{
  "fixes": {
    "slug": "daytona",
    "name": "Daytona",
    "listing": "https://www.anchorterminal.com/tools/daytona",
    "markdown": "# Fix list: Daytona\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/daytona, the October 2026 research run, assessed 1 October 2026. Grade B, 64.4 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on Daytona: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Reliability, 60 out of 100, up to 8 more on the total\n\nWhy it scored 60: Status page at status.app.daytona.io with component history (20). Two outages over an hour in the 90 days, both Windows runners marked down for sandbox creation, 3 hours 50 minutes on 31 July and 1 hour 40 minutes on 1 August 2026. There was also a 17.5-hour regional degradation of sandbox creation on 11 August and a 2-hour degradation of sandbox listing on 1 October. Two majors sit between the rubric's one-major and several-majors bands, so 5 (5). Rate limits published per tier, 10,000 to 50,000 general requests and 300 to 600 sandbox creations a minute (15). 429s carry `Retry-After-{throttler}` and `X-RateLimit-*` headers, and the docs advise exponential backoff. No idempotency keys found (10). No SLA found (0). GA (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 2. Agent ergonomics, 55 out of 100, up to 7.3 more on the total\n\nWhy it scored 55: List and toolbox calls return whole objects or files, with no field selection found (15). Labels and list calls exist, but we didn't confirm documented filters or page sizes this run (10). JSON errors with `statusCode`, `message` and `error`, plus rate-limit headers (15). No idempotency keys or safe-retry guidance for creates found (0). SDKs in Python, TypeScript, Ruby, Go and Java, and a create call works with an empty body, though the 15-minute auto-stop default can stop a sandbox mid-task (15). We scored the API, not the local MCP server.\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 3. Security \u0026 auth, 63 out of 100, up to 6.5 more on the total\n\nWhy it scored 63: API keys with per-action scopes (`write:sandboxes` separate from `delete:sandboxes`, plus snapshot, volume, audit, secret and billing scopes), an expiry date and immediate revocation. The docs add that any valid key in the organisation can reach a running sandbox whatever its scopes, so 27 of 30 (27). Container sandboxes get their own namespaces and resource limits on a shared kernel, while Linux VM and Windows classes get their own kernel (6). Tier 1 and 2 organisations get restricted network access that can't be changed per sandbox, and full internet with per-sandbox allow lists starts at Tier 3, a $500 top-up (5). We found nothing on keeping credentials out of the sandbox or on running untrusted code (5). Audit logs behind their own key scope, log streaming and webhooks (15). A SECURITY.md in daytona/clients. No security.txt, and no SOC 2 report, bug bounty or public advisories found (5).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 4. Payments \u0026 pricing, 50 out of 100, up to 6.3 more on the total\n\nWhy it scored 50: No x402, MPP or L402 (0). Per-second prices published per vCPU, GiB of memory, GiB of storage and GPU (20). $200 of compute without a card (20). Stripe Projects lists Daytona, so an agent can create the account through the operator's Stripe login (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 5. Transparency \u0026 trust, 58 out of 100, up to 3.7 more on the total\n\nMade of editorial 40, provenance 75.\n\nWhy it scored 58: SDKs and API clients are Apache-2.0 and the CLI is AGPL-3.0, but the platform code went private in June 2026 (20). A privacy policy and terms dated 22 August 2025 exist, but we found no retention statement for sandbox data in the docs (5). Breaking changes are flagged in release notes, with no deprecation policy or dated notices found (5). Shared regions in the US and EU are named and custom regions run on your own machines. No subprocessor list found (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Domain age: daytona.io, no registry record we could read (0 of 15)\n- security.txt: not found (0 of 10)\n\n## 6. Schema \u0026 documentation, 87 out of 100, up to 2.1 more on the total\n\nWhy it scored 87: Three public OpenAPI files, for the main API, the in-sandbox toolbox API and analytics (25). llms.txt and Markdown pages (10). The docs say what each sandbox class is for and what only VM classes can do (15). Typed fields from the spec, with integer types tightened in 0.215.0 (12). The 429 error body is documented and SDK pages carry examples, but we found no error-code reference (10). A public changelog and GitHub release notes that flag breaking changes (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 7. Maintenance \u0026 community, 80 out of 100, up to 1.8 more on the total\n\nWhy it scored 80: v0.220.0 on 2026-09-29 (30). Ten releases of daytona/clients in September 2026 alone (20). Core development went private in June 2026, and the old public repository keeps 311 open issues with a notice that it gets no further updates. The new clients repository has one or no open issues. Public changelog and releases, scored on the closed-service scale (10). Current official SDKs in five languages (15). No CI status visible for the clients repository (5).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## What we couldn't check\n\nWhat we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.\n\n- Which sandbox class a create call with an empty body gets. The isolation page doesn't name a default.\n- Whether Daytona holds a SOC 2 report or runs a bug bounty. We found neither in the docs.\n- How sandbox data is retained after deletion, and which subprocessors handle it.\n\n## Weaknesses\n\n- The container class shares the host kernel. Only the VM classes get their own\n- Full internet access and per-sandbox allow lists need Tier 3\n- Platform code went private in June 2026, and the old repository's 311 open issues won't be answered\n- Two Windows runner outages over an hour in July and August 2026\n- No security.txt, SOC 2 report or bug bounty found\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Pick a Linux VM class for untrusted code or when memory must survive a pause. Container sandboxes stop and archive instead\n- Set autoStopInterval yourself. The 15-minute idle default can stop a sandbox while the agent is still thinking\n- Give the agent a key without `delete:sandboxes` if it shouldn't destroy work\n- Read `Retry-After-{throttler}` on a 429 before retrying sandbox creation\n- Check the organisation's tier before relying on outbound calls from inside the sandbox\n\n## What the review panel asked for\n\n- Publish an SLA\n- Add idempotency keys on create\n- scopes enforced inside sandboxes\n- VM isolation as default\n\n## When it's done\n\nSend what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `\"kind\": \"dispute\"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.\n",
