Tweet Radar
Chrome extension that scores loaded X posts against your reading goal with Jev and ranks top matches pairwise.
Overview
Tweet Radar (推文雷达) helps readers find posts worth reading on X according to their own criteria. The extension reads posts already loaded on the page, sends each post's text along with your written goal and reader profile to Jev, and shows the resulting probability as a colored badge. It does not search, scroll or open posts by itself.
When at least two candidates pass the threshold, an optional "top three" mode compares up to 12 candidates pairwise with Choice questions and recommends up to three with jump links, at extra token cost. The core of the project is a community library of rule sets, goals, judging subjects and counterexamples, in Chinese and English. It uses your own TypeSafe key, stored locally; post text and goals are sent to TypeSafe. The README cautions that probabilities are not real-world accuracy.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this post relevant to the reader's goal and profile? | yes · no |
| Choice | Which of these two posts better matches the goal? | post A · post B |
How it works
- Write a goal, a reader profile and exclusions in the extension.
- Loaded posts are sent to Jev for a Noul relevance probability.
- Badges show green, yellow or grey by probability.
- Optionally run pairwise Choice comparisons to surface the top three.
Strengths
- Filtering criteria are user-written and shareable.
- Pairwise ranking is optional, controlling cost.
- Does not reorder or alter X's feed.
Caveats
- Sideloaded; not on the Chrome Web Store.
- Sends post text to TypeSafe with your own key.
- Screenshots in the README are illustrative, not real runs.
Getting started
Download the extension ZIP from Releases, load it unpacked in chrome://extensions, then enter your goal and TypeSafe key.At a glance
- Type
- Project
- Status
- beta
- Language
- JavaScript
- Runtime
- Chrome extension
- Has code
- yes
Use cases and integrations
How curated lists describe it
Social reading: uses Jev `Noul` to score already-loaded X posts against a reader's goal and profile, then pairwise `Choice` judgments to rank eligible matches and surface up to three for review.
yibie/awesome-jevJev / TypeSafe AI 驱动的 X 信息筛选：按你的规则发现值得读的帖子。开源判断规则库 + 免费 Chrome 扩展。Filter X with your own criteria.
hellogumbo/awesome-jev
Frequently asked questions
What does Tweet Radar decide?
How relevant each loaded post is to your goal, and optionally which posts are the best three matches.
Does it need a TypeSafe key?
Yes, you supply your own key, stored in the extension's local storage.
Is it a fact checker?
No, the README says it is a reading aid, not fact verification.
Related projects
Local-first feed that merges arXiv, GitHub, Hacker News and Bilibili results, with optional Jev title-relevance scores as a filter.
ProjectbetaTypeScriptTech reading feed from Hacker News, Dev.to, Hashnode and Lobsters, ranked by Jev scores against your skill summary.
ProjectprototypeTypeScriptChrome extension that asks Jev typed questions about an article, video or feed item and says read now, skim, save or skip.
Browser extensionbetaPython CLI that fetches recent arXiv papers, scores relevance to your research profile with Jev P(True) and writes daily rankings.
ProjectprototypePython- Paper Radar★ 30
Daily arXiv and bioRxiv radar where Jev answers one yes/no per plain-English interest for every new paper; fork-and-go GitHub Action.
AppbetaPython Multi-user Telegram bot that judges every new post in public channels with Jev templates and routes matches to your DM or channels.
ProjectbetaPython