That inspired me — if AI can rewrite a whole language stack that fast, I wanted to try building a programming language from scratch with AI assistance.
I've also been noticing growing global interest in Korean language and culture, and I wondered: what would a programming language look like if every keyword was in Hangul (the Korean writing system)?
Han is the result. It's a statically-typed language written in Rust with a full compiler pipeline (lexer → parser → AST → interpreter + LLVM IR codegen).
It supports arrays, structs with impl blocks, closures, pattern matching, try/catch, file I/O, module imports, a REPL, and a basic LSP server.
This is a side project, not a "you should use this instead of Python" pitch. Feedback on language design, compiler architecture, or the Korean keyword choices is very welcome.
Rather than just translating keywords, it lets you write code that actually uses Korean grammar. For example, "10을 5로 나누고 출력하다" (literally "10 by 5 divide and print") outputs "2".
You might already know this, but there's also a Korean programming language called 'Yaksok'. Here's a 2048 written entirely in Korean: https://github.com/yaksok/yaksok/blob/master/code_examples/2...
I self-taught programming quite early in my life, way before I had a good command of the English language. I've read books in my native language, talked on programming forums in my native language. In the end the "english" in programming languages is just a handful of keywords, and it didn't hinder me one bit that I had no idea "int" stands for "integer".
Of course, I started by writing code like "bool es_primo(int numero)" (in my language), but there's nothing in C that says identifiers must be english, just convention. Standard library and packages nowadays would be a problem, but back then standard library were thin and "strcpy" name is obscure anyway. The real hard part was always learning how to program and design properly.
And for more advanced topics, documentation and learning materials in english only are HUGE problem for ESL, because one has to actually read and understand them. But this is not something programming language can help with.
Also, in most languages you already can name variables/classes/members in any Unicode letters. So only "if/for/while" keywords and stdlib classes remain English. It makes little sense to translate those.
Learning the Korean alphabet (Hangul) can be done quite quickly, it's only about as many "letters" as the English alphabet!
Remembering the words is a bit more difficult though, especially if you don't know a similar language. Have been using Anki and my own app for that: https://game.tolearnkorean.com/
# def two_sum(arr: list[int], target: int) -> list[int]:
펀크 투섬(아래이: 목록[정수], 타개트: 정수) -> 목록[정수]:
# n = len(arr)
ㄴ = 길이(아래이)
# start, end = 0, n - 1
시작, 끝 = 0, ㄴ - 1
# while start < end:
동안 시작 < 끝:
I hear that information processing speed is nearly the same across all languages though regardless of density, so in terms of processing speed, may not make much difference.
One distinction though: Han uses actual Korean words, not transliterations. 함수 means "function" in Korean, 만약 means "if" — they're real words Korean speakers already know.
Your example uses transliterations like 펀크 and 아래이 which would look odd to a Korean reader. That difference matters for readability.
It never really took off. I think because computers already require users to read and type Latin letters in lots of other situations, and it's not that hard to learn what a few keywords mean, so you might as well stick with the English keywords everyone else is using.
There's probably a lot of reasons why non English programmers stick with English keywords, beyond just language/tooling support. Learning new keywords is already part of learning a programming language, and much of the documentation and resources available for languages and libraries are only in English. ASCII-only strings are still ubiquitous in software, like URLs and usernames. And in international teams, English is the go-to lingua franca.
Could this change with LLMs? Maybe, but most code in its training data is in English, so LLMs likely work most effectively in English.
It’s fun to look at your code samples, have absolutely no clue what any of it means, and think about just how many non-English-speaking programmers must have felt that way looking at our all-English programming languages.
Except lisp: that’s just inscrutable symbols like cond and cons and car and cadr and a bunch of parens! :-)
That said, a few things do lean into Korean specifically:
- Method names are real Korean verbs: .추가() (add), .삭제() (delete), .분리() (split)
- Error messages are in Korean
- The REPL prompt is 한> and exit command is 나가기 (literally "go out")
Good question — it pushed me to think about what makes this more than just s/function/함수/g.
https://github.com/farant/rhubarb/blob/main/include/latina.h
edit: oh, maybe you can’t do full unicode. that’s too bad!
