stylometry

Beautiful visualizations of how language differs among document types.

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

AI-writing humanizer for KO/EN/ZH/JA

The Java Graphical Authorship Attribution Program

A local, zero-dependency prose, copywriting, UI-text, and code-comment linter that flags stiff, AI-sounding writing (stock phrases, flat sentence rhythm, repeated wording) and tells you what to revise. Includes 8 language packs. A style checker, not an AI detector.

Collected solutions from Google Code Jam programming competition (2008-2021).

AI humanizer skill for Claude Code, Codex and Cursor. Removes AI slop and the signs of AI writing, then measures the rewrite against human baselines.

Stylometry library for Burrows' Delta method

Ghost Writer — AI Content Engine with 40-point QA, 18 platform formatters, and triple-detector validation. Built on Ghost Protocol. Passes GPTZero, Pangram, and Originality.ai.

Скилл для ИИ-агентов и CLI на Python/uv: находит и убирает ИИ-стиль в русских текстах (канцелярит, кальки, штампы), проверяет сохранность правки и оценивает текст по фрагментам в духе «Антиплагиата» с калибровкой по вашим отчётам. Русская адаптация avoid-ai-writing.

Stylometric Data Mining Library with a focus on identifying Satoshi Nakamoto as a case study.

Data and code for Kang et al., EMNLP 2019's paper titled "(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas"

Supervised Stylometry

Interpretable stylometric profiling + author-style transfer built on explicit and LLM-genenated JSON fingerprints and local measurements. Fingerprint your corpus, inspect/visualize signals, then LLM-generate stylistically similar text with meaning preserved, deterministic post-processing, normalization controls, and deviation reports. CLI + API.

Measures how you write and builds a voice profile, then enforces it with a deterministic checker: em dashes, filler, hedges, and AI tells are caught by code, not by asking the model to be careful. Multiple named voices, eval harness with golden tests, no dependencies.

Source code embeddings for various programming languages

Measure how closely writing matches a learned author's style. Japanese & English, local-first CLI for LLMs and humans.

Python package to deal with PAN corpora and extract stylometric features from text documents.

Repository for author masking

A command-line tool for masking authorship of text, by changing the writing style with a Large Language Model.