anomaly-detection

AI-driven IoT threat detection mesh — hand-written neural net trained live in the browser, visualized in 3D. No backend.

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and garbage mid-stream, before the user sees a bad token. Works with any OpenAI-compatible API.

Official code for "Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection" (NeurIPS 2026). RAMSAD selects the best anomaly detector for a new series by retrieving similar series from a knowledge base, with no selector training.