Freestyle

# Fix list: Freestyle

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/freestyle, the October 2026 research run, assessed 8 October 2026. Grade C, 58.5 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 Freestyle: 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. Reliability, 43 out of 100, up to 11.4 more on the total

Why it scored 43: Graded on the hosted lines. www.freestyle.sh/status is the vendor's own page with three components (Freestyle VMs, API, Dashboard), all operational, last updated 4 October 2026, with no incident list or component history (10 of 20). No readable history (5). Plan limits are published with numbers (10, 40 and 400 concurrent VMs, per-VM and total resource budgets), but no request rate limit for the API was found in the reviewed documentation (5 of 15). The OpenAPI file documents 429 `LIMIT_EXCEEDED` on VM creation and resize and marks which 409s are safe to retry, resumable uploads take retryable chunks, and a `x-freestyle-background-after-secs` header turns a long call into a polled request. No Retry-After or backoff guidance and no idempotency keys found (8 of 15). The pricing page lists a 99.99% SLA for Enterprise with no SLA document published (5 of 10). The API is served under `/v5` with no beta label (10).

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.

## 2. Security & auth, 53 out of 100, up to 8.2 more on the total

Why it scored 53: Account API keys are named, shown once, listed and revoked from the CLI, with no scopes or expiry found. Identity access tokens are separate, limited to granted VMs and named Linux users and to the exec and terminal routes, and revocable one by one (22 of 30). No documented option carries a secret in a URL query string. A new VM has no inbound or outbound network until firewall rules allow it, and identity tokens cannot create team resources. Deleting a VM takes one call with no confirmation step (14 of 20). Credential injection at the edge puts API keys, Postgres passwords and Git tokens on outbound requests without storing them in the VM, and forward auth keeps session cookies out of the guest (12 of 15). Audit logs are listed for Enterprise only, and the April 2026 changelog describes a logs dashboard (5 of 15). `/.well-known/security.txt` answers 404, and no disclosure policy, bug bounty, SOC 2 or ISO 27001 statement was found (0 of 20).

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.

## 3. Payments & pricing, 45 out of 100, up to 6.9 more on the total

Why it scored 45: No x402, MPP or L402 found in the docs, the OpenAPI file or the pricing page (0). Per-unit prices are public, $0.04032 a vCPU-hour, $0.0129 a GiB-hour of memory, $0.000086 a GiB-hour of storage and $0.02 a GB of data transfer (20). The Free plan costs $0 with 200 vCPU-hours and 400 GiB-hours of memory a month and needs no card (20). A person has to sign in through a browser first. After that an agent can mint its own key with `freestyle tokens create --output json`, so 5 of 20 (5).

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.

## 4. Transparency & trust, 41 out of 100, up to 5.2 more on the total

Made of editorial 20, provenance 62.

Why it scored 41: The platform is closed. The SDK and CLI are MIT on npm, and no terms of service or service agreement was found on www.freestyle.sh (`/terms`, `/tos` and `/legal` answer 404, and the sitemap lists none), so the terms of use are unclear (8 of 30). The privacy policy, last updated 15 June 2025, covers the website only, and no DPA, retention period or statement on customer VM data was found (3 of 30). The 9 September 2026 changelog deprecates the Git, code execution, web deployment and scheduled trigger APIs, and the OpenAPI file marks every unversioned route deprecated, in both cases without a removal date (6 of 20). The privacy policy names Google Analytics and PostHog for the website. No sub-processor list or data location for VMs was found (3 of 20).

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: freestyle.sh, registered 2024-04-11 (2 years) (7 of 15)
- Terms of service: not found (0 of 10)
- Privacy policy: not found (0 of 10)
- security.txt: not found (0 of 10)

## 5. Agent ergonomics, 69 out of 100, up to 5 more on the total

Why it scored 69: List calls take `limit` and `offset`, file reads take byte ranges, and paused VMs can be read without starting compute. `exec-await` returns whole stdout and stderr with no documented size control (15 of 25). VM lists filter by state, slug, search, snapshot, VPC and metadata, and snapshot lists by source VM and search (18 of 20). Every error has a stable `code` in SCREAMING_SNAKE_CASE and a message, and limit errors name the limit reached (18 of 20). No idempotency keys. A slug is unique per account and a repeated create answers 409, and the spec says which failures are safe to retry and warns against retrying an exec that returned `VM_NON_RESPONSIVE` (10 of 20). A create call needs only `firewall`, with defaults of 4 vCPU, 8 GiB and 32 GB. The only SDK is TypeScript, shipped with the CLI in one npm package (8 of 15).

