Verified project record

ruvnet/RuView

ruview turns ordinary WiFi signals into contactless spatial intelligence, detecting presence, breathing, heart rate, pose, and falls using low-cost ESP32 sensors instead of cameras or wearables. It ships ESP32 firmware for capturing WiFi Channel State Information plus an npm toolkit with an MCP server for AI-assisted setup and verification.

Project overview

It addresses privacy-invasive camera- and wearable-based people monitoring with a camera-free approach that works through walls and in the dark, combining real-time presence, breathing, and heart-rate measurement from WiFi CSI with AI-agent integration via MCP and Claude Code.

Project type: MCP
Deployment: Refer to project documentation
License: MIT

Best for

Developers building privacy-sensitive presence or vital-sign monitoring who can deploy ESP32 sensors and run a self-hosted server, and who want AI-assisted setup via MCP or Claude Code.

Key capabilities

Detects people through walls, counts them, and measures breathing and heart rate in real time from WiFi CSI captured by low-cost ESP32 sensors.
Ships ESP32-S3/C6 firmware that captures and streams Channel State Information to a bridge/server; edge modules run directly on the sensor with no internet needed.
The @ruvnet/ruview npm package provides a setup doctor, live CSI viewing, an MCP server over stdio or HTTP, and a Claude Code mod for onboarding and verification.

Limitations and risks

The on-device 17-keypoint pose model is a first cut with PCK@20 of 3.0%, below the ADR-079 target, and its runtime path is a confidence=0 stub — do not rely on pose estimation output yet.
The optional pretrained CSI model ruvnet/wifi-densepose-pretrained downloadable from Hugging Face has a published model file whose header is NUL-padded and is rejected by the reference safetensors.torch.load_file (issue #1522); a corrected re-upload is pending, so plan on operating without it until it is fixed.

Getting started

Run: docker pull ruvnet/wifi-densepose:latest; export RUVIEW_API_TOKEN=$(openssl rand -hex 32); docker run -p 127.0.0.1:3000:3000 -e RUVIEW_API_TOKEN ruvnet/wifi-densepose:latest. Setup difficulty is rated medium.

Evidence and sources

README: RuView captures these disturbances using Channel State Information (CSI) from low-cost ESP32 sensors and turns them into actionable data
README: Detect people, measure breathing and heart rate, track movement, and monitor rooms — through walls, in the dark, with no cameras or wearables.
README: **Presence and occupancy** — detect people through walls, count them, track entries and exits
README: The published file's header is NUL-padded, which the reference `safetensors.torch.load_file` rejects (issue [#1522](https://github.com/ruvnet/RuView/issues/1522)) — pending a corr…
README: python -m esptool --chip esp32s3 --port COM9 --baud 460800

Source updated at: 2026-11-09T18:43:13Z

Open original GitHub project