Documents and notes decision
Napkin
A competent developer can build a useful Napkin-like capture + suggestion workflow and host it cheaply, but reproducing Napkin's native iOS polish and their claimed EU-hosted, fully encrypted AI stack (and product maturity) is heavier and likely needs more resources.
Visit website↗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.
What a replacement has to do
- Collect short text ideas, store them, surface related topics/ideas using embeddings, and present a daily reflection flow to the user.
What it still won’t have
- Native iOS polish and UX refinements in the shipped Napkin app
- Napkin's claimed EU-hosted encrypted AI stack (if you rely on third‑party APIs)
- Any bespoke AI tuning or internal models Napkin runs on its servers
What remains hard
- Compliance and regulation
Napkin is a small independent company based in Switzerland, all our servers are in Europe. The databases are fully encrypted, all AI layers hosted on our servers.
First-year cost
No published price
Napkin does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
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
Build a minimal Napkin-style service using: React (web) or SwiftUI (iOS) client, Node.js + Express backend, Postgres + pgvector for vector search, and OpenAI (or similar) for embeddings. Core features in scope: (1) capture short text via share/typing and optional voice-to-text, (2) store encrypted idea records in Postgres, (3) compute/store embeddings and serve "related ideas" via nearest-neighbor queries, (4) a Daily Flow endpoint that returns 3 suggested reflection prompts, (5) user export endpoint (JSON). Out of scope: reimplementing a custom LLM, multi-platform mobile store deployment polish, complex import tools. Include error handling, retries for API calls, basic automated tests for backend endpoints, and a README with deployment steps for a single VPS in EU.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Hard moats found in the evidence-3
- Evidence score61
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 · 3
Every page the run actually retrieved.
- official productNapkin | Let your best ideas shape your mind.
- open sourcelaurent22/joplin
- open sourcestreetwriters/notesnook
Integrity checks
What held up, and what did not.