Error messages, REPL, LSP hover docs are all in Korean. You can't get that from #define 만약 if.
anecdotally it is also interesting to use with ai because apparently it is "harder to be on autopilot" based on a huge pre-existing corpus of code when you write it in a different language. could activate different reasoning regions somehow.
(i just appreciate what can be trivially accomplished in c even if it's kind of janky after spending way too much time in the JS preprocessor mines...)
I actually tested this with GPT-4o's tokenizer, and the result was the opposite — Korean keywords average 2-3 tokens vs 1 for English. A fibonacci program in Han takes 88 tokens vs 54 in Python.
The reason comes down to how LLM tokenizers work. They use BPE (Byte Pair Encoding), which starts with raw bytes and repeatedly merges the most frequent pairs into single tokens. Since training data is predominantly English, words like `function` and `return` appear billions of times and get merged into single tokens.
Korean text appears far less frequently, so the tokenizer doesn't learn to merge Hangul syllables — it falls back to splitting each character into 2-3 byte-level tokens instead.
It's a tokenizer training bias, not a property of Hangul itself. If a tokenizer were trained on a Korean-heavy corpus, `함수` could absolutely become a single token too.
So no efficiency benefit today. But it was a fun exploration, and Korean speakers can read the code like natural language. It could also be a fun way for people learning Korean to practice reading Hangul in a different context — every keyword is a real Korean word with meaning.
For Korean readers the character systems look quite different, but I can see how it's hard to parse visually without familiarity.
As you said, syntax highlighting helps a lot — there's a colored screenshot at the top of the README showing how it looks in practice.
I have similar idea to train LLM in Serbian, create even new encoding https://github.com/topce/YUTF-8 inspired by YUSCII. Did not have time and money ;-) Great that you succeed. Idea if train in Serbian text encoded in YUTF-8 (not UTF-8) it will have less token when prompt in Serbian then English, also Serbian Cyrillic characters are 1 byte in YUTF-8 instead of 2 in UTF.Serbian language is phonetic we never ask how you spell it.Have Latin and Cyrillic letters.
Even without retraining BPE from scratch, starting with YUTF-8 and measuring how existing tokenizers handle it would already be a worthwhile experiment.
Hope you find the time to build it, good luck!
The main benefit of Korean actually comes from the fact that the language itself fits perfectly into a standard 27 alphabet keys and laid out in such a way that lets you type ridiculously fast. The consonant letters are always situated in the left half and the vowels are in the right half of the keyboard. This means it is extremely easy to train muscle memory because you’re mostly alternating keystrokes on your left hand and right hand.
Anecdotally I feel like when I’m typing in English, each half of my brain needs to coordinate more compared to when I’m typing in Korean, the right brain only need to remember the consonant positions for my left hand and my left brain only need to remember the vowel positions.
What you talked is mostly right and I did not know about typing in Korean, the left-hand side and right-hand side. Btw, Consonant(Jaeum) and vowel(Moeum).
In experience-wise, what you had would be precise.
Perhaps look to APL for efficient ways to represent math concepts/structures?
Korean has its own pure Korean words (순우리말) as its foundation, and borrowed some Chinese-origin vocabulary on top of that.
Hangul was specifically created so people wouldn't need to learn Chinese characters.
So Han's keywords use native Korean words where possible — it fits the spirit of Hangul itself.
If X then Y, sure. While X, do Y? Maybe. For X equals Y, X equals Z, X is incremented, do A? Hardly. Match X case Y1 Z1 case Y2 Z2? Definitely not
Native English speakers have a small leg up understanding the vocabulary, not the syntax.
Amazing though!
This seems like a reasonably good security measure too