Last updated: April 23, 2026
Open Pocket is designed with privacy as a core principle. All language model inference runs entirely on your device. We do not operate any servers, and no data is transmitted from the app.
Open Pocket does not collect, store, or transmit any personal data. Specifically:
All AI model inference is performed locally on your device using Apple’s MLX framework. Your conversations, prompts, and model outputs are stored only on your device and are never uploaded to any server.
The app downloads AI models from public repositories (HuggingFace, ModelScope). These downloads are standard HTTPS requests to public servers. No personal data is sent during this process.
Open Pocket does not collect any personal information from anyone, including children under the age of 13.
We may update this privacy policy from time to time. Any changes will be reflected on this page with an updated revision date.
If you have any questions about this privacy policy, please contact us at:
Email: thinkhejie@163.com