Should you build your own Recall?
Save user-provided sources, summarize them, and build a linked personal knowledge graph
The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Recall, save user-provided sources, summarize them, and build a linked personal knowledge graph. The hard boundary is hosted extraction, model routing, browser capture, sync, and knowledge-graph polish, plus capture polish, sync, and content partnerships.
ENOriginal research content in English. Original prompt preserved in English.
Build a personal replacement for Recall in an empty repository.
Use Next.js 15, TypeScript, SQLite, Drizzle ORM, Readability.js, and a local background worker; do not offer alternative stacks.
The core loop is: save user-provided sources, extract readable text, summarize them, build a linked personal knowledge graph, and export the archive in open formats.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Support manual URL save, RSS or Atom subscriptions, OPML import, and a simple bookmarklet.
Fetch politely with a clear user agent, rate limits, conditional requests, and robots-aware behavior.
Extract title, author, date, canonical URL, readable HTML, and selected images.
Provide inbox, unread, archive, favorites, tags, highlights, notes, and full-text search.
Keep the original URL prominent and never attempt to bypass authentication or paywalls.
Export OPML, bookmarks HTML, Markdown, and a complete JSON backup.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out paywall circumvention.
Deliberately leave out licensed publisher content and recommendation networks.
Deliberately leave out native mobile clients and seamless commercial sync.
Finish by running the tests and listing the exact commands used.The prompt opens pre-filled in your agent. Review it before running. · this prompt is generated from the build plan · improve it via PR
What would building your own look like?
Save user-provided sources, extract readable text, summarize them, build a linked personal knowledge graph, and export the archive in open formats.
What you will need
- Node.js 22
- local disk
- optional browser bookmarklet
- user-supplied RSS feeds
People still pay for Recall because people pay when capture works everywhere, reading state syncs instantly, and the archive remains clean without constant parser repairs. The recurring cost buys feed quirks, parsing, paywalls, canonical URLs, deduplication, images, search, sync, browser extensions, and publisher changes, not just the visible interface.
xhosted extraction, model routing, browser capture, sync, and knowledge-graph polish
xpublisher bypasses
xcross-device mobile capture
xhigh-quality recommendation graph
xlicensed full-text feeds
Prefer something ready-made?
AtomicSaved sources become summaries and a linked semantic graph; bring your own model.Open source↗License, setup, and limitations for each alternative.
How much does Recall cost?
- Monthly billing
- $10/mo$10/mo
- Per year
- $120/yr$120/yr
- On a Brazilian card, with 3.5% IOF
- R$52.26/moR$627/yr
Saved to My list. You will see a notice on this site when the price changes.
You complete the purchase on Recall’s site. Vibe Radar does not handle payments.
| Plan | Monthly | Annual (per month) | What is included |
|---|---|---|---|
| free | $0 | $0 | 10 AI summaries/month and unlimited saved content; API and MCP access included. |
| plus | - | $10≈ $10 | Unlimited AI summaries under fair use; import up to 1,000 bookmarks or 10,000 Markdown notes. |
| max | - | $38≈ $38 | Unlimited summaries under fair use; bulk actions on up to 100 items and model choice. |
Free tier10 AI summaries per month; unlimited saved content.
Billing termsannual prices published with 20% savings; monthly selector exists but current monthly amounts were not independently recoverable; 30-day refund
Additional costsPaid 'unlimited' summaries remain subject to fair use and can be paused, reviewed or adjusted. Student pricing is 20% off where eligibility is accepted.
verified 2026-08-11 · source ↗
Is it cheaper to build or buy Recall?
Adjust the numbers: hours to build, your hourly rate, running costs and the subscription price.
Over 24 months, subscribing is cheaper.
Starting hours estimated from the analysis (one sitting). Does not price what you give up (support, integrations, security).
Is Recall free?
The free plan saves unlimited content but caps AI summaries at 10 a month. The paid plan is Plus at $10/mo (checked 10/20/2026).
Can I rebuild Recall?
Kinda. The core of Recall is buildable in a weekend with the prompt on this page, but there are real gaps: hosted extraction, model routing, browser capture, sync, and knowledge-graph polish, publisher bypasses. Read the honest list above before committing.
How much does Recall cost?
Recall costs about $10/mo (Plus, checked 10/20/2026), which is $120 per year.
What do I lose by replacing Recall?
Honestly: hosted extraction, model routing, browser capture, sync, and knowledge-graph polish; publisher bypasses; cross-device mobile capture; high-quality recommendation graph; licensed full-text feeds. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to Recall?
Yes: Atomic (Saved sources become summaries and a linked semantic graph; bring your own model.) The prompt is for when you want it exactly your way.