21–29 of 29 posts
Very cool! Congratulations on putting this together. Was also tinkering with Gmail bloat but, admittedly, with a less ambitious approach. Definitely going to give it a try.
Did you really use a LLM to generate the sample output in your readme instead of just running the application? I noticed the borders were all misaligned and wondered if you had hardcoded the number of spaces, but I looked at the code and you haven't. If you did generate the output with a LLM instead of just running it... why? Also: > It uses Claude AI for smart classification, but runs entirely locally: your emails n…
I would love it if it could run against archived messages (`in:anywhere -in:trash -in:spam`) ... I've been archiving all email for a very long time and being able to run stats and purge it would do wonders.
For me, it seems to be quite a few senders that fill my inbox. running
``` mailtrim purge ```
only finds about 200 MB of purge suggestions with a mailbox of 15GB, but deleting a few and running again finds a few more.
Gmail does some classification, it might be useful to have scopes that match those: promotions, updates, social and forums.
IMAP support would be useful for a yahoo account even if it's slower/less accurate. This is better than manual cleanup.
curious how you handle the volume - for heavy users with 50k+ emails, are you processing everything client-side or hitting the gmail api for each message?