Back to Projects
Full Stack
CopyGuard
A local-first web app that detects plagiarism in student assignments by combining hybrid local signals (MinHash, TF-IDF, embeddings, and section/block overlap) with optional LLM-based full-AI evaluations. Features persisted analysis runs and side-by-side reporting built for educators.
Tech Stack
PythonFastAPINext.jsSQLiteHugging FaceSSE
Key Features
- Hybrid analysis: MinHash, TF-IDF, embeddings, section & block overlap
- Optional full-AI mode via OpenRouter, OpenAI & Anthropic-compatible APIs
- Side-by-side comparison of hybrid and full-AI results
- Live progress tracking via Server-Sent Events
- Supports .docx, .pdf, .pptx, .md and .txt documents
- Searchable HTML reports, CSV exports and visual heatmaps
- Per-course and per-assignment file organization
Screenshots
Project screenshots and demo images will be added here.