23 Daily — According to the project's description, RuView is a platform that turns ordinary WiFi signals into real-time spatial intelligence and vital sign monitoring without using any cameras or wearable devices. It uses low-cost ESP32 sensors to capture WiFi Channel State Information (CSI), analyzing presence, breathing rate, heart rate, movement tracking, and more. As of November 9, 2026, RuView gained over 100,000 stars on GitHub Trending.
RuView is capable of working through walls and in the dark to detect people count, entries and exits, vital signs like breathing and heart rate contactlessly, activity recognition such as walking, sitting, falls, environment mapping, sleep quality monitoring, and even camera-free body pose estimation with 17 keypoints. The system operates entirely on edge hardware without requiring internet or cloud services.
Comprehensive WiFi-Based Sensing and Smart Home Integration
RuView leverages ubiquitous WiFi router radio waves and their disturbances caused by human presence and movements, capturing these via CSI technology and converting them into actionable data. The platform natively supports major smart home ecosystems: Home Assistant, Apple Home/HomePod, Google Home, and Amazon Alexa. Integration is possible through MQTT or Matter protocols, enabling voice assistants to access presence and vital signs information by room without custom skills.
Each sensor node outputs 21 entities: 11 raw signals plus 10 inferred semantic states such as someone sleeping, possible distress, room active status, elderly inactivity anomaly, meeting in progress, bathroom occupied, elevated fall risk, bed exit, no movement, and multi-room transition. Additionally, three starter Home Assistant blueprints are included for quick automation setup.
Low-Cost Edge Computing and Secure Measurement Verification
RuView runs on an ESP32 mesh network hardware costing about $9 per node, paired with Cognitum Seed for persistent storage, cryptographic attestation, and AI integration. The system locally learns each environment in under 30 seconds using spiking neural networks, scanning multiple WiFi channels and incorporating neighbor routers as radar illuminators. All measurements are cryptographically attested using an Ed25519 witness chain to ensure data integrity and privacy.
To improve accuracy, RuView uses pretrained models that run on low-power devices such as Raspberry Pi, with an 8 KB 4-bit quantized size and no need for cameras or wearables. The version 2 encoder achieves an honest, label-free held-out temporal-triplet accuracy of 82.3%. The open-source suite includes firmware flashing, device calibration, automation workflows, and AI agent guided operations for verification.
Editor's take: New possibilities in sensor-less monitoring
RuView's approach of transforming widely deployed WiFi signals into spatial and vital sign sensing opens new pathways in home health management, smart building security, and elderly care with enhanced privacy and reduced hardware costs. For entrepreneurs, this technology offers a low barrier-to-entry and scalable solution compared to traditional video or wearable-based sensing.
A practical way to validate RuView's capability is by deploying ESP32 nodes integrated with RuView’s Home Assistant implementation to assess detection accuracy and latency. Comparing this with conventional sensing methods on cost and performance can highlight viability. Future improvements with AI-powered local model fine-tuning promise more flexible and adaptive use cases.