "yes",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "yes",
        "b": "yes",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "27 stars",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "boat scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 4 of 7 scored categories. Render Sandboxes leads on reliability, maintenance \u0026 community and transparency \u0026 trust.",
        "question": "Which is better for AI agents, boat or Render Sandboxes?"
      },
      {
        "answer": "No hosted endpoint is listed for boat. No hosted endpoint is listed for Render Sandboxes.",
        "question": "Can an agent call boat and Render Sandboxes without installing anything?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Schema \u0026 documentation, 90 against 79",
          "Agent ergonomics, 93 against 73",
          "Payments \u0026 pricing, 45 against 30"
        ],
        "also": [
          "Agent-ready, a grade of BB or better"
        ],
        "goodFor": "Long-lived, full Ubuntu VMs with Docker, a desktop and Chrome for coding agents, evals and products that give each user a sandbox, hosted in the EU.",
        "slug": "boat",
        "watchFor": "No security.txt or bug bounty, and SOC 2 is in progress"
      },
      {
        "aheadOn": [
          "Reliability, 68 against 60",
          "Maintenance \u0026 community, 85 against 76",
          "Transparency \u0026 trust, 80 against 69"
        ],
        "also": null,
        "goodFor": "Teams already on Render that want agent sandboxes beside their services, or anyone who needs long-running sandboxes with idle suspension and process snapshots.",
        "slug": "render-sandboxes",
        "watchFor": "Public beta since 4 November 2026, with one region (Oregon) and no SLA outside Enterprise"
      }
    ],
    "history": null,
    "job": {
      "capability": "sandbox.code",
      "name": "Code sandboxes"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs boat",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes.json",
        "title": "Amazon Bedrock AgentCore Code Interpreter vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-boat.json",
        "title": "Blaxel Sandboxes vs boat",
        "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-boat"
      },
      {
        "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-render-sandboxes.json",
        "title": "Blaxel Sandboxes vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-celesto.json",
        "title": "boat vs Celesto (formerly SmolVM)",
        "url": "https://www.anchorterminal.com/compare/boat-vs-celesto"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-cloudflare-sandbox-sdk.json",
        "title": "boat vs Cloudflare Sandbox SDK",
        "url": "https://www.anchorterminal.com/compare/boat-vs-cloudflare-sandbox-sdk"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-daytona.json",
        "title": "boat vs Daytona",
        "url": "https://www.anchorterminal.com/compare/boat-vs-daytona"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-deltabox-lite.json",
        "title": "boat vs DeltaBox Lite",
        "url": "https://www.anchorterminal.com/compare/boat-vs-deltabox-lite"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-deno-sandbox.json",
        "title": "boat vs Deno Sandbox",
        "url": "https://www.anchorterminal.com/compare/boat-vs-deno-sandbox"
      },
      {
        "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-docker-sandboxes.json",
        "title": "boat vs Docker Sandboxes",
        "url": "https://www.anchorterminal.com/compare/boat-vs-docker-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-e2b.json",
        "title": "boat vs E2B",
        "url": "https://www.anchorterminal.com/compare/boat-vs-e2b"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-freestyle.json",
        "title": "boat vs Freestyle",
        "url": "https://www.anchorterminal.com/compare/boat-vs-freestyle"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-instavm.json",
        "title": "boat vs InstaVM",
        "url": "https://www.anchorterminal.com/compare/boat-vs-instavm"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-maritime.json",
        "title": "boat vs Maritime",
        "url": "https://www.anchorterminal.com/compare/boat-vs-maritime"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-microsoft-execution-containers.json",
        "title": "boat vs Microsoft Execution Containers",
        "url": "https://www.anchorterminal.com/compare/boat-vs-microsoft-execution-containers"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-modal-sandboxes.json",
        "title": "boat vs Modal Sandboxes",
        "url": "https://www.anchorterminal.com/compare/boat-vs-modal-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-morph-cloud.json",
