Unstoppable

# Fix list: Unstoppable

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/unstoppable, the October 2026 research run, assessed 27 October 2026. Grade F, 34.9 out of 100.

This 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.

For a coding agent working on Unstoppable: 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.

## 1. Agent ergonomics, 5 out of 100, up to 15.4 more on the total

Why it scored 5: These lines measure an interface an agent calls, and Unstoppable has none, so context cost, output controls and retries score nothing. For the person, a usage limit shows choices to wait for the reset or continue on credits (2 of 20). Guest use with no account, a first-run page that imports Claude and Codex projects, and few required settings. No SDK (3 of 15). Total 5.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 2. Schema & documentation, 30 out of 100, up to 11.4 more on the total

Why it scored 30: Graded on the interface an outside agent can use, which is none. No API, OpenAPI file, MCP server or documented command (0). unstoppable.ai/llms.txt lists the product, help and policy pages in Markdown (10). Twenty-two dated help articles explain for a person what each part does and when to use it, such as Code and Work modes and approval modes (5 of 20). No typed inputs an agent could call (0). Step-by-step examples for people and named error states such as usage limit reached and update failed, with no error responses for an agent (3 of 15). Numbered versions and a public dated changelog, which lists only four releases from 20 to 23 October 2026 (12 of 15). Total 30.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 3. Security & auth, 36 out of 100, up to 11.2 more on the total

Why it scored 36: Harness reading of the framework checklist, as for the other harnesses. 30 for what leaves the machine by default, 20 for approvals and sandboxing, 15 for prompt-injection posture, 15 for audit and 20 for the security programme. Activity sharing is Off for every activity type by default and secrets are removed before upload, but the privacy policy also collects usage telemetry (feature use, session activity, token and spend metrics, diagnostics) with no opt-out stated, and updates download automatically by default (15 of 30). Ask and Accept edits modes with allow and deny rules by command, file write, MCP tool and network host, deny winning, and safety rules that block force-pushes and destructive deletes. Every kind of chat starts in Full access, which skips prompts and safety rules, and local agents have no documented sandbox. Cloud worktrees get their own sandbox (8 of 20). The in-app browser stops agents acting on private sign-in pages. No other guidance on untrusted content from web pages, MCP servers or connected tools (3 of 15). Cost and usage panels, a team feed with tool-use metadata, approval rules with their origin, and an Audit Trail experiment in Labs (8 of 15). Two-factor authentication for accounts. No security.txt on unstoppable.ai, the parent's security.txt expired on 22 January 2024, its bug bounty policy link returns 404, and no SOC 2 or ISO 27001 found (2 of 20). Total 36.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 4. Reliability, 45 out of 100, up to 11 more on the total

Why it scored 45: Read as local software, because the product is the desktop app the owner runs, as for the other harnesses. Signed downloads for macOS Apple Silicon, macOS Intel and Windows on the download page, version 1.15.0, plus iOS and Android apps in the stores, with the supported platforms stated. No package registry (20). Closed source with no public CI or test suite (0). No public issue tracker. Bugs go through in-app feedback, email and Discord, none of which shows a record we could read (0). Version numbers and a dated changelog, but only 1.12.0 to 1.15.0 are listed and breaking changes are not marked as such (10). Version 1.15.0 (15). The hosted parts (accounts, AI credits, cloud agents, Remote Control) have no status page. status.unstoppabledomains.com covers the domains business only.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 5. Payments & pricing, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). The app is published as free, but AI credit prices appear only after sign-in, and no pricing page exists (unstoppable.ai/pricing redirects to the home page). Plan prices of $19, $29 and $49 appear only in an 11 August 2026 blog post (10). Guest use with no account, and 10 free AI credits a day with no card (20). A person has to download and install the app, so no autonomous onboarding (0). Total 30.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 6. Maintenance & community, 58 out of 100, up to 3.7 more on the total

Why it scored 58: Read for a closed product. Version 1.15.0 on 23 October 2026, and iOS 1.1.9 on 27 October (30). Four desktop releases from 20 to 23 October and nine iOS updates since 11 August 2026 (20). A public changelog, a support email, in-app feedback and a Discord server, none tested for replies. Help articles were updated between 19 and 24 October (6 of 15). No SDK and no MCP registry entry (0). Windows updates check signatures per the 1.13.0 notes, with no build pipeline to inspect (2 of 10). Total 58.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 58 out of 100, up to 3.7 more on the total

Made of editorial 40, provenance 76.

