Skip to content

Jev directory

jev-paste (Jev Paste for macOS)

A macOS menu-bar app that decomposes copied text — agendas, itineraries, bug reports, contact info — into semantic fields and offers an inline Tab hint when you focus a matching input, leaving native paste untouched. Powered by TypeSafe JEF.
Stars
2
Language
Swift
License
MIT
Reading time
3 min
Published by
Community
Author
anson-gzy
Last verified
Oct 2026

Highlights

  • Full clipboard history with time-decay ranking: an exponential half-life model (T-half = 6 h) keeps fresh copies ahead, older relevant history reachable.
  • Retention defaults to 24 hours and is adjustable in Preferences — 1 hour, 12 hours, 3 days, 7 days, 30 days or keep forever — stored in Application Support.
  • Recommendation gating keeps it silent in search bars, browser URL bars, filter fields, password/PIN inputs and untagged generic boxes.
  • Label-matched suggestions: copied Key: value lines from receipts, tickets, exports or OCR fill a field whose label matches the key, in Chinese and English.
  • Menu-bar only (LSUIElement = true) and ships a bilingual Smart Expense Audit Workbench demo in demo/ to test extraction in a real browser DOM.

Watch out

Copy reviewed against the repo README on 2026-10-15, plus the GitHub description and topics. The README was truncated after its highlights list, so build and install steps beyond the macOS 14+, Swift 6 and MIT badges were not inspected, and how JEF credentials are configured is not covered in the captured text.

Questions about this entry

Short answers drawn from the linked project or page.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Copy and paste, with a decision in between

X: A keystroke oracle that reads intent in ~100 ms

X: Voice-controlled computer use on a Mac

X: A Downloads folder that sorts itself

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.

Follow @typesafeai