Rewisp - See it once. Ask forever.
by•
Rewisp gives your Mac a memory. It reads your screen text on-device and remembers it for you. Catches promises like "I'll send it Friday" and reminds you until it's done. Ask "what changed since Tuesday?" and see exactly what's new. Search by meaning, not just words. Tracks numbers like weight or grades over time. Fills forms from your saved details — never passwords. One quiet 9 PM summary each day. Fully private: screenshots never saved, only text stays on your Mac.
Replies
Keeping everything on-device and never saving screenshots is the smart trust move here, a memory tool only works if you feel safe letting it watch.
Rewisp
@ilko_kacharov Thank you for the feedback!
Dial
on-device is the right call for something reading everything on your screen all day, but on-device isn't automatically safe - if my Mac gets stolen or someone gets local access, is that stored text file encrypted at rest, or just sitting in plaintext waiting to be read?
Rewisp
@omri_ben_shoham1 Good catch, thank you. Right now the database is a plaintext SQLite file, so FileVault plus your account permissions are what protect it at rest, and the Vault holding your personal details sits behind Touch ID(mac's auth) in the app on top of that. App-level encryption is on the roadmap and this is a good push to prioritize it.
The ambient memory idea feels useful for people who context-switch all day. The tricky part for me would be separating “I saw this once” from “this is worth remembering.” Are you doing any local filtering or recency scoring so old or accidental screen content does not pollute answers?
Rewisp
@simon_dao Yes, all locally: near-identical frames are dropped at capture, retrieval fuses keyword and semantic relevance with recency so old content has to be clearly relevant to surface, and anything you actually ask about gets reinforced and exempted from expiry while everything else decays and ages out around six months.
@yashmitb That retrieval design sounds thoughtful. The decay window plus explicit reinforcement is a nice way to avoid turning ambient memory into a junk drawer. Do users get any control over what gets reinforced or forgotten, or is that mostly automatic right now?
Rewisp
@simon_dao Good question, the user has a page in the app called memory and they can either approve or deny things as they get caught in the daily digest. They are able to approve of these and deny them at any point so if they think a memory is no longer important they can remove it. And based on this the app decides which wisps are important and which ones aren't and removes them.
@yashmitb That makes a lot of sense. The daily digest approval step feels like the right balance: automatic enough to catch things you would otherwise lose, but still giving the user a cleanup pass before memory gets stale. I also like that importance is learned from explicit approve/remove actions rather than just raw screen frequency.
LottieFiles
On-device screen reading is the right call, but I am curious about the practical cost — what does continuous OCR do to battery on a laptop that is unplugged all day? And can I exclude specific apps entirely (password managers, banking) so they never even hit the local index?
Rewisp
@reallynattu Good catches! The computational cost is little to none. In the 2 weeks of development/testing phase, my computer's battery performed the exact same. I even wrote a benchmark test to get real numbers and on average the program effected my computer's battery level by 1.1%. And also yes, you can blacklist apps and websites on the dashboard so they are blocked before even trying to get stored(the app automatically has some built in but is super customizable).
nice idea, do u plan to release a similar version for Windows as well?
Rewisp
@luca_ardito Yes! I'm currently taking feedback and improving my plans and going to make a windows version very soon!
The "what changed since Tuesday" search actually pulled up stuff I'd completely forgotten about scrolling through, which was a nice surprise. The on-device-only approach makes me feel way better about letting it read everything on my screen.
Rewisp
@salcanamin72213 Thank you for the kind words :)
As a fellow solo dev, the privacy-by-construction bit (text-only, screenshots discarded on the spot) is what makes this trustworthy vs a plain screen recorder. One thing I always hit shipping Mac apps though — the screen-recording permission prompt on first launch scares a chunk of users off. How are you handling that onboarding moment so people don't bounce before they get to the value?
Rewisp
@lennoxbeflying This is still an issue I am working on trying to fix. I would love to connect outside of this and discuss/collab more on this issue.
Congrats on the launch and #5th rank on Sunday.
Love the promise-catching idea. that's the stuff that always slips through the cracks. Does it handle commitments made in voice memos or dictated text, or only typed content?
Rewisp
@kbaqeri Thank you!
It currently handles everything that it saw on the screen, no audio/dictated content can be detected yet, but it is in the future improvements.
Awesome! Under what context and rules does it catch and register as something remind you about? Would writing "I should make x adjustment to y project" count? Also not sure if this is already possible but if it could be connected to a broader to do list or calendars so that it would seamlessly incorporate reminders into someone's "plan", I think that would be very useful too.
Video feedback is a workflow that's surprisingly painful today.
Do you think AI's biggest value is generating better feedback, or making collaboration fast enough that teams review more often?