        "title": "boat vs Morph Cloud",
        "url": "https://www.anchorterminal.com/compare/boat-vs-morph-cloud"
      },
      {
        "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/boat-vs-perplexity-space.json",
        "title": "boat vs SPACE",
        "url": "https://www.anchorterminal.com/compare/boat-vs-perplexity-space"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-runloop.json",
        "title": "boat vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/boat-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-sandbox0.json",
        "title": "boat vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/boat-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-sprites.json",
        "title": "boat vs Sprites",
        "url": "https://www.anchorterminal.com/compare/boat-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-together-code-sandbox.json",
        "title": "boat vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/boat-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/boat-vs-vercel-sandbox.json",
        "title": "boat vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/boat-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/celesto-vs-render-sandboxes.json",
        "title": "Celesto (formerly SmolVM) vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/celesto-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-render-sandboxes.json",
        "title": "Cloudflare Sandbox SDK vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/daytona-vs-render-sandboxes.json",
        "title": "Daytona vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/daytona-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-render-sandboxes.json",
        "title": "Deno Sandbox vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-render-sandboxes"
      },
      {
        "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/docker-sandboxes-vs-render-sandboxes.json",
        "title": "Docker Sandboxes vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/docker-sandboxes-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/e2b-vs-render-sandboxes.json",
        "title": "E2B vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/e2b-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/freestyle-vs-render-sandboxes.json",
        "title": "Freestyle vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/freestyle-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/instavm-vs-render-sandboxes.json",
        "title": "InstaVM vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/instavm-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/maritime-vs-render-sandboxes.json",
        "title": "Maritime vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/maritime-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-render-sandboxes.json",
        "title": "Microsoft Execution Containers vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-render-sandboxes.json",
        "title": "Modal Sandboxes vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/morph-cloud-vs-render-sandboxes.json",
        "title": "Morph Cloud vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-render-sandboxes"
      },
      {
        "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/perplexity-space-vs-render-sandboxes.json",
        "title": "SPACE vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/perplexity-space-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/render-sandboxes-vs-runloop.json",
        "title": "Render Sandboxes vs Runloop Devboxes",
        "url": "https://www.anchorterminal.com/compare/render-sandboxes-vs-runloop"
      },
      {
        "json": "https://www.anchorterminal.com/compare/render-sandboxes-vs-sandbox0.json",
        "title": "Render Sandboxes vs Sandbox0",
        "url": "https://www.anchorterminal.com/compare/render-sandboxes-vs-sandbox0"
      },
      {
        "json": "https://www.anchorterminal.com/compare/render-sandboxes-vs-sprites.json",
        "title": "Render Sandboxes vs Sprites",
        "url": "https://www.anchorterminal.com/compare/render-sandboxes-vs-sprites"
      },
      {
        "json": "https://www.anchorterminal.com/compare/render-sandboxes-vs-together-code-sandbox.json",
        "title": "Render Sandboxes vs Together Code Sandbox",
        "url": "https://www.anchorterminal.com/compare/render-sandboxes-vs-together-code-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/render-sandboxes-vs-vercel-sandbox.json",
        "title": "Render Sandboxes vs Vercel Sandbox",
        "url": "https://www.anchorterminal.com/compare/render-sandboxes-vs-vercel-sandbox"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-boat.json",
