Ai Detection Python Packages

aiw-ru

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.

ru-humanizer

humanizer-ru: редактура русского текста для AI-агентов. Убирает канцелярит и шаблонные обороты, сверяет смысл и факты. 67 признаков, 21 жёсткий запрет, сканер, CLI, MCP и расширение Chrome. | Russian text editing for AI agents: removes bureaucratese and template phrasing, checks facts.

raidxai

Official TypeScript and Python SDKs for the Raid AI detection API

aidetect

Local, offline AI-writing detector — scores your own drafts paragraph-by-paragraph before a teacher runs Turnitin

fetchit-engine

Deterministic text cleanup and AI writing tells. Strips invisible Unicode and look-alike spaces, turns em dashes into commas, then flags wording that reads as AI written. Zero dependencies, identical results in JavaScript and Python, and your users' text never leaves your process.

pystylometry

Comprehensive Python toolkit for stylometry

c2pa-scanner

Scan website sitemaps for AI-generated images via C2PA and EXIF/XMP provenance - an EU AI Act Art. 50 labeling helper (Python/Textual TUI).

encypher-ai

Metadata encoding and extraction for AI-generated content

aegis-integrity

Free, local-first academic integrity checker and MCP server: citation hallucination detection, AI-text and plagiarism signals, venue guideline checks (IEEE, ACM, Elsevier). Documents never leave your machine.

lmscan

🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline.

humanizer-pro

Finds the habits that make text read as machine-written, removes them, and checks that every fact survived. Local, no API key.

unslop

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

bonafide

A calibrated, provenance-first framework for detecting AI-generated media — honest about what it knows and what it doesn't.

prnu

A Python library for Photo-Response Non-Uniformity (PRNU) noise extraction, camera identification through fingerprint correlation and a ResNet-18-based AI image detector.

unslopify

Audit and rewrite text to remove AI-writing patterns. Deterministic audit core, phrase bank, and an agent skill for the rewrite loop.

is-it-ai-mcp

MCP server that reads C2PA Content Credentials: what an image declares about its own origin, and whether that declaration still verifies

aiornot

AIOrNot API Python client

styleprofile

Build a stylometric profile from a writer's texts, see how far a draft drifts from it, and learn which habits separate that writer from LLM output.

defluff

Deterministic slop detector for AI-generated prose. No model, no API key.

gaige

Calibration and drift receipts for AI measurement: your corpus, your thresholds, honest error bars, and proof the instrument has not changed.

llm-detector

Research implementation for transparent probabilistic classification of human-written and LLM-generated text.

hiddenink

Find the ink you can't see. Inspects and cleans invisible Unicode, homoglyphs, and container metadata — deciding per occurrence whether a codepoint is a hidden mark or real content. Zero dependencies.

ai-provenance-tracker

Open-source multimodal AI provenance detection platform with explainable evidence cards, provider consensus, and benchmark-driven quality gates.

watermark-remover

Find and remove AI provenance signals from files you own: hidden Unicode, token watermarks, visible image marks, and C2PA/EXIF/XMP metadata. Zero-dependency Python 3.10+ core; models, GPUs, and system binaries sit behind opt-in adapters.