Help and Privacy Policy

Can't see models in the list?
Make sure your Ollama models are installed and located in ~/.ollama/models. The app should auto-detect this location.
Server won't start?
Click the Start button under "Local Server Control". Make sure no other app is using the same port. Try restarting your Mac if issues persist.
Export not working?
When saving a chat, choose a valid destination folder and confirm write permissions.
Is this private?
Yes. All model inference happens locally on your Mac. No cloud or internet access is required for chat processing.
Still stuck?
Email support@cerevault.com and tell us which app, which Mac and which macOS version you use.

Privacy

Privacy Policy

Perfect Brief Studio. The Perfect Brief Studio app does not collect or transmit any personal data, and has no accounts, analytics or tracking. The requests you paste and the briefs you generate stay on your Mac. A built-in language model runs on your Mac and is downloaded once from Hugging Face when you choose to. If you choose to connect a language-model server (such as Ollama, LM Studio or CereVault Serve) or a cloud provider with your own API key, your request is sent to that server or provider, and their privacy terms apply. API keys are stored in the macOS Keychain on your Mac. Questions: support@cerevault.com.

The CereVault app does not collect or transmit any personal data. All language model processing occurs locally on your Mac and never leaves your device. No usage analytics, chat history, or personal information is stored or shared.

Our websites. cerevault.com and wickbrook.com use Google Analytics to count visits and see which pages are read. Google may set cookies and collect your IP address, browser and approximate location for this purpose. This applies only to the websites, never to the apps. You can opt out with Google's opt-out browser add-on. In Europe, the UK, Switzerland and Quebec we ask first, and you can change your choice at any time: Analytics choices.