I made a web app + agent-ready CLI for stripping out the "Made with AI" tag from images you upload to X (along with all other user-identifiable metadata).

x.com started parsing metadata from uploaded images and using it to automatically mark posts as "Made with AI".

Philosophy

IMO social media websites shouldn't be using user image metadata to in the first place, this is a user privacy issue.

Also, the question should not be about whether something is generated with AI or not. it should be about whether someone deceived others or not. AI is just one tool people use to deceive others, and there are tons of other "shitposts" on social media that do NOT use AI but blatantly deceive people. By labeling things as "AI" or not, it just hides the actual problem.

Anyway, here's how it works:

How it works

Install stripper and launch. Then:

1. Just drag and drop any image
2. Stripper displays all the metadata
3. Download the clean version and use.

Use in agents

To use stripper in an agent, just tell your agent to read the docs here https://github.com/cocktailpeanut/stripper

Compare before & after https://x.com/cocktailpeanut/status/2047400536576774226?s=20