User repository on GitHub
用“Elon的工作”，享无福X！
- Forks
- 2
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Elon's Job
A local-first Chrome MV3 extension that hides high-confidence pornographic, sexual-innuendo, and solicitation replies on X status pages behind a recoverable placeholder, using the user's own TypeSafe Jev key.
- Stars
- 21
- Language
- JavaScript
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- bugkiwi
- Last verified
- Oct 2026
- Languages
- JavaScript
- Platforms
- Chrome extension
- Capabilities
- Open sourceRuns locallyRequires API key
Highlights
- Only processes X status detail pages; high-confidence hits become a recoverable hidden placeholder, not a deletion.
- The API key lives in chrome.storage.local and is read only by the service worker; requests go to https://api.typesafe.ai/v1/systemone.
- The content script sends only { tweetId, text } (username plus comment body); no cookies, history, logins, or the root tweet are read.
- Fails open on timeouts, 401, 429, 5xx, or unexpected API responses; the default daily TypeSafe request cap is 100,000 with caching and concurrency limits.
- Rules are editable (name, hide and exclude conditions, sensitivity) and the repo ships a labeled comment corpus with benchmark tooling.
Quickstart
bash
npm test
npm run check
npm run packageWatch out
Copy reviewed against the repo README on 2026-10-15; the README is in Chinese with an English translation, and it states no accuracy numbers beyond describing the benchmark tooling. It targets X status pages only, and its tests use deterministic mocks rather than live TypeSafe calls.
Questions about this entry
Short answers drawn from the linked project or page.
A local-first Chrome Manifest V3 extension for X: on status detail pages it hides high-confidence pornographic, sexually suggestive, or solicitation replies behind a recoverable placeholder, using your own TypeSafe Jev API key.
Content scripts send the tweet ID and the combined username-plus-comment text to the service worker, which calls https://api.typesafe.ai/v1/systemone. A configurable threshold plus rules such as the spam-behavior check decide whether a comment gets hidden.
The API key stays in chrome.storage.local and is read only by the service worker; the content script does not read cookies, history, X login data, or the root tweet, and the manifest requests none of tabs, history, cookies, webRequest, or <all_urls>.
Install from the Chrome Web Store link in the README, or build it yourself with Node.js 20+: npm test, npm run check, npm run package, then load the generated dist/ folder via chrome://extensions in developer mode.
Yes. The rule editor lets you change a rule's name, hide conditions, exclude conditions, and sensitivity, and the settings center caps daily TypeSafe requests at 100,000 by default with caching and concurrency controls.
It fails open: unexpected API responses, timeouts, 401, 429, and 5xx responses leave the comment visible rather than hidden. Cached entries key on username context, rule fingerprint, and model hash without storing comment text.
It is built by bugkiwi under the MIT license. Automated tests use deterministic mocks so they never spend API budget, and the repo ships a labeled comment corpus with benchmark tooling for precision, recall, and latency.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: An X timeline labeler that flags engagement bait
X: Unclutter: an ad and slop blocker that runs on Jev
X: A real-time ad blocker that classifies every DOM element
X: Hide posts on X in plain language
More Jev resources like this
An open-source BYOK Chrome extension that applies personal, reversible filters to the X timeline: you choose interests, weights and thresholds, Jev scores eligible post text remotely, and every display decision stays on your device.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
mithrilman/your-signalJavaScript
mithrilman/your-signalJavaScriptA Chrome extension (MV3) that scores every post entering your X timeline with a single Jev call — worth engaging plus selectable tags like spam, buzz, misread and AI-ish, shown as calibrated probabilities in the avatar column, with the goal you pick steering the worth-engaging question.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
ddnim/jev-tweet-radarJavaScript
ddnim/jev-tweet-radarJavaScriptChrome extension that classifies X posts with Jev and blurs chosen expression categories — discrimination, provocation, hatred, calls to attack, cynicism, resignation — behind a translucent overlay you can reveal with one click.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
eijiaraki/toxic-filterJavaScript
eijiaraki/toxic-filterJavaScriptChrome extension that badges X and LinkedIn posts READ / MAYBE / SKIP as they scroll into view, judged by Jev against an interest profile you write in plain English — no keyword lists, no cloud account.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
sahajamit/jev-lensJavaScript
sahajamit/jev-lensJavaScriptA bring-your-own-key Chrome extension that asks Jev one slop/not_slop Choice per X or LinkedIn post as it scrolls into view, then blurs and stamps anything at or above a configurable threshold. Scrolling never blocks, and each post is scored once from a local cache.
Jev Tools & CLIs#community#chrome-extension#moderation
Community
davertor/jev-slop-guardJavaScript
davertor/jev-slop-guardJavaScriptA privacy-first Chrome and Edge extension that dims, collapses, or hides noisy replies, posts, and ads on X using local, reversible keyword and account rules, with an optional Jev second pass for replies no rule matched.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
rokcso/bluenoiseTypeScript
rokcso/bluenoiseTypeScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.