I made an App for learning Japanese, and it won in Vercel's OSS program
Monkeytype-inspired Japanese learning UI with Vercel sponsorship, 1.8k GitHub stars.
Aesthetic, minimalist platform for learning Japanese inspired by Duolingo and Monkeytype, built with Next.js and sponsored by Vercel. Beginner-friendly with plenty of good first issues - all contributions are welcome!
Monkeytype-style customization for kana practice, but WaniKani already owns this space.
Japanese language learners, typing enthusiasts
Duolingo · WaniKani · Bunpro
Here's the main selling point: I added a gazillion different color themes, fonts and other crazy customization options, inspired directly by Monkeytype. Also, I made the app resemble Duolingo, as that's what I'm using to learn Japanese at the moment and it's what a lot of language learners are already familiar with.
Miraculously, people loved the idea, and the project even managed to somehow hit 1k stars on GitHub now. Now, I'm looking to continue working on the project to see where I can take it next.
Back in January, I even applied to Vercel's open-source software sponsorship program as a joke. I didn't seriously expect to win, and did it more out of curiosity.
Lo and behold, yesterday I woke up to an email saying the app has been accepted into Vercel's Winter cohort. Crazy!
Anyway. Why am I doing all this?
Because I'm a filthy weeb.
どうもありがとうございます
Monkeytype-inspired Japanese learning UI with Vercel sponsorship, 1.8k GitHub stars.
SRS flashcards plus AI chat practice, but Wanikani and Bunpro already dominate this space.
Topic-based conversation generator when Talkpal and Lingodeer already do this.
Yoga framing for prompt templates, but the techniques themselves aren't new.
Prerequisite graph + spaced repetition schedules LeetCode problems, but Codeforces already does adaptive difficulty.
The visual concept is strong: generous negative space, a micro-typographic centerline and restrained UI that actually sells the idea of 'ma'. Unfortunately the page reads like a demo/theme — repeated copy blocks and zeroed stats suggest placeholder content rather than a finished system or component library. Useful as a quiet starting point for designers who like minimalism, but it needs real docs, components and examples to move beyond a pretty landing.