Jev in production › Moderation and content filtering

lkclean

Chrome extension sends each LinkedIn post and the user's interests to Jev in one request of typed questions; local thresholds turn the probabilities into collapsing engagement bait, self-promotion and blocked topics, with scores shown on the post.

Open on GitHub ↗

The source publishes no measured number.
Use
Moderation and content filtering
Industry
Media and social
Form
Open-source tool
Stage
In production
Plugs into
Chrome
Listed
2026-09-22
Found via
github
Repository
stefw/lkclean
Stars
14
Forks
1
Last push
2026-09-20
Language
TypeScript
License
MIT

The README opens with

A Chrome extension (Manifest V3, TypeScript) that cleans up your LinkedIn feed. Every post is sent to Jev, the typed classification model from TypeSafe AI, which returns probabilities instead of prose. Engagement bait, self-promotion, off-topic and sponsored posts are collapsed into a one-line bar, and every decision is explained right on the post.

Not affiliated with LinkedIn or TypeSafe AI. You need your own TypeSafe API key.

- Hides the noise – engagement bait, humble-brags, sponsored posts, topics you block, and posts unrelated to the interests you list. - Explains itself – hidden posts show the reason and the scores, with a Show / Hide again toggle. Kept posts get a discreet "Kept by Jev" line with their scores; a score close to the...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for moderation and content filtering