Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Feed Lens

Chrome extension that labels Weibo, Threads and X posts by topic and expression style using Jev and your own label dictionary.

Browser extensionbetaApache-2.0
View on GitHub ↗

Overview

Feed Lens is an open-source Chrome extension that adds customisable text labels beside posts on Weibo, Threads and X, showing what a post is about and how it communicates. Labels are organised into content topics and expression styles, and you can edit both the displayed label and the description used for classification. Each platform has its own dictionary and automatic-labelling switch, and up to four labels show beside the author with a gear for scores, extracted text and retries.

According to a list summary, it uses Jev Noul judgments against the user-defined labels. It requires your own TypeSafe API key and usage allowance; the key stays in the browser and settings can be exported as JSON. New installations start with all platforms paused. The interface supports six languages, and the README states it is independent of the social platforms, Google and TypeSafe.

What the decision model decides

TypeQuestionAnswers
Yes / noDoes this post match the user-defined label (topic or expression style)?yes · no

How it works

  1. Enable automatic labelling for a platform
  2. Extension extracts post text
  3. Jev judges each label for each post
  4. Show up to four labels beside the author

Strengths

  • User-defined labels and descriptions
  • Per-platform control, paused by default
  • Key stays in the browser

Caveats

  • Usage billed to your TypeSafe account
  • Installed unpacked from releases

Getting started

Download the release zip, load it unpacked at chrome://extensions, enter your TypeSafe key in settings and enable a platform.

At a glance

Type
Browser extension
Status
beta
Language
TypeScript
Runtime
Chrome extension
Has code
yes
License
Apache-2.0

Use cases and integrations

How curated lists describe it

  • Social media: uses Jev `Noul` judgments against per-platform, user-defined topic and expression labels to annotate Weibo, Threads and X posts directly in a Chrome extension.

    yibie/awesome-jev

Frequently asked questions

Which sites are supported?

Weibo, Threads and X.

Can I define my own labels?

Yes, both the label and its classification description.

Who pays for API usage?

Your TypeSafe account.

Related projects

  • bluenoise

    Privacy-first X filtering extension with local keyword and account rules, plus an optional Jev second pass on replies no rule matched.

    Pluginproduction
  • Sharp

    Browser extension that filters your X timeline by plain-language rules, with a decision model like Jev scoring every post by default.

    Browser extensionproductionTypeScript
  • Jev Chat for Twitch

    Chrome extension adding a second Twitch chat column that shows only messages Jev classifies as helpful, questions, funny or feedback.

    Browser extensionbetaJavaScript
  • JevFilterForX

    Browser extension that scores X posts 0-100 with Jev on signal, actionability and originality and folds low-value posts.

    Browser extensionbetaTypeScript
  • lkclean

    Chrome extension that has Jev judge each LinkedIn post for engagement bait, self-promotion and relevance, hiding noise with explanations.

    Browser extensionbetaTypeScript
  • PlotVeil

    Chrome extension that covers YouTube comments while one Jev yes/no per comment checks for spoilers of the video or protected titles.

    Browser extensionbetaTypeScript