Before Gemma touches my mom's phone, I raced it on mine: 35 minutes deleting Good Morning forwards by hand vs one night
Description and use
Good Morning Sweep automates the removal of WhatsApp Good Morning forwards and duplicate or accidental photos from a phone using a locally run Gemma 4 model, saving time while ensuring personal photos are preserved.
Problem
Parents’ phones accumulate large numbers of WhatsApp Good Morning forwards, duplicate photos, blurry or accidental shots, and old screenshots, consuming storage and cluttering the gallery.
Outcome
The tool deleted 1,137 images in 31 minutes, matching the manual effort but with automated, repeatable, and safe deletion; no personal photos were mistakenly removed.
Workflow
- Plug phone into laptop via USB
- Run
sweep runto copy WhatsApp Images, WhatsApp Video, Screenshots and Camera folders to laptop - Gemma 4 E2B processes each image, returning a JSON with kind, words, people, screen
- Apply rules (forward detection, duplicates, blur/brightness, age, etc.) to decide deletion
- Generate review page with grouped suggestions and explanations
- User reviews page, taps to keep or delete
- Run
sweep reviewto delete selected files from phone after confirmation
Evidence
Good Morning Sweep clears junk off a phone without uploading anything. You plug the phone into a laptop. The laptop copies the WhatsApp pictures, WhatsApp videos, screenshots and camera photos, and then Gemma 4, an open AI model running on the laptop itself, looks at them one by one.
For each picture, Gemma says what it is (a greeting, a quote, a meme, forwarded news, an ad, a real photo, a document, a screenshot or an accidental shot) and copies out the words printed on it.
The rule I kept coming back to: it reads before it deletes.
The scan runs as a Temporal workflow: if the model crashes, each picture is retried until it gets an answer, and if the laptop sleeps, running the command again carries on from the next picture.
- Record date: 2026-10-26T07:26:10.809Z