        "title": "Agent 37 Cloud vs boat",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-boat"
      },
      {
        "json": "https://www.anchorterminal.com/compare/agent37-vs-render-sandboxes.json",
        "title": "Agent 37 Cloud vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/agent37-vs-render-sandboxes"
      },
      {
        "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-render-sandboxes.json",
        "title": "DeltaBox Lite vs Render Sandboxes",
        "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-render-sandboxes"
      }
    ],
    "panel": null,
    "scores": [
      {
        "boat": 60,
        "by": 8,
        "edge": "render-sandboxes",
        "key": "reliability",
        "name": "Reliability",
        "render-sandboxes": 68,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "boat": 90,
        "by": 11,
        "edge": "boat",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "render-sandboxes": 79,
        "weight": 13
      },
      {
        "boat": 93,
        "by": 20,
        "edge": "boat",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "render-sandboxes": 73,
        "weight": 13
      },
      {
        "boat": 67,
        "by": 4,
        "edge": "boat",
        "key": "security",
        "name": "Security \u0026 auth",
        "render-sandboxes": 63,
        "weight": 14
      },
      {
        "boat": 45,
        "by": 15,
        "edge": "boat",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "render-sandboxes": 30,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "boat": 76,
        "by": 9,
        "edge": "render-sandboxes",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "render-sandboxes": 85,
        "weight": 7
      },
      {
        "boat": 69,
        "by": 11,
        "edge": "render-sandboxes",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "render-sandboxes": 80,
        "weight": 7
      }
    ],
    "summary": "boat scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 4 of 7 scored categories. Render Sandboxes leads on reliability, maintenance \u0026 community and transparency \u0026 trust. Both do code sandboxes.",
    "tasks": null,
    "tutorials": [],
    "verdicts": {
      "boat": "boat publishes an OpenAPI 3.1 contract with 123 operations, per-hour prices, scoped expiring keys and idempotent creates for full Ubuntu VMs in the EU. It has no security.txt, SLA or readable incident history, SOC 2 is in progress, and the trial needs a card.",
      "render-sandboxes": "Render Sandboxes has per-operation rate limits, per-second prices and typed SDKs in three languages, with sandboxes that suspend when idle and resume from snapshots. It is a public beta in one region, with no public REST API, no idempotency on create and API keys that reach every workspace."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/boat-vs-render-sandboxes",
    "json": "https://www.anchorterminal.com/compare/boat-vs-render-sandboxes.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/boat-vs-render-sandboxes.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/compare/boat-vs-render-sandboxes.min.md"
  },
  "markdown": "boat scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 4 of 7 scored categories. Render Sandboxes leads on reliability, maintenance \u0026 community and transparency \u0026 trust. Both do code sandboxes.\n\n- boat: grade BB, 71.8/100, rank #255 of 1557. Markdown https://www.anchorterminal.com/tools/boat.md · JSON https://www.anchorterminal.com/api/v1/tools/boat.json\n- Render Sandboxes: grade B, 67.5/100, rank #441 of 1557. Markdown https://www.anchorterminal.com/tools/render-sandboxes.md · JSON https://www.anchorterminal.com/api/v1/tools/render-sandboxes.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### boat (BB)\n\nGood for: Long-lived, full Ubuntu VMs with Docker, a desktop and Chrome for coding agents, evals and products that give each user a sandbox, hosted in the EU.\n\nAhead on:\n- Schema \u0026 documentation, 90 against 79\n- Agent ergonomics, 93 against 73\n- Payments \u0026 pricing, 45 against 30\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n\nWatch for: No security.txt or bug bounty, and SOC 2 is in progress\n\n### Render Sandboxes (B)\n\nGood for: Teams already on Render that want agent sandboxes beside their services, or anyone who needs long-running sandboxes with idle suspension and process snapshots.