Everything that uses a model you have already downloaded works offline. Chat, transcription, speech, image work and the tools all run on your Mac, so pulling the network cable changes nothing about them. What needs a connection is downloading something you do not have yet, plus the few background checks listed below.

Works with no connection

  • Every model already on disk, for every task it supports.
  • All the local tools: files, system control, browser automation against a browser on this machine.
  • The knowledge base, which ships inside the app and answers offline once its encoder model is on disk, and the in-app help pages.

Needs a connection

  • Downloading a model you have not installed.
  • Cloud model providers, if you have configured one with your own API key. Those are calls to that provider, made by your machine, using your key.
  • Checking for an app update, which happens on its own every six hours when a connection exists, sends no identifiers and reads the release list. ToolPiper may also download updated versions of its built-in model files.
  • Refreshing your license, about every six hours, when you are signed in.
  • Sending the daily activity count, if you leave it on.

This is the architecture, not a fallback

Your prompts, files and outputs stay on your Mac when you use local models, so offline is the same code path as online rather than a degraded mode that gets less testing. ToolPiper contacts our servers for update checks, a license check when you're signed in and a daily activity count, and it can send optional usage counts. You can turn the last two off in Settings, and none of them include your content.

  • Update checks go to releases.modelpiper.com about every six hours and carry no identifiers.
  • The license check goes to api.modelpiper.com about every six hours while you are signed in. It identifies your account and this Mac.
  • The daily activity count reports which days ToolPiper was used, its version and its release channel. It is on by default, has its own switch in Settings → Activity, and is stored only as totals.
  • Optional usage counts are on by default. Turn them off in Settings → Analytics.
  • A benchmark is sent only if you choose to submit one. It shows you what it sends first, and it is linked to your installation (and your account when you are signed in); published results omit identifiers.

Working on a plane

Download the models you want before you go and nothing else is required. There is no license check on the way to a local model and no first-run activation that has to happen online.

If you use a cloud provider through your own key, that one path stops until you have a connection again. Local models keep working.