WiFi-DensePose
Reconstruct human pose and vitals from WiFi CSI with ESP32 — "seeing through walls"
Reconstructs human pose, breathing, and heartbeat from WiFi CSI signals captured with ESP32 — "seeing through walls"; a topic-exploding project.
AI agents that code, operate computers, and get work done.
Key features
- Turns ordinary WiFi into a spatial sensing system: detects people, measures breathing
- Uses Channel State Information (CSI) from low-cost ESP32 sensors; no cameras or wearables
- Integrates with Home Assistant, Apple Home, Google Home, Alexa via MQTT/Matter; 21
- Camera-free pose: estimates 17 body keypoints from WiFi CSI
- Includes MetaHarness npm toolkit for guided operation by humans and AI agents
Good for
- Smart-home presence, fall detection, and elderly monitoring without
- Privacy-preserving occupancy and sleep monitoring
Stack & tags
TypeScriptwifi-sensingpresence-detectionvital-signsesp32smart-homehome-assistantprivacy
Quick start
npx @ruvnet/ruview@0.9.1 doctorFrom the project README on GitHub.
Screenshots
Screenshots from the project’s GitHub README.
Similar open-source projects
openclaw
★ 391,183The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Hermes Agent
★ 250,268Nous Research's autonomous AI agent — persistent memory, self-generated skills