Writing and content decision

Ulysses

A competent developer can build a useful distraction-free editor with export and blog publishing in about a week, but reproducing Ulysses’ deep Apple integrations, polished native UX, iCloud sync and integrated Apple Intelligence proofreading is not realistic for one person.

Visit website
You pay

$5.99/mo

$72/yr

Read off the official pricing page.

You’d pay instead

$50one-off30 h to build

$20/mo8 h/mo upkeep

On cash alone, building overtakes the subscription at 5 seats.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Ulysses alternatives, with the arithmetic →

What a replacement has to do

  • Open a focused editor -> write/organize sheets in a library -> export or publish to a blog

What it still won’t have

  • Tight Apple platform integrations (Apple Intelligence proofreading)
  • Seamless iCloud sync across Apple devices
  • Polished macOS/iPad/iPhone native UX and long-term maintenance from vendor
  • Automatic App Store updates, family-sharing and volume-licensing infrastructure

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 5 seats.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a cross-device writing app using Electron (macOS desktop) or SwiftUI (preferred for Apple-native) + a lightweight Node.js backend for optional syncing: implement a markdown/ulss-like editor with sheet/chunk model, a library view (projects/groups/filters/keywords), exports to PDF/DOCX/EPUB/HTML with a style/template system, publishing adapters for WordPress/Ghost/Medium via their REST APIs, and a grammar/style check integration using an external NLP API. Out of scope: App Store distribution, family-sharing, and a full CloudKit/iCloud sync implementation (provide simple encrypted user-scoped sync via the Node backend instead). Include error handling for network/API failures, input validation, and automated tests for editor rendering, export output, and publishing flows.
How we checked5 sources · 3/3 runs agreed · evidence score 67

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 5 cited sources+3
  • Price verified on pricing page+3
  • 3/3 assessment runs agreed+4
  • Evidence score67

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 5

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded