v0.6.0-esp32

ruvnet/RuViewv0.6.0-esp32Apr 3, 2026by ruvnet

AI Summary

Pre-trained models published on HuggingFace with 17 sensing applications including sleep monitor, apnea detector, stress monitor, gait analyzer, and through-wall detection. Achieves 0.008ms inference and 100% presence accuracy.

Key Highlights

Pre-trained weights on HuggingFace (ruv/ruview)
17 sensing applications (sleep, apnea, stress, gait, RF tomography, passive radar, etc.)
0.008ms inference latency, 164K emb/s throughput
100% presence accuracy, 51.6% contrastive improvement
8 KB model size trained on 60,630 overnight samples

New Features

17 new sensing applications
Kalman tracker (PR #341)
Security fix (PR #310)
10 ADRs (069-078)
HuggingFace model hosting

Full Release Notes

Pre-trained weights: **https://huggingface.co/ruv/ruview** | [mirror](https://huggingface.co/ruvnet/wifi-densepose-pretrained)

**0.008ms inference | 164K emb/s | 100% presence | 51.6% contrastive improvement | 8 KB model**

Trained on 60,630 overnight samples. 17 sensing applications. 10 ADRs (069-078).

New: sleep monitor, apnea detector, stress monitor, gait analyzer, RF tomography, passive radar, material classifier, through-wall detector, device fingerprint.

PR #341 (Kalman tracker by @taylorjdawson) + PR #310 (security fix) merged.

[HuggingFace](https://huggingface.co/ruv/ruview) | [Cognitum.one](https://cognitum.one) | [Tutorial](https://github.com/ruvnet/RuView/blob/main/docs/tutorials/cognitum-seed-pretraining.md)