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.

## 6. Maintenance & community, 71 out of 100, up to 2.5 more on the total

Why it scored 71: `freestyle` 0.2.16 was published to npm on 27 September 2026 (30). 25 versions were published between 13 August and 27 September 2026 (20). Closed service with a public changelog of three entries in 2026 and a Discord server, whose response times we did not check (8 of 15). One current official SDK, TypeScript, with the CLI in the same package (10 of 15). The package has three dependencies and no `repository` field, no public CI was found, and the CLI repository linked from the site footer (freestyle-sh/freestyle-sh) last changed on 22 May 2025 (3 of 10).

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. Schema & documentation, 86 out of 100, up to 2.3 more on the total

Why it scored 86: A public OpenAPI 3.1 file at www.freestyle.sh/openapi.json with 88 operations under `/v5` and 128 schemas (25). llms.txt, llms-full.txt, a Markdown twin of every docs page and a read-only shell over the docs at `/docs/bash` (10). Every `/v5` operation has a description, and the about page states when to use the product and when not to (18 of 20). Request bodies are typed with enums, required fields and `additionalProperties: false`, with free-form objects only for metadata and environment variables (13 of 15). Each operation lists its error statuses with a named code and cause, on one `PublicErrorBody` shape, and the docs carry TypeScript and CLI examples but few raw HTTP examples (12 of 15). Paths are versioned at `/v5`, but the changelog has three entries in 2026 (11 April, 17 April, 9 September) and the npm package ships no changelog across 25 releases since 10 July (8 of 15).

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.

## 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.

- No terms of service, service agreement or DPA was found on www.freestyle.sh, so `provenance.terms` is left out. The dashboard at dash.freestyle.sh is drawn by script and may link terms at sign-up that we did not see.
- `provenance.privacy` is left out because the only privacy policy (www.freestyle.sh/privacy, 15 June 2025) says it covers the website.
- unchecked: whether the Git, code execution, web deployment and scheduled trigger APIs deprecated on 9 September 2026 were announced beforehand or have a removal date. No deduction taken.
- unchecked: the isolation technology. The docs say full hardware virtualisation on bare metal with oversubscribed hosts and name no hypervisor.
- unchecked: request rate limits on api.freestyle.sh, which are not in the docs. We sent one unauthenticated request and did not probe.
- unchecked: response times on the Discord server, and whether a current public source repository exists for the SDK. The npm package names none.
- llms.txt, docs/llms.txt, the Markdown twins and `/docs/bash` open with a note addressed to AI models asking them to install a `freestyle-docs` skill and to carry the note into any summary. We did not act on it and took no deduction.
- The lead gave the CLI as the interface. There is also a public REST API at https://api.freestyle.sh/v5 with an OpenAPI file, and the legal entity is Freestyle Cloud Inc.

## Weaknesses

- No terms of service or service agreement found on the site, and the privacy policy covers the website only
- The status page shows three components with no incident history
- No request rate limit, Retry-After guidance or idempotency keys found in the docs or the OpenAPI file
- No security.txt, disclosure policy, bug bounty or SOC 2 statement found. Audit logs are Enterprise only
- TypeScript is the only SDK, and the CLI repository linked from the site last changed on 22 May 2025

## 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.

- Send a `firewall` object on every `POST /v5/vms`. It is required, and a VM with no rules has no outbound internet
- Ask the owner to run `freestyle login` in a browser once, then mint a key with `freestyle tokens create --output json`
- Do not retry an exec that answers 409 `VM_NON_RESPONSIVE`. The command may already have run
- Keep `exec-await` under its 300,000 ms cap and use a PTY session or `x-freestyle-background-after-secs` for longer work
- Call the `/v5` paths. The unversioned duplicates in the OpenAPI file are marked deprecated

## 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.