A repository that defines a profanity-rich Russian language style for concise technical communication, claiming to save root words while maintaining accuracy.

Stars

754

7-day growth

+208

Forks

14

Open issues

4

License

MIT

Last updated

2026-07-22

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It creatively combines Russian profanity with engineering precision, offering a benchmark showing ~96% root economy and a plugin for AI assistants like Claude Code and Cursor.

Who it is for

  • Russian-speaking developers
  • DevOps and incident responders
  • Tech humor enthusiasts
  • Users of Claude Code, Cursor, or similar AI coding tools

Use cases

  • Expressing technical issues concisely in Russian
  • Code reviews and pull request comments
  • Incident reports and project status updates
  • Adding personality to technical documentation

Strengths

  • Demonstrated root economy of ~96% in benchmark
  • Comprehensive dictionary of 70+ idioms with engineering mapping
  • Graded severity scale (10 levels) for accurate emotional calibration
  • Plugin integration for multiple AI coding assistants

Considerations

  • Heavy profanity limits adoption in professional environments
  • Russian language only, not useful for non-Russian speakers
  • Novelty may not improve actual communication clarity for all teams

README quick start

ПОХУЙ

Зачем весь словарь, когда есть четыре корня

Та же точность, но быстрее. С первого слова понятно, работает оно — или наебнулось.

18+ · мат идиоматический, прикладной, народный. · вдохновлено caveman


Русский мат — генеративная морфология: четыре корня плюс приставки и суффиксы лучше чем Caveman. Caveman экономит слова. Похуй экономит корни. Одно «наебнулось» — это "the service has unexpectedly crashed and requires investigation", только сразу ясно.

До / После

🗣️ Обычный агент 🚬 Похуй

The deployment failed because the DATABASE_URL environment variable is empty, which caused the database connection to be refused. I recommend checking your environment configuration.

Деплой наебнулся: DATABASE_URL пустой. Хуйня вопрос, чиню.

The rebase completed remarkably smoothly — all forty commits applied cleanly without a single merge conflict.

Ребейз вошёл как слива в жопу: сорок коммитов, ни одного конфликта.

The test suite failed again on the third retry. This appears to be an intermittent timing issue rather than a genuine regression. I suggest investigating the flaky test.

Опять этот блядский тест на таймауте лёг. Третий раз за день, заебал. Что за еблан sleep(2) захардкодил. Чиню.

I noticed the project includes left-pad as a dependency. Given that this functionality can be implemented in three lines, we might consider removing it.

На кой хуй тут left-pad? Три строчки же. Снёс.

Interestingly, the race condition no longer reproduces after adding the logging statements. This is a classic heisenbug situation and will require further investigation.

Добавил логи — отъебалось. Хуйня какая-то, хайзенбаг. Гонка где-то в запуле коннектов, копаю.

This module was written in 2014 and contains several patterns that are no longer considered best practice. A careful refactoring would be beneficial, though it carries some risk.

Модуль 2014 года, ёбаный стыд: jQuery, колбэки, глобальный стейт. Перехуячить бы, но один хуй работает — не трогаю.

We are experiencing a critical production incident. The primary database is not responding, and the replicas have fallen significantly behind.

Полный пиздец: мастер лёг, реплики отстали на час. Поднимаю из бэкапа, потери — минут двадцать ебли.

One small suggestion: consider renaming this variable for

Description

Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
xuchonglang
Featured
xuchonglang GitHub avatar

investing-for-beginners

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

Blockchain & Web3
2,739
Krishnagangwal
Featured
Krishnagangwal GitHub avatar

CS-Fundamentals

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.

Data & DatabasesDatabases & Storage
2,326