Support

Help for Ghost Architect™.

// contact

Email: [email protected]

Typical response time: within 1 business day

Start a live chat

// ghost open™ cli

What does Ghost Architect™ do?

It tells you what is in a codebase before you commit money or people to it: the risks, the conflicts, what each fix will reach, and what it will cost to fix. It reads your codebase, ranks findings by severity and business impact, estimates remediation cost, and writes reports you can share with clients or stakeholders, on any language and any platform.

How do I install Ghost Open™?

Ghost Open™ has no license fee for one person and installs from npm:

npm install -g ghost-architect-open

Every mode runs unlimited on your own Anthropic API key. There is no license key to activate. For teams, see Ghost Architect™ Local.

What are the requirements?

  • Node.js 18 or later
  • An Anthropic API key (BYOK: Bring Your Own Key)
  • macOS, Windows or Linux

Is my code sent to your servers?

No. Ghost Open™ runs on your machine, and your code goes directly from your machine to Anthropic’s API using your own API key. It never reaches a server of ours. See the Privacy Policy for details.

My code cannot leave our infrastructure at all. What then?

Then Ghost Open™ is not the right one, and Ghost Architect™ Local is: it runs against a model you host, on your own hardware, with zero-egress mode included in every license. While it analyzes, nothing about the code leaves your machines.

// ghost architect™ mobile

Ghost Architect™ Mobile is the iOS and iPadOS companion app. It gives architects, CTOs and agency leaders a portfolio view of their reports (remediation progress, critical findings and estimated cost) on their phone or tablet.

What does the app do?

It reads reports from a private GitHub repository and displays them as an interactive portfolio. You can see overall remediation progress across your projects, drill into any project’s findings, and present results to stakeholders in a client-ready Present Mode.

Which setups publish reports to the app?

Ghost Open™ does not publish reports to the mobile app. If you are not sure whether your setup does, email [email protected] and we will tell you directly.

How do I connect my own data?

The app uses a GitHub Personal Access Token (PAT) to read reports from a private repository you control. Tap Settings in the app, enter your GitHub PAT and repository URL, and your reports will sync. Your PAT is stored only on your device and is never transmitted to us.

What is Demo Mode?

When you first install the app, you see a seeded demo portfolio with a single example project (meta-for-magento2) showing what the reports look like. Demo data stays until you connect your own GitHub repository in Settings, and you can revisit Demo Mode at any time from Settings.

Why is my report not showing up?

  • Confirm your GitHub PAT has repo scope for the repository
  • Confirm the repository contains Ghost Architect™ report files at the expected path
  • Confirm the reports come from a setup that publishes to the app (reports from Ghost Open™ do not)
  • Pull down on the portfolio screen to force a refresh

// billing and licenses

Is there anything to pay for or cancel?

Not for Ghost Open™: it has no license fee for one person and no subscription. You pay Anthropic directly for the model usage on your own API key.

How do I cancel a Ghost Architect™ Local license?

Ghost Architect™ Local licenses are managed through Stripe. Sign in to the billing portal with the email address you bought with: you can update your card, see your invoices, or cancel. A canceled subscription runs to the end of the period you paid for. The link is in your purchase email too. If it does not work for you, email [email protected].

Do you offer refunds?

Refund requests are handled case by case. Contact [email protected] with your license details and we will work with you directly.

// what ghost architect™ local is

Ghost Architect™ Local is the edition for code that cannot leave the building. Everything runs on machines you own: your code is read from your disk, analyzed by your model, and written to reports on your machines.

It is a different product from Ghost Open™. Local is not on npm and does not need an Anthropic API key: it runs on the model server you host. Its Cloud API position, on your own key, is off by default. If you installed something with npm install -g ghost-architect-open, that is Ghost Open™, not Local.

// getting it

How do I get the download?

Local is delivered directly by us, not through a public package registry. Fill in the form on the download page and the download link is emailed to you straight away.

How do I verify the tarball before I install it?

The file is about to become a global command on your machine, so check it first:

shasum -a 256 ghost-architect-local-8.1.19.tgz

On Windows PowerShell: Get-FileHash -Algorithm SHA256 ghost-architect-local-8.1.19.tgz

Expected for 8.1.19: 84e0350b566fdb563600b3db74fd18a0ebcca5f07cf6c4038924dc7a0ed817c7

If the hash does not match, stop. Do not install it. Email [email protected] with what you got.

// requirements

  • macOS 13 or later, Linux, or Windows 10 or later. The installer checks the OS floor and stops below it rather than guessing.
  • Node.js 24 or later. The installer checks for it and does not install it.
  • A model server on your network with a model pulled: Ollama, vLLM, LM Studio, Jan.ai or any OpenAI-compatible endpoint. Our own machines run qwen3.5:9b on Ollama.
  • Enough disk for the model you choose; your model server lists each model’s size.
  • A second machine only if you want the fleet view. Any of the three platforms can be a spoke.

The installer does not install Node.js, Homebrew or a model server for you. It checks for them and stops with a single list of what is missing. Want company for the install? Ask for an install call and we will do it together.

