[verdict][generated prompt][source: readwise.io]
Can I vibecode Readwise Reader?
// buildable in a weekend, but real gaps stay open
Saving articles and highlighting is easy; reliable extraction, mobile/offline reading, sync, Kindle/import integrations, RSS/PDF support, and review loops are real work.
confidence: high
what it is: Read-it-later app with highlights, RSS, PDFs, and spaced review
Buildability index · an editorial game
- Price 12.99 $/month weight: plus 2
- Time multi-day weight: plus 1
- Category read it later no weight
- Moat integrations · execution quality · switching costs weight: minus 3
- Confidence high weight: plus 1
- What you lose 6 items weight: minus 3
- Site readwise.io (si apre in una nuova scheda) no weight
The moat outweighs the price: rebuilding this is a project, not an evening.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Build a browser save endpoint, article extractor, reader view, highlights table, export to Markdown, and review emails.
what you need
- hosted app
- browser extension or share sheet
- parser/extractor
- database
- email or notification service
- optional OCR/PDF tools
Useful because DIY covers 60% quickly but power users pay for the ingestion web.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a personal read-it-later app to replace Readwise Reader. Requirements:
- A self-hosted web app (VPS or localhost): Node + Express + better-sqlite3, server-
rendered with one clean reading column.
- Save via a bookmarklet POSTing the URL; extract with @mozilla/readability + jsdom and
store title, author, site, word count, and cleaned HTML. When extraction fails, keep
the bare link with a 'source only' badge instead of mangling it.
- Reading view: the cleaned article, estimated read time, and select-to-highlight (a
little vanilla JS; store the highlight with surrounding context).
- Library: Inbox, Archive, and per-tag lists; keyboard j/k to move, Enter to open, e to
archive.
- A highlights page grouped by article, plus a nightly node-cron export of all
highlights to ~/highlights/YYYY-MM-DD.md so they outlive the app.
- A daily review email with 5 random old highlights via Resend or SMTP (creds in .env).
- Full-text search over articles and highlights with SQLite FTS5.
- No accounts, no telemetry; if hosted, put it behind basic auth and HTTPS.
- Out of scope: RSS ingestion, PDF/epub parsing, Kindle sync, and mobile apps. The
browser is the reader.
- README: bookmarklet install and SMTP setup.Prompt generated from the data on this page, not reviewed by hand yet. In English on purpose — it is the language coding agents work best in.
What you lose
- excellent parsing
- mobile/offline apps
- Kindle integrations
- RSS/PDF workflows
- spaced repetition
- exports
Why people still pay
They pay because all reading inputs flow into one durable highlight system.
moat: Integrations Execution quality Switching costs what a moat is
capture/sync/integrations
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- wallabag (opens in a new tab) — Open-source read-it-later app with article extraction and self-hosted reading workflows. (alive)
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
