Local, full-logit AI text forensics and humanization toolkit. It scores markdown with observer/performer llama.cpp models (logPPL, logXPPL, B), surfaces chunk-aware hotspots and heatmaps, ranks rewrites, and ships CLI, desktop UI, Obsidian plugin, VS Code extension, and HTTP API (dev-grade) server with GUI test/demo harness.
vscode vscode-extension humanizer obsidian stylometry cross-entropy tkinter-gui perplexity humanization obsidian-plugin perplexity-score binoculars api-http gptzero ai-detection llama-cpp-python likelihood-scoring humanizing-interactive ai-text-forensics authorship-signals
-
Updated
Feb 27, 2026 - Python