Jevstiller is a local model distillation system that learns to replicate a remote AI model's (Jev) answers with a formal disagreement bound, enabling fast on-device inference (~15ms) while maintaining agreement on a specified percentage of requests. The system uses a small logistic regression head trained on sentence embeddings plus routing logic calibrated to keep disagreement below a target threshold, and demonstrates that naive confidence-threshold selection fails to maintain statistical guarantees, requiring more sophisticated calibration.
Llamora is a private, self-hosted journal application that uses local AI models to provide daily summaries, suggest topic tags, and respond to entries—with all data encrypted and no telemetry or external requests.