User repository on GitHub
Scores search-result links before you click: browser extension + Cloudflare Worker + Jev
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Tools & CLIs
LinkScout
A browser extension plus Cloudflare Worker that scores search results before you click: Jev answers six questions per page (relevance, depth, SEO filler, sales page, page type, key passage) and code combines them into a 0-100 badge that re-ranks Google, Bing, DuckDuckGo and 104.com.tw.
- Stars
- 0
- Language
- JavaScript
- License
- MIT
- Published by
- Community
- Last verified
- Oct 2026
About this project
Scores the links on a search results page before you click them. npm run env:sync regenerates worker/.dev.vars on its own. Only the keys listed in worker/.dev.vars.example are copied; to sync a new key, add it there. CFAPITOKEN needs the Browser Rendering - Edit permission. JINAAPIKEY is optional: without it the Jina fallback still works, just with a lower rate limit.
Quoted from the project's README. Read the full README.
- Languages
- JavaScriptTypeScript
- Platforms
- Chrome extensionCloudflareBrowser
- Capabilities
- Open sourceSelf-hostedRequires API key
Highlights
- One systemOne request asks relevance, depth, SEO filler, sales page, page type and key passage for each result.
- The 0-100 badge is computed in code: (0.65*relevance + 0.35*depth) * (1 - 0.7*seo) * (1 - 0.5*sales*(1-transactional)).
- Worker caches results for 24 hours per (query, url) and fetches pages via Cloudflare Browser Run with a Jina Reader fallback.
- Fast mode fetches pages in the browser (0.06-0.4 s on 10 articles) and asks Jev in about 0.25 s, versus 3-30 s for server fetchers.
- Monitoring mode scores client exposure and tone for PR reports; 104.com.tw jobs are scored against a free-text seeker profile.
Watch out
MIT-licensed but needs Cloudflare, TypeSafe and optionally Jina keys, plus a random production token protecting the public workers.dev URL. Most of the code was written with Claude Code.
Questions about this entry
Short answers drawn from the linked project or page.
Yes. Each result page is fetched and cleaned to Markdown, then judged by six Jev questions in one request. Fast mode fetches pages in the browser without cookies, and pages under 300 characters fall back to the Worker's fetchers.
Yes. With reordering enabled, results are sorted by the 0-100 score, and on Google, Bing, DuckDuckGo and 104.com.tw a side panel lists every scored result best first. On 104.com.tw the panel is the only ranking because its job list is virtual.
Put CF_ACCOUNT_ID, CF_API_TOKEN (or CF_API_KEY) and TYPESAFE_API_KEY in the root .env, plus JINA_API_KEY if you want a higher Jina fallback rate limit. CF_API_TOKEN needs the Browser Rendering - Edit permission, and npm run dev syncs .env into worker/.dev.vars first.
Open chrome://extensions, enable Developer mode, choose Load unpacked and select the extension/ directory. It defaults to localhost:8787 with the token dev-token, both changeable on the options page. The interface follows the browser language or a manually set English or Traditional Chinese.
Set LINKSCOUT_TOKEN to a random value like `openssl rand -hex 32`, not dev-token, because the workers.dev URL is public and that token is all that stops strangers spending your Browser Run, Jev and Jina quota. Deploy with npx wrangler deploy and npx wrangler secret bulk secrets.json, then delete secrets.json.
Jev answers six questions per page, and the total is computed in code as (0.65 * relevance + 0.35 * depth) * (1 - 0.7 * seo) * (1 - 0.5 * sales * (1 - transactional)). Because the weighting is code, changing it does not require running the model again.
Fast mode is an options-page switch that asks for Chrome's optional read-all-sites permission; the extension fetches each result page itself without cookies and extracts the article from JSON-LD articleBody or vendored Mozilla Readability, then the Worker only asks Jev. Pages yielding under 300 characters fall back to the Worker's Browser Run and Jina fetchers.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Search and tagging on keep.md
X: Natural-language search over Zillow
X: Filtering WIP todos by meaning
X: Seven more SEO and GEO workflows
More Jev resources like this
3GitHub stars
A 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-guardJavaScript1GitHub stars
A lightweight Chrome extension that scores selected webpage text for how strongly it resembles AI-generated writing, using Jev inline in the browser after a right-click or Cmd/Ctrl+Shift+Y. It aims to give readers an uncertainty-aware signal without interrupting reading.
Jev Tools & CLIs#community#chrome-extension#ai-detection
0GitHub stars
A dependency-free JavaScript library that maps uploaded CSV columns onto your destination schema: a strict normalized-name pass first, then one Jev boolean per remaining source-destination pair plus a guard question per column, leaving uncertain fields visible instead of guessed.
Jev Tools & CLIs#community#csv#data-import
203GitHub stars
Native DeepSeek Harness (DSH) plugin that uses Jev or Luna Decisions as a System One judgment layer across 12 separately configurable features: skill selection, file ranking, drift reminders, completion checks, goal supervision, corrections, log admission and workspace approvals. All features ship disabled by default.
Jev Tools & CLIs#community#deepseek#plugin
4GitHub stars
Chrome MV3 extension that groups every tab in a window into named, colored groups from one parallel Jev call - one Choice question per tab against user-edited criteria, with a fixed fallback bucket, manual groups untouched, and the original tab order restored on ungroup.
Jev Tools & CLIs#community#chrome-extension#tab-management
Community
AstonyCat/jev-tab-grouperJavaScript
AstonyCat/jev-tab-grouperJavaScript2GitHub stars
MIT-licensed Chrome extension that asks Jev whether the page, video or post you are on serves your written goals -- a category Choice, a goals Noul and a 0-4 waste-of-time Score -- then blocks or blurs in code, tightening thresholds at 2, 10 and 20 minutes of engaged time.
Jev Integrations & Adapters#community#chrome-extension#digital-wellbeing
Community
plusminushalf/rot-guardJavaScript
plusminushalf/rot-guardJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.
Jev Tools & CLIs#gateway#vercel#cloudflare
Read article
Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.
Jev Tools & CLIs#open-models#local#onnx
Read article
Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.
Jev Tools & CLIs#classification#email#security
Read article
From the Jev community
Posts from builders shipping with Jev right now.