    "grade": "B",
    "score": 64.4,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 60,
        "maxGain": 8,
        "reason": "Status page at status.app.daytona.io with component history (20). Two outages over an hour in the 90 days, both Windows runners marked down for sandbox creation, 3 hours 50 minutes on 31 July and 1 hour 40 minutes on 1 August 2026. There was also a 17.5-hour regional degradation of sandbox creation on 11 August and a 2-hour degradation of sandbox listing on 1 October. Two majors sit between the rubric's one-major and several-majors bands, so 5 (5). Rate limits published per tier, 10,000 to 50,000 general requests and 300 to 600 sandbox creations a minute (15). 429s carry `Retry-After-{throttler}` and `X-RateLimit-*` headers, and the docs advise exponential backoff. No idempotency keys found (10). No SLA found (0). GA (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 55,
        "maxGain": 7.3,
        "reason": "List and toolbox calls return whole objects or files, with no field selection found (15). Labels and list calls exist, but we didn't confirm documented filters or page sizes this run (10). JSON errors with `statusCode`, `message` and `error`, plus rate-limit headers (15). No idempotency keys or safe-retry guidance for creates found (0). SDKs in Python, TypeScript, Ruby, Go and Java, and a create call works with an empty body, though the 15-minute auto-stop default can stop a sandbox mid-task (15). We scored the API, not the local MCP server.",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 63,
        "maxGain": 6.5,
        "reason": "API keys with per-action scopes (`write:sandboxes` separate from `delete:sandboxes`, plus snapshot, volume, audit, secret and billing scopes), an expiry date and immediate revocation. The docs add that any valid key in the organisation can reach a running sandbox whatever its scopes, so 27 of 30 (27). Container sandboxes get their own namespaces and resource limits on a shared kernel, while Linux VM and Windows classes get their own kernel (6). Tier 1 and 2 organisations get restricted network access that can't be changed per sandbox, and full internet with per-sandbox allow lists starts at Tier 3, a $500 top-up (5). We found nothing on keeping credentials out of the sandbox or on running untrusted code (5). Audit logs behind their own key scope, log streaming and webhooks (15). A SECURITY.md in daytona/clients. No security.txt, and no SOC 2 report, bug bounty or public advisories found (5).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 50,
        "maxGain": 6.3,
        "reason": "No x402, MPP or L402 (0). Per-second prices published per vCPU, GiB of memory, GiB of storage and GPU (20). $200 of compute without a card (20). Stripe Projects lists Daytona, so an agent can create the account through the operator's Stripe login (10).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 58,
        "maxGain": 3.7,
        "reason": "SDKs and API clients are Apache-2.0 and the CLI is AGPL-3.0, but the platform code went private in June 2026 (20). A privacy policy and terms dated 22 August 2025 exist, but we found no retention statement for sandbox data in the docs (5). Breaking changes are flagged in release notes, with no deprecation policy or dated notices found (5). Shared regions in the US and EU are named and custom regions run on your own machines. No subprocessor list found (10).",
        "blend": "editorial 40, provenance 75",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 87,
        "maxGain": 2.1,
        "reason": "Three public OpenAPI files, for the main API, the in-sandbox toolbox API and analytics (25). llms.txt and Markdown pages (10). The docs say what each sandbox class is for and what only VM classes can do (15). Typed fields from the spec, with integer types tightened in 0.215.0 (12). The 429 error body is documented and SDK pages carry examples, but we found no error-code reference (10). A public changelog and GitHub release notes that flag breaking changes (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 80,
        "maxGain": 1.8,
        "reason": "v0.220.0 on 2026-09-29 (30). Ten releases of daytona/clients in September 2026 alone (20). Core development went private in June 2026, and the old public repository keeps 311 open issues with a notice that it gets no further updates. The new clients repository has one or no open issues. Public changelog and releases, scored on the closed-service scale (10). Current official SDKs in five languages (15). No CI status visible for the clients repository (5).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Domain age",
        "value": "daytona.io, no registry record we could read",
        "points": 0,
        "max": 15
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Which sandbox class a create call with an empty body gets. The isolation page doesn't name a default.",
      "Whether Daytona holds a SOC 2 report or runs a bug bounty. We found neither in the docs.",
      "How sandbox data is retained after deletion, and which subprocessors handle it."
    ],
    "weaknesses": [
      "The container class shares the host kernel. Only the VM classes get their own",
      "Full internet access and per-sandbox allow lists need Tier 3",
      "Platform code went private in June 2026, and the old repository's 311 open issues won't be answered",
      "Two Windows runner outages over an hour in July and August 2026",
      "No security.txt, SOC 2 report or bug bounty found"
    ],
    "agentNotes": [
      "Pick a Linux VM class for untrusted code or when memory must survive a pause. Container sandboxes stop and archive instead",
      "Set autoStopInterval yourself. The 15-minute idle default can stop a sandbox while the agent is still thinking",
      "Give the agent a key without `delete:sandboxes` if it shouldn't destroy work",
      "Read `Retry-After-{throttler}` on a 429 before retrying sandbox creation",
      "Check the organisation's tier before relying on outbound calls from inside the sandbox"
    ],
    "requests": [
      {
        "text": "Publish an SLA",
        "reviews": 1
      },
      {
        "text": "Add idempotency keys on create",
        "reviews": 1
      },
      {
        "text": "scopes enforced inside sandboxes",
        "reviews": 1
      },
      {
        "text": "VM isolation as default",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}