lyrics-kb: Knowledge base of Russian lyrics for generative…

A developer released lyrics-kb, an MIT-licensed Python knowledge base of Russian lyrics for generative songwriting that bundles style canons, anti-AI-slop markers, genre chapters and quality gates. The tool runs on the standard library, reads only the data it is pointed at and sends nothing externally, and ships with navigation-rule regression tests. Its author cautions that the checkers can yield false positives and should be used to flag candidates for rewriting rather than to grade writers.

Most lyrics-kb write-ups stop at the README: here is what the tool does, here is how you run it. This one covers what it refuses to do, and where it breaks. Knowledge base of Russian lyrics for generative songwriting: style canons, anti-AI-slop markers, genre chapters and quality gates. In Russian: База знаний по русским текстам для генеративного songwriting: каноны стиля, анти-AI-слоп маркеры, жанровые главы и качество-гейты. python3 -m unittest scripts/test check navigation.py регрессии правил навигации Python. MIT licensed. Standard library first: the tool reads the data you point it at and sends nothing anywhere. Every rule in a checker like this can produce a false positive. Use it to find candidates for a rewrite, not to grade a writer, and not where the voice is the point. Source, issue tracker and documentation: https://gitlab.com/ameobius-ai/lyrics-kb https://gitlab.com/ameobius-ai/lyrics-kb Other tools from the same author: https://ameobius-ai.gitlab.io https://ameobius-ai.gitlab.io