LLaMAudit: Perform AI detection using local or open models (github.com)

LLaMAudit has launched an open-source tool enabling users to conduct AI text detection on their own by hosting a local or cloud-based LLM auditing system. This innovative tool allows for the analysis of essays, articles, and reports to determine sections likely generated by AI. Users receive per-paragraph probability scores, reasoning, and highlighted results, enhancing understanding of AI authorship indicators. The system supports various file formats, including Word and ODT, and enables connection to multiple AI models through platforms like OpenRouter and Ollama. The significance of LLaMAudit lies in its democratization of AI detection technology, making it accessible for educators, students, and content creators alike. By providing a transparent method for auditing written work, it empowers users to identify AI-generated sections effectively. The backend utilizes technologies like Express and PostgreSQL for data management, while the frontend is built on Next.js and React, offering a user-friendly interface. Additionally, the ability to review analysis history and run multiple model comparisons enhances its utility, marking a significant stride toward responsible AI usage in writing and education.