# Fix list: Core From Anchor Terminal's listing at https://www.anchorterminal.com/tools/ghost-core, the October 2026 research run, assessed 5 October 2026. Grade F, 7.3 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 Core: 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, 5 out of 100, up to 19 more on the total Why it scored 5: Read with the local-software lines, as GHOST.md asks and as the Underdog and Screenpipe dossiers did for software the owner runs. Core is a box running Ghost's software at home, and it hadn't shipped on 5 October 2026 (batch 1 is scheduled for 31 October). Nothing installs today. The app page states 'Apple Silicon only, macOS Big Sur or higher', but its download buttons link to the setup guide (checked 23:33 UTC) and no package is published, so the line isn't met (0 of 20). The software is closed and no public CI or tests were found (0). No public issue tracker or forum, and no units have shipped, so there's nothing to count. Underdog's judgement call for the same situation (5 of 25). No changelog, release notes or version numbers for Core's software. The setup guide's 'Updated September 18th, 2026' is a dated help page, not a changelog, and ghost.ai/changelog returns 404 (0 of 15). No software version or stability statement, and the product is on pre-order (0 of 15). Low because the product is closed and unshipped, not because of any failure found. 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, 6 out of 100, up to 16.5 more on the total Why it scored 6: Tool lines, graded on the Responses-compatible endpoint as GHOST.md asks, the same interface as Schema and Ergonomics, with the device's documented controls counted where a line covers them. How the endpoint authenticates callers is not documented. No key, token or pairing requirement for it was found, and the privacy policy mentions 'device-access controls' without detail. App pairing covers the app, not the endpoint (0 of 30). Screen history is off until enabled, connected accounts get the permissions the owner approves and can be disconnected, and the setup guide says Ghost connects to home devices only when the owner approves a live view. Against that, the home page says Core acts 'without waiting for a prompt', and no read-only mode or confirmation before it acts through imported browser sessions was found (4 of 20). Core reads email, messages, web results and screen text, all untrusted content, and no prompt-injection guidance was found (0 of 15). No audit log or per-action record described (0 of 15). No security.txt (404 at 23:34 UTC on 5 October 2026), disclosure policy, bug bounty, certification or advisories. The privacy policy invites independent security firms to audit the gateway and relay through support@ghost.ai (2 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. Agent ergonomics, 4 out of 100, up to 15.6 more on the total Why it scored 4: Graded on the Responses-compatible endpoint. No context length, response sizing or truncation is documented for any listed model. Underdog's 5 on this line rested on published evidence of prompt reuse, and nothing comparable was found for Core (0 of 25). No pagination, filtering or output-size controls documented (0 of 20). No error responses documented (0 of 20). Nothing on retries, idempotency or statelessness (0 of 20). Ghost states the endpoint works with any app that supports the Responses API and a custom endpoint, so OpenAI's own SDKs should reach it, a vendor claim that couldn't be tested without an address or credential. No Ghost SDK, default model or required parameters are documented, where Underdog's 7 also covered documented defaults and two named runtimes (4 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. ## 4. Schema & documentation, 7 out of 100, up to 15.1 more on the total Why it scored 7: Graded on the interface an agent would use, the endpoint Ghost's FAQ says is compatible with the OpenAI Responses API, for OpenCode, OpenClaw, Codex and the owner's own apps, scripts and agents. No MCP server or other agent interface found. OpenAI's Responses API is a public contract by reference, but Ghost publishes no spec, address, port, model identifiers or supported parameters. The Underdog dossier gave 5 for an OpenAI-compatible API named with no spec from the vendor (5 of 25). llms.txt, /docs and /developers return 404, and the setup guide is an HTML page for people (0 of 10). One FAQ answer states the endpoint's purpose and the clients it suits, with nothing on when not to use it or its limits. Underdog earned 6 for several model cards stating purpose, so one answer earns 2 (2 of 20). No typed inputs, context lengths or limits documented (0 of 15). No request examples or documented errors (0 of 15). No API versioning or public changelog (0 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. ## 5. Payments & pricing, 10 out of 100, up to 11.3 more on the total Why it scored 10: Self-hosted rule, scoring the paid option (the box), as the Underdog and Screenpipe dossiers did. No x402, MPP or L402 on ghost.ai or in its site code. Orders go through Stripe Checkout (0 of 40). $3,499 one-off, public without a login, with no subscription and no per-token fee stated. That's a single product price with no per-call unit, the reading the Screenpipe and Marmot dossiers used for public prices without a per-call unit, and the line has no step between 10 and 20 (10 of 20). No free tier or trial. The 30-day return follows a paid purchase (0 of 20). A person buys in a browser and pairs the box through the Ghost app, and no programmatic route to access is documented (0 of 20). Batch 1 showed sold out at 23:31 UTC on 5 October 2026, which doesn't change the published price. 