SlopTotal, a Self-hosted AI text detector that runs 23 open models (github.com)

SlopTotal has launched a free, self-hosted AI text detection tool that operates on your local machine, enabling users to analyze text, PDFs, and URLs without any data leaving their device. This platform integrates 23 independent detection models, including sophisticated neural classifiers like DeBERTa and RoBERTa, along with statistical and linguistic heuristics. By running these models in parallel, SlopTotal provides a comprehensive view of AI content detection, showing individual scores from each model and the overall verdict, which can be inspected in detail. This self-hosted solution is a significant advancement for the AI/ML community as it offers an open-source alternative to commercial detectors like GPTZero and Originality.ai. Users can examine how each model performs against curated corpora, including both AI-generated text and classic literature, thus addressing the common criticism of accuracy transparency in AI detectors. SlopTotal emphasizes privacy by ensuring that no data is sent to third-party services, making it a valuable tool for researchers and developers interested in understanding and mitigating AI-generated content while maintaining user confidentiality.