\n\nAhead on:\n- Reliability, 68 against 60\n- Maintenance \u0026 community, 85 against 76\n- Transparency \u0026 trust, 80 against 69\n\nWatch for: Public beta since 4 November 2026, with one region (Oregon) and no SLA outside Enterprise\n\n\n## Why the edge\n\n### Agent ergonomics: boat +20\n\n- boat (93): Lists take `limit` from 1 to 200, commands can stream or detach, and a file read above 5 MiB returns `413` with a pointer to a signed download URL (20). Cursor pagination with `hasMore` and filters by name, name prefix, label and state (20). A stable error envelope with `code`, `message`, `details` and `requestId`, and a per-status table of what to do (20). `Idempotency-Key` on create and fork, kept 24 hours, with `409 idempotency_in_progress` and `409 idempotency_key_reused`, and per-code guidance on whether a command may have run (18). `ttlSeconds` defaults to one hour, the body of a create can be empty, and SDKs exist in Python and TypeScript beside the CLI with `--json` on every command (15). 20+20+20+18+15 = 93.\n- Render Sandboxes (73): Downloads take `maxSizeBytes` (256 MiB default since 1.8.0), exec streams output as events, and lists take a limit (15). `list` filters by status and name with cursor pagination, and snapshots and images list by name and status (18). Typed errors for each known API code since 1.9.0, such as `SandboxGroupSuspendedError` and `SandboxEndedError` with the sandbox's status, and 429 for both rate and concurrency caps. A nonzero exit code does not raise, which the docs state (17). No idempotency key for creating sandboxes or snapshots. The CLI previews stop and delete without `--confirm` (8 of 20). Sensible defaults (`1c-2g`, the default group) with few required parameters, SDKs in TypeScript, Python and Go plus the CLI (15). 15+18+17+8+15 = 73.\n\n### Payments \u0026 pricing: boat +15\n\n- boat (45): No x402, MPP or L402 (0). Per-hour prices for each size published without login, from $0.018 an hour for `small` to $0.20 for `xlarge`, with overage and start prices (30). The 7-day trial (25 compute hours) needs a card in Stripe Checkout (0). An agent can register itself through the auth.md agent registration protocol or AgentID, but a person has to claim the agent or verify the AgentMail organisation and enter a card before a sandbox can start (15 of 30). 0+30+0+15 = 45.\n- Render Sandboxes (30): No x402, MPP or L402 (0). Per-unit prices published without login, $0.12 per CPU-hour used and $0.019 per GB-hour of memory, also given per minute and per second (30). No free sandbox allowance was found. Hobby workspaces cost $0 but sandbox compute is billed from the first second, and whether a payment method is needed first was not stated (0). A person signs up and creates the API key in the dashboard (0). 0+30+0+0 = 30.\n\n### Schema \u0026 documentation: boat +11\n\n- boat (90): A public OpenAPI 3.1 file, docs.boat.dev/openapi/boat-v1.yaml, with 123 operations, each with an operationId and a summary (25). llms.txt indexing every page and a Markdown copy of each (10). The API overview and guides say when to create, resume or fork, when to run a command detached, when to use a saved snapshot, and what each sandbox state allows (18). 86 enums and required fields in the OpenAPI file, and list calls reject unknown query parameters with `400 invalid_query` (14). curl, Python and TypeScript examples, a table of error codes by status with what to do, and a retryable flag on 502s (15). Paths versioned under `/v1`, but no changelog was found (8 of 15). 25+10+18+14+15+8 = 90.\n- Render Sandboxes (79): No public REST API or OpenAPI document for sandboxes, and the SDK README lists the REST API as \"Soon\". The SDKs are typed and generated from Render's API schema, and the TypeScript and Python references document every method, which we count as 15 of 25 for an SDK, the reading modal-sandboxes was given (15). render.com/llms.txt, a Markdown twin of every page and a single sandboxes bundle at /docs/sandboxes/all (10). The guides say when to use idle suspension, runtime timeouts, filesystem or process snapshots and sandbox groups, and what a deleted snapshot breaks (15). Typed SDK inputs with a plan enum, a network policy type and documented bounds such as a 64-character snapshot name (12). Examples in CLI, TypeScript and both Python styles on every page, and 18 named error types with when each is thrown. No list of API error codes (14). Semver SDK changelog with dates and Render's product changelog. The 1.9.0 breaking change came in a minor version, called out in the changelog (13). 15+10+15+12+14+13 = 79.\n\n### Transparency \u0026 trust: Render Sandboxes +11\n\n- boat (69): Closed service under terms of 12 October 2026 from Dedale AI, Corp., a Delaware corporation (15). The terms, privacy policy and docs agree on retention. A stopped sandbox's disk is kept at least 14 days, saved snapshots have no scheduled expiry, and zero data retention can be turned on. The terms say the cleanup job does not yet delete in production. A DPA is available on request (25 of 30). The Box to boat rename on 15 September 2026 put `Deprecation` and `Sunset` headers on old surfaces with a dated sunset of 31 October 2026, and deprecated endpoints are marked in the reference (18 of 20). Infrastructure hosts (OVH, Hetzner) and other processors are named, sandboxes run in Germany, Finland and France, and snapshot copies can be stored outside the EU (16 of 20). 