Paste any text and see every trace a chat interface left in it: hidden HTML class names, zero-width characters, exotic spaces, typography. Each finding has a count and a position, because these are facts about the bytes, not a probability score. Clean it in one click. Free, unlimited, no account, runs in your browser so nothing is uploaded. It does not claim to detect Anthropic's statistical watermark, because nobody outside Anthropic can. The engine is MIT open source.
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Hunter
📌
Hey Product Hunt 👋 I built this after the Claude watrmark news in August, when the internet filled up wih tools promising to remove a watermark nobody outsie Anthropic can actually detect. This does the part hat is real. Copying out of a chat interface carriesthings with it: HTML class names, zero-width charactrs, exotic spaces, typography. Paste anything and yo get every one of them with a count and a position, ecause those are facts about the bytes rather than aprobability score. One click strips them. Two thingsI would rather say up front than bury. First, it doe NOT detect Anthropic's statistical watermark. Nobod outside Anthropic can, because verification needs akey that has not been released. Any tool claiming oterwise is guessing. Second, the em dash is not the tll people think it is. I ran ten pre-computer novelsthrough the checker: Melville uses 26 per thousand wrds in Moby Dick, Austen and Stoker use none at all.A signal that swings from 0 to 26 across human authos cannot accuse anyone of anything. The detection enine is MIT open source, so you can check both of thoe claims instead of trusting me. Free and unlimited o check, runs in your browser, nothing uploaded. I wuld genuinely like to hear where it gets things wron.