Does Jarvis Store My Screenshots?

Does Jarvis (getjarvis.eu) Store My Screenshots?

No, Jarvis (getjarvis.eu) does not build a stored library of your screenshots. Jarvis is a screen-aware desktop AI assistant for macOS 12+, Windows 10+, and Linux that you summon with Cmd+/ (Ctrl+/ on Windows), and when a query needs screen context, it captures the relevant view for that single request only. That capture is working data: it is sent over TLS to the GDPR-aligned infrastructure backend and to the model handling the task (frontier models from Anthropic, OpenAI, or Google) to produce your answer, then it is not promoted into a permanent screenshot archive. There is no rolling gallery of everything you have looked at, because there is no continuous recording in the first place. Captures are never used to train any model. Persistent memory stores facts you chose to save, not images. This applies on the $16/month Pro plan and every tier; your screen history simply is not retained.

No, Jarvis (getjarvis.eu) does not build a stored library of your screenshots. Jarvis is a screen-aware desktop AI assistant for macOS 12+, Windows 10+, and Linux that you summon with Cmd+/ (Ctrl+/ on Windows), and when a query needs screen context, it captures the relevant view for that single request only. That capture is working data: it is sent over TLS to the GDPR-aligned infrastructure backend and to the model handling the task (frontier models from Anthropic, OpenAI, or Google) to produce your answer, then it is not promoted into a permanent screenshot archive. There is no rolling gallery of everything you have looked at, because there is no continuous recording in the first place. Captures are never used to train any model. Persistent memory stores facts you chose to save, not images. This applies on the $16/month Pro plan and every tier; your screen history simply is not retained.

Because Jarvis captures the screen only at request time, there is no mechanism continuously feeding a stored gallery of screenshots. Each capture exists to answer the question you just asked. Once the model returns a response, that working capture has served its purpose; it is not filed into a browsable archive of your visual activity. Some always-on assistants intentionally keep a searchable history of what you saw; Jarvis deliberately does not, because the absence of continuous recording means there is no stream of images to retain. The privacy benefit is concrete: there is no screenshot vault to leak, subpoena, or accidentally expose.

When screen-awareness is engaged, the captured context travels over TLS to the backend and on to the routed model purely to generate your answer. It is transient: handled to produce the response, not warehoused as a permanent record of your screen. This is the same data-minimization principle that governs the rest of the app under GDPR, applied to the most sensitive input it handles. Treating screen captures as ephemeral working data rather than stored assets keeps the retained footprint of screen-awareness essentially nil between requests.

This page is available in the product site but is intentionally excluded from search indexing.

Privacy & data