User repository on GitHub
Fast English–Icelandic dictionary on Cloudflare Workers: D1 full-text, Vectorize semantic recall and Jev System One re-ranking.
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Ensk
An English–Icelandic dictionary running on Cloudflare Workers: D1 provides full-text lookup, Vectorize adds semantic recall, and Jev System One re-ranks the candidates. The repository has no README, so details come from the GitHub description and list context.
- Stars
- 0
- Language
- TypeScript
- Reading time
- 2 min
- Published by
- Community
- Author
- jokull
- Last verified
- Oct 2026
Works forJev for Ranking
Used inJev for Education
- Languages
- TypeScript
- Platforms
- Cloudflare
- Capabilities
- Open sourceRequires API key
Highlights
- D1 provides full-text lookup, Vectorize adds semantic recall, and Jev System One re-ranks results, per the repository description.
- Runs on Cloudflare Workers; the repo language is TypeScript and the last push was 2026-09-18.
- The author is Jökull Sólberg Auðunsson, listed on madewithjev as the builder behind the project.
Watch out
The repository has no README, so this entry is grounded only on the GitHub description, repo metadata and the madewithjev list context, all read on 2026-10-15. No licence is listed, and no benchmarks, pricing, commands or usage details are available.
Questions about this entry
Short answers drawn from the linked project or page.
A fast English–Icelandic dictionary that runs on Cloudflare Workers. Its GitHub description says D1 handles full-text search, Vectorize does semantic recall and Jev System One re-ranks the results.
As the re-ranking layer: D1 and Vectorize produce candidate results, and Jev System One re-ranks them. The description does not detail the exact questions asked, and there is no README to expand on it.
That is not documented. The repository has no README, so no install, deploy or local development commands could be captured; only the GitHub description and metadata are available.
On Cloudflare, per the description, using its D1 and Vectorize bindings. The repo language is TypeScript.
Jökull Sólberg Auðunsson (jokull on GitHub), listed on madewithjev as the builder behind the project. The repository was created and last pushed on 2026-09-18.
No licence is declared in the captured GitHub metadata, and there is no pricing information. Jev re-ranking would require a TypeSafe key, but that is inferred from the architecture rather than stated in a README.
It layers retrieval: before Jev re-ranks, D1 answers full-text lookups and Vectorize supplies semantic recall, per the description. The specific advantages are not benchmarked anywhere in the captured material, so no accuracy claims are made here.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Search and tagging on keep.md
X: LinkedIn bookmarks search
X: 1,066 reaction videos, searchable
X: Intent-based search in a Chrome extension
More Jev resources like this
Fish-style zsh autosuggestions ranked by Jev instead of prefix matching: as you type, it asks a model which recent command you are most likely retyping and shows the best guess as grey inline text you accept with the right arrow.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
findmalek/guessworkTypeScript
findmalek/guessworkTypeScriptA 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.
Jev Tools & CLIs#community#browser-extension#search
Community
ianTPE/linkscoutJavaScript
ianTPE/linkscoutJavaScriptA Chrome extension that reorders the Gmail message list on screen only - unread first, critical messages on top - using Jev to score each row's urgency and criticality and to answer one boolean question per custom label.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
iamomiid/jev-inboxTypeScript
iamomiid/jev-inboxTypeScriptCtrl+F for questions: an open-source Chrome extension that splits a page into passages, has Jev score them against your question in parallel — 8 passages per request — and jumps to the ones that answer it. Measured at 0.4 to 0.9 seconds and $0.0005 to $0.007 per search.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
eduardoalba00/smart-findJavaScript
eduardoalba00/smart-findJavaScriptObsidian plugin that searches a vault locally and offline with BM25 and no API key, then reranks the top candidates with Jev only after you approve exactly what gets sent. The README reports nDCG@10 rising from 0.53 to 0.88 on 120 queries.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
jh1373/jev-searchJavaScript
jh1373/jev-searchJavaScriptNatural-language lookup over the US App Store top charts: describe an ambiguous feature, a look, or a name and get matching apps with how likely each one is, scored by a single Jev request over a local shortlist.
Jev Tools & CLIs#community#github#appstore
From 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.