How it works

It runs on your machine, not ours.

AI Agent Sync installs inside your own environment and governs agents from there. Your properties, telemetry, policies, credentials and audit records stay on your infrastructure. We never hold your operational data — there is no copy of it to hold.

The shape of it

Two pieces, and only one of them is ours to run.

Runs on your infrastructure

The product

Scanning, the governance engine, Live Agent telemetry, journeys, policies, the audit trail and your local database. Everything operational. It listens on your own machine and answers only to you.

Runs on ours

Billing and licensing only

Stripe checkout and licence issuance. It knows your subscription is active and nothing else — no site data, no agent activity, no customer records.

Why this matters when agents transact. The audit trail only proves something if it cannot have been quietly edited by a third party. Keeping it inside your boundary is what makes it defensible to an auditor, a bank or a regulator.

The journey, end to end

Free public scan Subscribe Install locally Verify your property Deep scan Govern & remediate Verify independently Monitor

Getting set up

About twenty minutes, once. After that it runs continuously without supervision.

  1. Run the free audit

    No account, nothing installed. It shows you what agents can already read and do on your public site, so you know what you are dealing with before you spend anything. Run it now.

  2. Subscribe

    Choose a plan and pay through Stripe. You are returned to an activation page that issues your licence key immediately — copy it and keep it. It also arrives in your Stripe receipt.

  3. Install it

    Download the installer and double-click it. It checks your Mac, sets everything up privately, starts the app and opens your dashboard. Two to three minutes, no typing.

    The first time you open it, macOS may say it is from an unidentified developer. Right-click the installer and choose Open, then Open again — that only happens once.

    Running Linux or a server, or prefer containers? A Dockerfile ships with it, and the same service runs on your own host. Ask us and we will send the exact steps for your setup.

  4. Activate and set your policies

    Paste your licence key. A setup assistant asks in plain language what your business is, which AI you want it to use — a local model, your own API key, your own gateway — and what your agents are allowed to do. It generates the agent team from your answers.

  5. Connect and verify your property

    Nothing private is assessed until you prove you own the site. You place a small verification file at a well-known address on your own domain. Until that passes, AI Agent Sync only ever looks at what is publicly visible.

  6. Let it run

    From here it works continuously: watching agent traffic, deciding what each agent may do, stopping actions that fail the gates, verifying outcomes independently and recording everything in a tamper-evident trail you can export.

Choosing where it runs

Guardian

Your own machine

A laptop, a workstation or a small server. The local database holds everything. Simplest to start, and nothing leaves the device.

Business

Your own infrastructure

Run it as a container on your existing servers or private cloud, behind your own access controls, with SSO and role-based access for your team.

Enterprise

Air-gapped

Fully disconnected operation for regulated environments. Licences can be provisioned out of band, so the deployment never needs to reach the internet at all.

What we can and cannot see

We never receive

Your site content, agent conversations, telemetry, customer records, policies, credentials, remediation history or audit records. None of it is transmitted to us, because the product has nowhere to send it.

We do receive

Your subscription status through Stripe, so licensing works. That is the whole list. Outbound connections happen only for things you explicitly turn on — a model provider you configure, or an integration you authorize.