ai-text-watermark-audit is an MIT-licensed Python package for auditing invisible Unicode signals and evaluating claims about AI-generated text watermarks. It runs locally and is intended for developers and researchers performing text forensics.
In the Other dev tools space, ai-text-watermark-audit takes a focused approach. It focuses on determining whether text contains invisible Unicode signals or credible AI text watermark indicators. It is built as an open-source project for developers and AI researchers. ai-text-watermark-audit is open source under the MIT license. It runs on the command line, and it can be self-hosted.
ai-text-watermark-audit first shipped in 2026. Among its 5 catalogued features are unicode signal auditing, watermark claim analysis, and text forensics.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do