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, 3 out of 100, up to 8.5 more on the total Why it scored 3: Read for a closed product. No software release, model update or API change found, since Core hadn't shipped on 5 October 2026. The privacy policy (effective 4 October 2026) and setup guide (updated 18 September 2026) are policy and help pages, not releases (0 of 30). No releases or dated changelog entries in the last 90 days (0 of 20). Closed-service scale. No public changelog, a support page with seven FAQ answers, a setup guide with troubleshooting and support@ghost.ai, while the app page's troubleshooting link uses hello@tryghost.ai. Neither address was tested. Underdog earned 2 for a contact address alone, and Core adds a support page and troubleshooting (3 of 15). No SDK and no MCP registry entry (0 of 15). No visible CI or dependency information (0 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. Transparency & trust, 45 out of 100, up to 4.8 more on the total Made of editorial 30, provenance 60. Why it scored 45: The editorial half. The software is closed, and ghost.ai has no terms of service, terms of sale, warranty terms or software licence (/terms, /legal, /warranty and /returns return 404). Ghost doesn't state the licences of the listed models, and the origin of Muse-Glimmer-30B wasn't found. Unclear terms (0 of 30). The privacy policy of 4 October 2026 says what stays on Core and what passes through Ghost's gateway and relay, says neither stores forwarded content, and gives retention periods (usage counts deleted at the daily reset, diagnostics within seven days of resolution or 30 days of receipt, support cases up to 90 days after closure, screen history seven days after last seen). It names no providers, only categories, and doesn't state the countries of processing, and the home page's 'No data ever leaves your home' and the FAQ's 'entirely on-device' disagree with it. Screenpipe and Marmot earned 18 with named third parties or processors, so 15 here (15 of 30). No deprecation policy or dated notices. The policy's promise of notice before material changes 'where required' covers the privacy policy only, with no period, so it isn't counted as a deprecation notice (0 of 20). The policy says Ghost collects no product telemetry, usage analytics or diagnostic reports from Core or its apps, and discloses the device identifiers, authorisation records and usage counts its online services keep, with routes around both through the owner's own keys and a private network. What over-the-air update checks send isn't described, the gap the Underdog dossier counted on this line (15 of 20). The provenance half is computed from the provenance block, where terms, status page, changelog and security.txt are absent. 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: ghost.ai, registered 2017-12-16 (8 years) (11 of 15) - Status page: not found (0 of 10) - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - 2026-10-05. Ghost's home page says 'No data ever leaves your home' and 'Everything you do with Core is run locally' (seen at 23:31 UTC on 5 October 2026), and the FAQ says Core processes data 'entirely on-device', while the privacy policy, effective 4 October 2026, says web search, phone calls and email requests go through Ghost's gateway to third-party providers that may keep them unless the owner sets their own keys, and that remote access runs through Ghost's relay. A misleading claim, weighed as Screenpipe's README claim was. The policy and the FAQ's internet answer disclose the online services, they carry task requests rather than default-on analytics, and Core hadn't shipped, so the minimum, -2. https://ghost.ai/ ; https://ghost.ai/core ; https://ghost.ai/privacy ## 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. - How the Responses-compatible endpoint is addressed and authenticated, whether it listens beyond the local network, and which Responses API parameters, tools and context lengths it supports. Not found on ghost.ai on 5 October 2026 - Whether the endpoint reaches Core's memory and connected accounts or only runs inference - Terms of sale, warranty terms and software licence. /terms, /legal, /warranty and /returns return 404 - Whether Ghost-managed services are on by default, which third-party providers they use and what their daily limits are - Which desktop platforms the app supports. The FAQ says Mac, Linux and Windows and the app page says Apple Silicon Macs only - The origin and licence of Muse-Glimmer-30B, and the licences Ghost ships the Qwen and Gemma models under - What over-the-air update checks send to Ghost - Batch 2 timing and price. The stock endpoint returned sold_out at 23:31 and 23:35 UTC on 5 October 2026 - unchecked: the Stripe checkout page itself. The one-unit cart and Stripe route are in the site code, and the tax wording is per the draft listing's check earlier on 5 October - The about page names Andreessen Horowitz, Abstract Ventures, Audacious, SV Angel and Z Fellows as backers, a vendor claim not checked - Nothing on the product has been observed in use, since no units had shipped. Every statement about its behaviour is Ghost's ## Weaknesses - Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening - The Responses-compatible endpoint has no published address, port, authentication method, model identifiers, limits or API reference - No terms of service, terms of sale or software licence on ghost.ai, and no security.txt or disclosure policy - Core can import saved passwords and signed-in sessions and act through the owner's accounts, with no confirmation step or injection guidance found - The home page says no data ever leaves the home, while the privacy policy routes online services through Ghost's gateway to third parties ## 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 on reaching a Core before 31 October 2026. Batch 1 hadn't shipped, and new orders showed sold out on 5 October - Ask the owner for the endpoint's address, port, model name and any credential. Ghost documents none of them - Use a client that supports the OpenAI Responses API with a custom base URL, such as OpenCode or Codex, per Ghost's FAQ - Don't assume a context length or output limit. Ghost states none for Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B or Muse-Glimmer-30B - Treat memory and connected-account content as untrusted, and confirm with the owner before acting through imported browser sessions ## What the review panel asked for - documented endpoint authentication - confirmation before acting through imported sessions ## 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.