// installing

Everything happens inside the directory you unpack. Keep that directory: the global ghost command links into it rather than copying it.

tar -xzf ghost-architect-local-8.1.19.tgz
cd package
bash install/setup.sh              # macOS
sudo bash install/setup-linux.sh   # Linux
.\install\setup.ps1                # Windows, elevated PowerShell

The installer tells you what it changes on your machine before it changes it, and the full guide, INSTALL.md, is in the directory you just unpacked.

How do I upgrade?

Re-running the installer is the supported upgrade path. Your service account, data root and signing key are left alone.

Is the Windows installer safe to use?

Honest answer: it runs on our own Windows hardware. Ghost Architect™ Local is installed on a Windows machine as two Windows Services, and the full test suite runs on that machine on every push. We have not yet watched a fresh install on a machine outside our own, so send us the console output of yours and we will work it through with you.

// first run and the evaluation trial

Run ghost. The evaluation trial starts on first use, registered against that install, and the product tells you the day it ends. No card, no account.

Start with Recon: it tells you what a full scan of your codebase will read and how long it will take on your machine, with the basis of that estimate printed beside the number.

Then open the portal it prints (https://localhost:3443 by default) for the Fleet page, the queue, LLM Status and the reports.

To keep it, convert from inside the product during the trial and your first month is half price. The license arrives by email, signed, and activates against that install.

// hub and spokes

What is the difference?

One machine is the hub: it holds the model server, the user roster, the license, the portal and the queue. Every other machine is a spoke. A spoke runs scans and reports them back, and its model calls relay to the hub’s model server over your LAN, so a spoke does not need its own model. A solo installation is just a hub.

How do I add a machine?

Enroll it from Admin Console on the hub. On the new machine, run ghost, choose Spoke, and enter the hub address plus the activation token from your admin.

What do the roles mean?

  • admin and architect see the full portal
  • developer works with assigned projects
  • viewer sees project health and reports
  • auditor sees the audit log and compliance exports

// the portal says “not secure”

That is expected on a first visit, and please do not just click through it. Your hub generates its own TLS certificate at install time, and a browser will not trust it until you tell it to. The connection is encrypted either way; what the browser cannot confirm yet is your hub’s identity.

Admin Console, System Settings, TLS prints the exact commands with your own hub address already filled in, and docs/PORTAL-CERTIFICATE.md in your install has the steps for macOS, Windows and Linux. It takes a few minutes per machine. A certificate from your own internal CA removes the step entirely.

// zero egress

Does anything leave my network?

One call, once: license activation sends the license key and an install id to ghostarchitect.dev and gets a signed license back. Nothing from your codebase is in it. After that you can turn on zero-egress mode, included with every license, and the product refuses every internet-bound destination at the code level.

What stays reachable under zero egress are the LAN destinations you control: your model endpoint, your SMTP relay, your SIEM collector, and hub-to-spoke traffic between your own machines. Those do need to actually be on your network for the containment to hold.

How do I know what it can send?

Look in the product, not at a page like this one: Admin Console, System Settings, Egress Inventory lists every vector, its current on or off status, exactly what it would send, and how to turn it off. That screen is generated from the same code that gates the traffic, so it cannot drift from reality the way documentation can.

Activation fails with zero egress on. Is that a bug?

No, that is the design. License key activation is an outbound call, so zero egress blocks it and the product says so directly. Install the signed license file instead:

ghost --install-license /path/to/license.json

Ask us for the file rather than turning zero egress off.

// licenses

How do I install a purchased license?

Two paths, both ending with a signed license.json in your data root, after which license checks run fully offline. With outbound access: run ghost, open Admin Console, then License Management, and enter your key. Fully offline: we send you the signed file and you run ghost --install-license.

What does it cost?

$80, $400, $1,000 or $2,000 a month for 1, 5, 15 or unlimited seats. No per-token bill, cancel any time, and the first month is half price when you convert during the trial. The details are on the pricing page; for questions about your setup, email [email protected] and we will confirm it for you directly.

// if something goes wrong

  • ghost --version confirms the CLI is installed and on your PATH.
  • logs/portal.log in your data root (usually ~/.ghost-local/logs/portal.log) is the first place to look if the portal address does not answer. It holds both the portal’s output and its errors.
  • logs/scheduler.log is where to look if a scheduled job did not run.
  • If the installer’s self-test failed, the product is installed and your model provider is the thing to look at. That is why the installer says so rather than claiming a broken install.
  • Ask about Ghost, inside the product, answers from the manual and error catalog that ship with your version.

Anything else: email [email protected] and include the installer output, or start a chat above with the product set to Local.

// bug reports and feature requests

Email [email protected] with:

  • A clear description of the issue or requested feature
  • Which product you are on, Ghost Architect™ Local or Ghost Open™
  • Your version (run ghost --version)
  • Your operating system
  • Any relevant error messages or screenshots

// security disclosures

If you discover a security issue in Ghost Architect™, please disclose it responsibly by emailing [email protected] with “SECURITY” in the subject line. Security reports are never handled by the automated support agent; they go to the founder directly.