15+25+18+16 = 74.\n- Render Sandboxes (80): The service is closed, under terms last modified 10 July 2026. The SDKs are open source (MIT and Apache-2.0) (20 of 30). A privacy policy and DPA, plus stated lifetimes for sandbox data. The filesystem is deleted on termination, suspended sandboxes stay resumable 30 days, and snapshots expire 30 days after last use unless the TTL is changed (20 of 30). The docs warn that APIs, defaults and limits might change during the beta, and the SDK changelog marks breaking changes with migration steps, but no deprecation policy or notice period was found (8 of 20). Eight sub-processors with countries on render.com/security, and the region (Oregon) is stated (15 of 20). 20+20+8+15 = 63.\n\n### Maintenance \u0026 community: Render Sandboxes +9\n\n- boat (76): Python SDK `boat-sdk` 1.13.0 on 28 October 2026 (30). 25 SDK releases from 1.0.0 on 16 September to 1.13.0 on 28 October 2026 on PyPI (20). Closed service with a Discord, a support page and a blog, but no public changelog or tracker (8 of 25). Official SDKs in Python and TypeScript (`@boatdev/sdk` 1.13.0) generated from the OpenAPI file (15). No public source repository or CI for the SDKs was found (3 of 10). 30+20+8+15+3 = 76.\n- Render Sandboxes (85): SDK 1.9.0 on 16 November 2026 (30). Eight SDK releases in the 90 days, from 1.1.0 on 10 September to 1.9.0, five of them since 17 October (20). 118 commits since 18 October from Render staff and release bots, the last on 18 November. Two open pull requests. The issue list draws in a script and could not be read, so responsiveness is not established (10 of 25). Official SDKs in TypeScript, Python and Go, current with the docs (15). CI for both languages with pinned actions, Dependabot configured. The result of the latest run was not seen (10). 30+20+10+15+10 = 85.\n\n### Reliability: Render Sandboxes +8\n\n- boat (60): Hosted reading. A status page at status.ascii.dev, linked from the docs, draws its system status and metrics in a script our reader could not run, so component history was not confirmed (15 of 20). No readable incident history (5). Limits published per plan with numbers, from 12 starts a minute and 100 sandboxes at once on the $20 plan to 90 a minute and 2,000 on the $2,000 plan, plus 10,000 requests a minute per IP (15). Every 429 sends `Retry-After`, `RateLimit` headers carry the remaining starts, 503s carry `retryAfterSeconds`, the docs give a backoff example, and create and fork take an `Idempotency-Key` (15). No SLA found. The docs cite a measured 99.95% sandbox uptime, and the terms disclaim uptime warranties (0). The API is v1 with no beta label (10). 15+5+15+15+0+10 = 60.\n- Render Sandboxes (68): Scored on the hosted checklist, since sandboxes run on Render's infrastructure and the SDKs and CLI are clients of its API, the reading given to modal-sandboxes and vercel-sandbox. status.render.com is a Statuspage with incident history, though it has no Sandboxes component (20). Its history feed, read on 18 November 2026, has no incident naming sandboxes. Since the 4 November beta it lists API performance issues on 11 November for 18 minutes (13:17 to 13:35 UTC, dashboard and API requests) and a maintenance window announced on 10 November, with the REST API down for up to 30 minutes on 18 November. Earlier in the 90 days, builds and deploys did not start in any region on 14 October. Minor for this surface (20). Rate limits per operation with numbers, such as 100 creates and 1,000 execs a minute per user, and per-group concurrency caps (15). The docs say limits return 429, and the API schema in the SDK source documents `Retry-After` and `RateLimit-*` headers, but there is no backoff guidance in the sandbox docs and no idempotency key on create (8 of 15). The pricing page lists contractual uptime SLAs for Enterprise without publishing their terms (5 of 10). Public beta, not generally available (0). 20+20+15+8+5+0 = 68.