User repository on GitHub
AI text detection with Jev in browser
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
SniffSlop
A browser extension that classifies web text with Jev: hover, pin, drag or double-click to judge blocks or whole articles as slop, or define your own questions. No build step; the key stays in storage.local and only api.typesafe.ai is reachable.
- Stars
- 1
- Language
- JavaScript
- Reading time
- 3 min
- Published by
- Community
- Author
- kmcheung12
- Last verified
- Oct 2026
- Languages
- JavaScript
- Platforms
- Chrome extensionBrowser
- Capabilities
- Open sourceRequires API key
Highlights
- Hover a block of 25+ words to judge it; click to pin blocks, drag across a range, or double-click for the whole article as reader mode would see it.
- The outline runs grey in flight, then green to amber to red: hue is the answer and saturation the certainty, computed from the probability distribution.
- A score or noul question maps onto the outline scale; if every configured question is a choice, the outline stays neutral blue and the card carries the detail.
- The API key lives in storage.local, is read only by the background script, and the extension's sole host permission is api.typesafe.ai.
- Selections are judged as one document with visible trimming past the maximum, and results are cached per page by text hash until reload.
Watch out
Copy reviewed against the truncated README on 2026-10-15; the excerpt ends mid-sentence in the caching section, so details after that point are not covered. GitHub metadata lists no license, and the madewithjev listing credits the build to 'a_c' while the repository sits under kmcheung12.
Questions about this entry
Short answers drawn from the linked project or page.
A browser extension that classifies text with Jev. Hover a paragraph, pin blocks, drag across a range, or double-click a whole article to learn how likely it is written by AI, or define your own questions for Jev to answer.
There is no build step — load the folder as-is. In Chrome, open chrome://extensions, enable Developer mode, and pick the folder with Load unpacked. In Firefox, use about:debugging#/runtime/this-firefox and Load Temporary Add-on.
Get a key at console.typesafe.ai/keys, then paste it in the extension by clicking the toolbar icon and hitting Save. It is stored with storage.local — this machine and browser profile only, not browser-synced — and is read only by the background script.
The only host it can reach is api.typesafe.ai, its sole host_permissions entry. The README says nothing is collected: no telemetry, no analytics, no server belonging to the extension, and the content script never sees the key.
The outline is grey while a request is in flight, then green, amber or red. Hue is the answer and saturation is the certainty, computed from the probability distribution; noul certainty is derived from the distance to 0.5. Choice-only questions leave the outline neutral blue.
Click pins blocks, drag selects a range, and double-click grabs the whole article as reader mode would see it; a selection is scored as one document, and the card reports coverage like 4 blocks · 310 words. Esc drops the selection or disarms.
Firefox temporary add-ons are cleared when the browser restarts — a permanent install needs a signed build. Text past the maximum is trimmed rather than refused, and results are cached per page by text hash until reload.
More Jev resources like this
A Chrome extension that hides posts you do not want on your X timeline: tap noise bubbles or type rules in plain words, and Jev judges each tweet one-shot before it scrolls into view. Good hide and Shouldn't have hidden answers stay local as an eval set.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
icpmacdo/signal-and-noiseHTML
icpmacdo/signal-and-noiseHTMLA Manifest V3 Chrome extension that sends each LinkedIn feed post's text to TypeSafe's Jev with a rubric of narrow yes/no and 0–2 questions, then blurs only the posts that plain code marks as filter — uncertain and failed checks stay visible, with one-click reveal.
Jev Tools & CLIs#community#catalog-import#madewithjev
A local app that reads a few lines of notes about your product and lets Jev pick its way to a finished landing page: Jev never writes text, it only chooses between options, and code builds the page from those picks.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
sagapranav/jev-pagesHTML
sagapranav/jev-pagesHTMLChrome 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-filterJavaScriptA Chrome extension that files bookmarks by rules you write: you define categories and what each means in natural language, Jev applies them as one typed Choice per page, and the extension performs deterministic bookmark moves.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
acorn181/semantic-bookmarkTypeScript
acorn181/semantic-bookmarkTypeScriptAI Gmail organizer for Chrome and Brave: it classifies every email with TypeSafe's Jev, auto-labels the inbox, and bulk-cleans junk with preview and undo. Uses your own OpenRouter or TypeSafe key, with no server involved.
Jev Tools & CLIs#community#github#gmail
Community
KirtanUgreja/jev-mailJavaScript
KirtanUgreja/jev-mailJavaScriptFrom 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.