Why it scored 58: Closed source under terms of 6 October 2026 that name Unstoppable Domains, Inc. and Delaware law. The terms forbid reverse engineering and building a competing product (15). The privacy policy of 8 October 2026 is written for this product. It states activity sharing levels, Off by default, secret removal and encryption, and configurable transcript retention. It gives no retention periods, names no subprocessors, and says usage telemetry may sync depending on settings, which the site's 'we don't collect your code or conversations' leaves open (16 of 30). No deprecation policy. The terms allow removing parts of the service without notice. The changelog dates one retirement (GPT 5.5 to GPT 6.1 Sol) (3 of 20). No subprocessors or data locations disclosed, and the telemetry the app sends has no documented opt-out (6 of 20). Total 40.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: unstoppable.ai, registered 2021-01-05 (5 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What 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.

- Not tagged as an agent interface. The 1.15.0 changelog says MCP tools can cancel or wait on cloud tasks and that ChatGPT and Claude show as verified clients when connected to an account, but no endpoint, tool list or docs for this were found. api.unstoppable.ai's OAuth metadata names Unstoppable Domains' domains MCP server (api.unstoppabledomains.com/mcp/v1, scopes such as domains:search and checkout), not this product. Tagged not-for-agents until a documented interface appears.
- `firstReleased` is 24 July 2026, iOS app 1.0 in the App Store's version history, which pairs with the desktop app. That is earlier than the 5 August 2026 launch post. The first desktop version's date was not found, because the changelog starts at 1.12.0.
- Pricing pages disagree. The home FAQ and help say every app feature is free when signed in with no subscription required. The 14 October Remote Control post says a plan may not include Remote Control, the governance page says its controls work with Unstoppable subscriptions, the terms mention paid subscriptions, and an 11 August post lists $19, $29 and $49 plans. Recorded, not deducted, because which is current could not be established.
- The lead said free with sign-in. The help says the desktop app can be used as a guest with no account, and the web app allows guest chat.
- Linux. The download page and help name macOS and Windows only, while the 1.13.0 and 1.15.0 notes mention a Linux download (Ubuntu 24.04 LTS), arm64 packages and a Linux command-line tool. Not listed as a platform.
- Vendor claims recorded, not checked. '#1 AI Workspace' titles in llms.txt, '6x code output' on the about page, and comparison tables that mark ChatGPT and Claude Cowork 'No' on several rows. One table publishes a note that partner terms were 'confirmed by the product owner on October 1, 2026'.
- Not our job. Unstoppable runs coding agents chosen by the person. It does not pick a tool for an agent's job the way letme does, and it is not a private personal data server like LocalGhost.
- Process note. status.unstoppabledomains.com/api/v2/components.json and incidents.json were fetched in the same command as that host's robots.txt, which disallows /api/. Nothing from them is used; the HTML status page was read instead.
- unchecked: the github.com/unstoppabledomains organisation, because GitHub was not reachable from our network, so whether any Unstoppable Code source, CLI or issue tracker is public was not established.
- unchecked: AI credit prices and the plan, if any, that gates Remote Control or team controls. Both are behind sign-in. Nothing was installed, signed in to or bought.

## Weaknesses

- No API, MCP server, SDK or documented CLI for an outside agent. A Linux command-line tool and MCP tools for cloud tasks appear only in changelog lines
- Every kind of chat starts in Full access, which skips approval prompts and the safety rules for risky commands, until the person changes the default
- The home page says every app feature is free when signed in, while a 14 October post says a plan may not include Remote Control and the governance page ties controls to subscriptions
- AI credit prices are shown only after sign-in, and no status page covers the accounts, cloud agents or Remote Control relay
- No security.txt on unstoppable.ai. The parent's security.txt expired on 22 January 2024 and its bug bounty policy link returns 404

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Don't plan to drive Unstoppable from another agent. It has no documented API, MCP server or CLI. Call Claude Code, Codex or Cursor directly and let the person use Unstoppable around them
- Inside Unstoppable, check the approval mode before acting. New chats start in Full access unless the person set Ask or Accept edits in Settings, Approvals
- When a Claude or Codex usage limit is reached, ask the person before choosing Use credits now or Always use credits, since both spend their AI credits
- Keep each task in its own worktree and let the person review the diff and press Create PR, rather than pushing to a shared branch

## When it's done

Send 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.