\n\n## Score by category\n\n| Category | Weight | boat | Render Sandboxes | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 60 | 68 | Render Sandboxes +8 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% | 90 | 79 | boat +11 |\n| Agent ergonomics | 13% | 93 | 73 | boat +20 |\n| Security \u0026 auth | 14% | 67 | 63 | boat +4 |\n| Payments \u0026 pricing | 10% | 45 | 30 | boat +15 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% | 76 | 85 | Render Sandboxes +9 |\n| Transparency \u0026 trust | 7% | 69 | 80 | Render Sandboxes +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **71.8 · BB** | **67.5 · B** | |\n\n## Facts side by side\n\n| Fact | boat | Render Sandboxes |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | Dedale AI, Corp. | Render Services, Inc. |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | API key |\n| Pricing | Pay per use | Pay per use |\n| x402 | no | no |\n| Licence | Proprietary service under boat's terms. The TypeScript SDK `@boatdev/sdk` is MIT | The service is proprietary under Render's terms. The SDK is MIT (TypeScript `@renderinc/sdk`) and Apache-2.0 (Python `render`) |\n| Read-only variant documented | yes | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-28 | 2026-11-16 |\n| Terms last updated | no date given | 2026-07-10 |\n| Privacy policy last updated | no date given | 2026-07-10 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | yes |\n| Arbitration or class-action waiver | yes | yes |\n| Popularity | none | 27 stars |\n\n## Verdicts\n\n**boat.** boat publishes an OpenAPI 3.1 contract with 123 operations, per-hour prices, scoped expiring keys and idempotent creates for full Ubuntu VMs in the EU. It has no security.txt, SLA or readable incident history, SOC 2 is in progress, and the trial needs a card.\n\n**Render Sandboxes.** Render Sandboxes has per-operation rate limits, per-second prices and typed SDKs in three languages, with sandboxes that suspend when idle and resume from snapshots. It is a public beta in one region, with no public REST API, no idempotency on create and API keys that reach every workspace.\n\n## Before you call either\n\n### boat\n\n1. Send an `Idempotency-Key` on every create and fork, and resend the same key and body after a timeout or 5xx\n2. Check `GET /limits` before a batch of starts. A retry loop does not help once the hour or day start limit is full\n3. Set `detached: true` for any command that may run past 30 seconds, then attach to its stream\n4. If a 502 `sandbox_direct_failed` has `retryable` false, check the command's effect before you run it again\n5. Use a `read-only` or per-sandbox key with a short TTL for anything that does not create sandboxes\n\n### Render Sandboxes\n\n1. Set `timeoutSeconds` when you create a sandbox. A disabled timeout keeps the sandbox, and its billing, running until you terminate it\n2. Pass `networkPolicy` with an allowlist or deny-all at creation, since the default allows outbound traffic to any destination\n3. Check the exit event's `exit_code` after `exec`. A nonzero exit code does not raise an error in the SDK\n4. If create returns 429, check whether the group is at its concurrency cap before you retry. Rate and concurrency limits share the same code\n5. Use `ttlSeconds` on snapshots with SDK 1.9.0 or later. The `expiresAt` option was removed in 1.9.0\n\n## Questions\n\n### Which is better for AI agents, boat or Render Sandboxes?\n\nboat scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 4 of 7 scored categories. Render Sandboxes leads on reliability, maintenance \u0026 community and transparency \u0026 trust.\n\n### Can an agent call boat and Render Sandboxes without installing anything?\n\nNo hosted endpoint is listed for boat. No hosted endpoint is listed for Render Sandboxes.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/boat-vs-render-sandboxes.json, and with the fewest tokens: https://www.anchorterminal.com/compare/boat-vs-render-sandboxes.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"boat\", \"b\": \"render-sandboxes\"}`. From a terminal: `anchor compare boat render-sandboxes`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/boat.json and https://www.anchorterminal.com/api/v1/tools/render-sandboxes.json\n\n## Other comparisons with boat or Render Sandboxes\n\n- [Amazon Bedrock AgentCore Code Interpreter vs boat](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-boat.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Render Sandboxes](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-render-sandboxes.md)\n- [Blaxel Sandboxes vs boat](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-boat.md)\n- [Blaxel Sandboxes vs Render Sandboxes](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-render-sandboxes.md)\n- [boat vs Celesto (formerly SmolVM)](https://www.anchorterminal.com/compare/boat-vs-celesto.md)\n- [boat vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/boat-vs-cloudflare-sandbox-sdk.md)\n- [boat vs Daytona](https://www.anchorterminal.com/compare/boat-vs-daytona.md)\n- [boat vs DeltaBox Lite](https://www.anchorterminal.com/compare/boat-vs-deltabox-lite.md)\n- [boat vs Deno Sandbox](https://www.anchorterminal.com/compare/boat-vs-deno-sandbox.md)\n- [boat vs