Open-Source Tool Claims to Remove Several Types of AI Provenance Marks
A GitHub project called watermarks-remover is designed to handle invisible Unicode characters, file metadata, and text-rewriting techniques intended to disrupt statistical watermark signals. Its documentation lists formats including PNG, JPEG, SVG, PDF, DOCX, HTML, and Markdown, and references provenance systems associated with several AI vendors.
The project describes several layers of processing: removing invisible Unicode characters, deleting C2PA, EXIF, and XMP metadata, and rewriting text to try to weaken statistical signals. The repository and multiple social posts support the tool’s existence and its stated scope.
The available evidence does not independently establish how effective the tool is against any particular vendor’s watermarking system. It also does not verify the reported 10,000-star milestone or the timing of related disclosures by Anthropic. Rewriting can alter meaning, style, and readability, so the project’s claims should not be treated as independently demonstrated results.
Source evidence
watermarks-remover/skills/remove-ai-marks/SKILL.md at main · guillaumemeyer/watermarks-remover · GitHubgithub.com · supportingRaw Copy raw file Download raw file Outline Edit and raw actions | | | --- | | name | remove-ai-marks | | description | Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B, always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance, and open-LLM sampling marks. Use when the user asks to strip watermarks, remove C2PA/Content Credentials, clean AI metadata, remove invisible Unicode, anti-detect clean AI output, or runs /remove-ai-marks (aliases: /remove-claude-marks). | # Remove AI marks Multi-vendor anti-detection hygiene for text (Unicode + statistical rewrite) and files (C2PA / AI metadata across common containers). [...] ``` "$WM/clean" " $WM "'Content-Type: application/json' ' '"{\"file\": \"$(base64 < shot.png | tr -d '\n')\", \"name\": \"shot.png\", \ " \" \" \"$(base64 < shot.png | tr -d '\n')$(< | '\n' ' ') \" \"
Guillaume Meyer builds open source AI watermark removerfacebook.com · supportingGuillaume Meyer built an open-source tool that removes several kinds of AI provenance markers from text and supported files.
Someone Just Put an AI Watermark Remover on GitHub What if your ...instagram.com · supportingStrip multi-vendor AI provenance marks: Unicode text hygiene ... GitHub repo link:- https://github.com/guillaumemeyer/watermarks-remover
GitHub - guillaumemeyer/watermarks-remover: Strip multi ...linkedin.com · supportingGitHub - guillaumemeyer/watermarks-remover: Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks,
link: https://github.com/guillaumemeyer/watermarks-removerthreads.com · supportingTech Threads yuqi._.0313's profile picture AI Threads AI浮水印大戰，燒到 OpenAI 和 Gemini 了！ GitHub 開源工具 watermarks-remover 上線 宣稱能清理 Claude／Gemini SynthID／OpenAI 三大廠的隱形浮水印痕跡 一次性拆解：不可見Unicode字元、C2PA元資料、統計採樣訊號 2 3 1 Log in to see more replies. Log in Log in or sign up for ThreadsSee what people are talking about and join the conversation.Log in with username instead [...] # Thread 1.6K views aeejazkhan's profile picture aeejazkhan SOMEONE JUST BUILT AN OPEN-SOURCE AI WATERMARK REMOVER and it now supports Claude, Gemini, and OpenAI provenance marks 224 31 29 62 aeejazkhan's profile picture aeejazkhan ·Author > it strips invisible Unicode characters and other hidden text markers > it removes C2PA, EXIF, XMP, and document metadata from supported files > for statistical text watermarks, it can rewrite the text to try to disrupt the signal > it works across formats like PNG, JPEG, PDF, DOCX, HTML, and Markdown 1 1 1 aeejazkhan's profile picture aeejazkhan ·Author but t
Postx.com · supportingGitHub - guillaumemeyer/watermarks-remover: Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks,