isGenAI.com

isGenAI.com · Free AI code detector

AI code detector: find every Copilot, ChatGPT and Claude mark in your code

Paste source code, a diff, comments or a README and choose Check my code. isGenAI lists every statement that an AI tool helped write it, every AI tool it names and every AI library it imports, quoting the exact line each time.

Free. No account. Up to 16,000 characters. Code is read, never run.

The free isGenAI detector

Check for AI. See the evidence.

Free · No sign-up

0 / 16,000 characters

Finds every AI-use statement and tool mention in your text or code, and shows you the exact words.

Your uploads and pasted content stay private by default.Privacy

Every result shows exactly what we found and exactly how we checked it.

What the AI code detector finds

AI help usually leaves marks in the code or around it. The detector reads the characters you paste and reports three kinds of evidence, each with the matching text:

  • Declared AI use. Comments and notes such as “generated by GitHub Copilot” or “written with ChatGPT”.
  • AI tool mentions. Names such as Copilot, ChatGPT, Claude, Gemini or Cursor, including attribution lines like a commit trailer naming Claude.
  • AI libraries. Imports of AI service SDKs, for example an OpenAI or Anthropic client, which show the code talks to a model.

The report keeps these apart. A comment saying a function was generated is a different claim from code that calls an AI service, and both differ from a passing mention of a product name.

What it does not do

It does not score coding style or guess a percentage of AI-written lines. Unmarked code carries no declared evidence, so the report says so instead of inventing a verdict. That makes every finding something you can quote in a review, a classroom or an audit, rather than a probability you have to take on trust.

How to check code for AI use

  1. Copy the file, function, diff or README you want to review, including its comments.
  2. Paste it into the checker above and select Check my code.
  3. Read each finding and the exact line it quotes, then open “How we checked” for the method.
  4. Compare the findings with the commit history, the pull request and the author's own account, then save the report with your notes.

Checking commits, pull requests and repositories

Commit messages and pull request descriptions often carry the clearest marks, such as a co-author trailer or a note that a change was drafted with an assistant. Paste them alongside the code. To check many files automatically, call the same reader from your own scripts with the free isGenAI API, which takes code with "kind": "code" and needs no key.

Checking prose instead? Use the AI text detector. Have a picture? Use the AI image detector. The full scope is in the checker methodology.

Questions about checking code for AI

Can this AI code detector tell if ChatGPT or Copilot wrote my code?

It shows what the code itself says. Comments such as “generated by Copilot”, attribution lines naming Claude or ChatGPT and AI service libraries are reported with the exact words. Code with no such marks carries no declared evidence, so isGenAI does not guess an author from style.

What does the AI code detector look for?

Statements that an AI tool helped write the code, mentions of AI tools such as Copilot, ChatGPT, Claude, Gemini or Cursor, and imports of AI service libraries. Each finding quotes the matching text, so you can point to it in a review.

Is my source code uploaded or run?

Pasted code is read as plain characters and never executed. Checks are private by default, and the exported report leaves out the code you pasted. No account is needed.

How should I use the result in a code review?

Treat each finding as a traceable statement, then compare it with the commit history, the pull request description and the author's own account. A missing mark is not proof that a person wrote the code; teams that need certainty should ask contributors to declare AI help.