DigitalOcean Managed Agents](https://www.anchorterminal.com/compare/boat-vs-digitalocean-managed-agents.md)\n- [boat vs Docker Sandboxes](https://www.anchorterminal.com/compare/boat-vs-docker-sandboxes.md)\n- [boat vs E2B](https://www.anchorterminal.com/compare/boat-vs-e2b.md)\n- [boat vs Freestyle](https://www.anchorterminal.com/compare/boat-vs-freestyle.md)\n- [boat vs InstaVM](https://www.anchorterminal.com/compare/boat-vs-instavm.md)\n- [boat vs Maritime](https://www.anchorterminal.com/compare/boat-vs-maritime.md)\n- [boat vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/boat-vs-microsoft-execution-containers.md)\n- [boat vs Modal Sandboxes](https://www.anchorterminal.com/compare/boat-vs-modal-sandboxes.md)\n- [boat vs Morph Cloud](https://www.anchorterminal.com/compare/boat-vs-morph-cloud.md)\n- [boat vs Offscreen](https://www.anchorterminal.com/compare/boat-vs-offscreen.md)\n- [boat vs SPACE](https://www.anchorterminal.com/compare/boat-vs-perplexity-space.md)\n- [boat vs Runloop Devboxes](https://www.anchorterminal.com/compare/boat-vs-runloop.md)\n- [boat vs Sandbox0](https://www.anchorterminal.com/compare/boat-vs-sandbox0.md)\n- [boat vs Sprites](https://www.anchorterminal.com/compare/boat-vs-sprites.md)\n- [boat vs Together Code Sandbox](https://www.anchorterminal.com/compare/boat-vs-together-code-sandbox.md)\n- [boat vs Vercel Sandbox](https://www.anchorterminal.com/compare/boat-vs-vercel-sandbox.md)\n- [Celesto (formerly SmolVM) vs Render Sandboxes](https://www.anchorterminal.com/compare/celesto-vs-render-sandboxes.md)\n- [Cloudflare Sandbox SDK vs Render Sandboxes](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-render-sandboxes.md)\n- [Daytona vs Render Sandboxes](https://www.anchorterminal.com/compare/daytona-vs-render-sandboxes.md)\n- [Deno Sandbox vs Render Sandboxes](https://www.anchorterminal.com/compare/deno-sandbox-vs-render-sandboxes.md)\n- [DigitalOcean Managed Agents vs Render Sandboxes](https://www.anchorterminal.com/compare/digitalocean-managed-agents-vs-render-sandboxes.md)\n- [Docker Sandboxes vs Render Sandboxes](https://www.anchorterminal.com/compare/docker-sandboxes-vs-render-sandboxes.md)\n- [E2B vs Render Sandboxes](https://www.anchorterminal.com/compare/e2b-vs-render-sandboxes.md)\n- [Freestyle vs Render Sandboxes](https://www.anchorterminal.com/compare/freestyle-vs-render-sandboxes.md)\n- [InstaVM vs Render Sandboxes](https://www.anchorterminal.com/compare/instavm-vs-render-sandboxes.md)\n- [Maritime vs Render Sandboxes](https://www.anchorterminal.com/compare/maritime-vs-render-sandboxes.md)\n- [Microsoft Execution Containers vs Render Sandboxes](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-render-sandboxes.md)\n- [Modal Sandboxes vs Render Sandboxes](https://www.anchorterminal.com/compare/modal-sandboxes-vs-render-sandboxes.md)\n- [Morph Cloud vs Render Sandboxes](https://www.anchorterminal.com/compare/morph-cloud-vs-render-sandboxes.md)\n- [Offscreen vs Render Sandboxes](https://www.anchorterminal.com/compare/offscreen-vs-render-sandboxes.md)\n- [SPACE vs Render Sandboxes](https://www.anchorterminal.com/compare/perplexity-space-vs-render-sandboxes.md)\n- [Render Sandboxes vs Runloop Devboxes](https://www.anchorterminal.com/compare/render-sandboxes-vs-runloop.md)\n- [Render Sandboxes vs Sandbox0](https://www.anchorterminal.com/compare/render-sandboxes-vs-sandbox0.md)\n- [Render Sandboxes vs Sprites](https://www.anchorterminal.com/compare/render-sandboxes-vs-sprites.md)\n- [Render Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/render-sandboxes-vs-together-code-sandbox.md)\n- [Render Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/render-sandboxes-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs boat](https://www.anchorterminal.com/compare/agent37-vs-boat.md)\n- [Agent 37 Cloud vs Render Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-render-sandboxes.md)\n- [DeltaBox Lite vs Render Sandboxes](https://www.anchorterminal.com/compare/deltabox-lite-vs-render-sandboxes.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": "boat vs Render Sandboxes",
        "url": ""
      }
    ],
    "description": "boat scores 71.8 (BB) to Render Sandboxes's 67.5 (B) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "boat BB 71.8",
      "Render Sandboxes B 67.5",
      "scores"
    ],
    "h1": "boat vs Render Sandboxes",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/compare/boat-vs-render-sandboxes",
    "published": "2026-10-01",
    "section": "tools",
    "title": "boat vs Render Sandboxes for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-11-18",
    "url": "https://www.anchorterminal.com/compare/boat-vs-render-sandboxes"
  },
  "tokens": {
    "markdown": 5300,
    "slim": 1030
  },
  "version": 1
}
