Learning and careers decision
Onigiri Anki
A capable developer can reproduce the core AI-powered SRS flashcard features (cards, AI generation, scheduler, storage) using existing open-source prior art, but the paid product's added value—live native lessons and community—would not be replaced by a small self-hosted project.
Visit website↗$14.9/mo
$179/yr
Read off the official pricing page.
$100one-off90 h to build
$20/mo3 h/mo upkeep
On cash alone, building overtakes the subscription at 2 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User creates/inputs words or sentences → AI generates Japanese translation, furigana, example sentence and pronunciation → store card in DB with SRS schedule → user reviews due cards and records accuracy → SRS updates schedule
What it still won’t have
- Access to native monthly 1-on-1 lessons and teacher feedback
- Access to the vendor's Slack community and any community support
- Polish and UX conveniences of the hosted product (onboarding, payments, analytics)
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 2 seats.
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 self-hosted web app (Next.js + TypeScript frontend, Node.js API, PostgreSQL database, hosted on Vercel/Render and Supabase or Railway for Postgres) that provides AI-assisted Japanese flashcards. Core features in scope: user signup/login and subscription flag; card creation UI that sends English input to an LLM (OpenAI-compatible) to return Japanese translation, furigana, romaji, and an example sentence; persist cards and review history in Postgres; implement a spaced-repetition scheduler (SM-2 or simplified algorithm) to queue due cards; review UI to present cards, capture user accuracy, and update scheduling; TTS playback using a cloud TTS API; payment stub or simple Stripe integration for subscription gating. Out of scope: live 1-on-1 lessons, managed Slack community, advanced analytics. Require: retry and error handling for API calls, input validation, migrations, integration tests for scheduler logic, and end-to-end tests for card creation and review flows.
How we checked
How the score was reached
- Partly verdict base52
- 3 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score62
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 productOnigiri Anki | Anki Japanese - AI-Powered Japanese Learning Flashcards
- official pricingOnigiri Anki — Pricing section
- official pricingOnigiri Anki — Pricing section (Standard)
Integrity checks
What held up, and what did not.
