lkclean
Chrome extension that has Jev judge each LinkedIn post for engagement bait, self-promotion and relevance, hiding noise with explanations.
Overview
lkclean is a Manifest V3 Chrome extension that cleans up the LinkedIn feed. A content script picks up each post and the service worker sends the author and text, together with your listed interests, to Jev in one request with several typed questions: whether the post is engagement bait, whether it is self-promotion, whether it matches your interests, which interest it covers, and whether it falls under a topic you always want hidden. Plain code turns the probabilities into a verdict using your thresholds.
Hidden posts collapse into a one-line bar showing the reason and scores with a show or hide toggle, and kept posts get a discreet 'Kept by Jev' line, turning orange when a score is close to the threshold to help tuning. A floating badge shows calls in flight, tokens, estimated cost, latency and recent verdicts. It also nudges LinkedIn's infinite scroll when most posts are collapsed. Verdicts are cached per session, and the README estimates a scrolling session costs a fraction of a cent. You need your own TypeSafe key; it is not affiliated with LinkedIn or TypeSafe. Documentation is in English and French.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this post engagement bait? | — |
| Yes / no | Is this post self-promotion? | — |
| Yes / no | Does this post match one of your interests? | — |
| Choice | Which blocked topic, if any, does this post cover? | — |
How it works
- Content script detects each feed post
- Service worker sends the post and your interests to Jev
- Code applies your thresholds to the probabilities
- Noise is collapsed with an explanation; kept posts show scores
- Badge reports cost and latency
Strengths
- Every decision is explained on the post
- Threshold tuning made visible
- Very low cost per session
- Keeps infinite scroll working
Caveats
- Post text is sent to TypeSafe
- Depends on LinkedIn's changing markup
- Requires your own key
At a glance
- Type
- Browser extension
- Status
- beta
- Language
- TypeScript
- Runtime
- Chrome extension (MV3)
- Has code
- yes
Use cases and integrations
How curated lists describe it
Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide?
Whether each post is engagement bait, self-promotion, relevant to your interests or a blocked topic.
Can I see why a post was hidden?
Yes, the reason and scores appear on the collapsed bar.
What does it cost?
A fraction of a cent per scrolling session, per the README.
Related projects
Privacy-first X filtering extension with local keyword and account rules, plus an optional Jev second pass on replies no rule matched.
PluginproductionBrowser extension that filters your X timeline by plain-language rules, with a decision model like Jev scoring every post by default.
Browser extensionproductionTypeScriptChrome extension that labels Weibo, Threads and X posts by topic and expression style using Jev and your own label dictionary.
Browser extensionbetaTypeScriptChrome extension adding a second Twitch chat column that shows only messages Jev classifies as helpful, questions, funny or feedback.
Browser extensionbetaJavaScriptBrowser extension that scores X posts 0-100 with Jev on signal, actionability and originality and folds low-value posts.
Browser extensionbetaTypeScriptChrome extension that covers YouTube comments while one Jev yes/no per comment checks for spoilers of the video or protected titles.
Browser extensionbetaTypeScript