Genuinely one of the simpler builds here — a browser extension sending a URL to your server, plus an existing readability library doing the hard part of content extraction.
Build it
Effort: an eveningRunning cost: $0/mo to start
Why CanICodeThis says Build it
A browser extension that sends the current page URL to your server is a small, well-documented integration
Extracting readable article text from a messy webpage is a solved problem with existing readability libraries
A saved-articles list with read/unread and tags is ordinary CRUD
The parts that'll cause problems
Content extraction fails gracefully but imperfectly on some sites (paywalls, heavy JS rendering) — expect occasional rough edges
Offline mobile sync and text-to-speech are real additional scope beyond a web-based reader
Full-text search across a large saved-article archive benefits from a proper search index at scale
How I'd build this
frontend
Astro
database
Turso
hosting
Cloudflare Pages
MVP scope
A browser extension to save the current page
Extract readable article text via an existing library
A saved-articles list with read/unread and tags
Postpone to v2
Offline mobile sync
Text-to-speech playback
Full-text search across saved articles
What it actually costs to build
AI agent — with a subscription (Claude Pro/Max, Cursor, etc.)
$0 marginal
AI agent — pay-per-use API, no subscription
$16–$27 one-time
Hosting, once it's running
$0/mo (free tier)
Domain name, if you want your own
~$12/yr
Existing tools solving a similar problem typically run $4.99–$4.99/mo — see how they compare below.
The build prompt
Genuinely one of the simpler builds here:
1. A browser extension that sends the current page URL to your server — a small, well-documented integration.
2. Extract readable article text using an existing readability library (Mozilla's Readability.js) — a solved problem.
3. Store it with read/unread status and tags — ordinary CRUD.
That's a real, complete read-it-later tool. Out of scope: offline mobile sync, real additional platform work beyond a web-based reader, and text-to-speech playback, which needs a separate text-to-speech API integration on top of storage.
