Predator is a copy detection system aimed at finding the copy among documents. Currently it supports documents in pdf format. All you have to do is make your repository first by uploading the documents and check the suspected documents with the repository built. For easy installation, you can run install_dependencies.sh in linux to install all the required dependencies. For the rest, please check the README.
Yes, i have not been able to benchmark the performance, write test cases (which i will do in the days to come), yet i would like to know your take on the project.