{"name":"RuView: Turn WiFi CSI into Spatial Intelligence","description":"RuView uses WiFi Channel State Information from ESP32 sensors to detect presence, movement, and vital signs without cameras or wearables. Built on RuVector and Cognitum Seed, it targets privacy-conscious edge sensing and smart-home automation.","github":"https://github.com/ruvnet/RuView","url":"https://osrepos.com/repo/ruvnet-ruview","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/ruvnet-ruview","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/ruvnet-ruview.md","json":"https://osrepos.com/repo/ruvnet-ruview.json","topics":["rust","ai","automation","privacy","wifi-sensing","vital-sign-monitoring","channel-state-information"],"keywords":["rust","ai","automation","privacy","wifi-sensing","vital-sign-monitoring","channel-state-information"],"stars":null,"summary":"RuView uses WiFi Channel State Information from ESP32 sensors to detect presence, movement, and vital signs without cameras or wearables. Built on RuVector and Cognitum Seed, it targets privacy-conscious edge sensing and smart-home automation.","content":"## Overview\n\nRuView is an edge WiFi-sensing platform that analyzes Channel State Information (CSI) to infer presence, movement, and vital signs without cameras or wearables. It is built on RuVector and Cognitum Seed, and uses low-cost ESP32 sensors to capture radio-signal changes for local processing and smart-home integrations.\n\nThe project is aimed at developers and researchers building room-level sensing, home automation, or privacy-preserving monitoring. It supports ESP32 sensing nodes, Python packages, and a Docker-based evaluation path with simulated data. Advanced sensing requires CSI-capable hardware; ordinary WiFi laptops provide only coarse RSSI-based detection.\n\n## Key Features\n\n- Detects room presence and movement from WiFi signal changes, including through walls where signal conditions allow.\n- Provides signal-processing pipelines for breathing and heart-rate estimates, with results that require validation for the target environment.\n- Supports ESP32 CSI nodes and multi-node sensing, alongside research NICs and experimental hardware integrations.\n- Offers Python packages for using sensing and signal-processing components in applications.\n- Integrates with Home Assistant through MQTT and describes bridges for Apple Home and Matter-compatible ecosystems.\n- Includes model workflows and pretrained CSI models, while clearly distinguishing benchmark results from the less mature live pose-estimation path.\n- Provides a guided operator toolkit with device access, MCP support, and guarded agent workflows.\n\n## Use Cases\n\n- Smart-home developers can use room-level presence signals to trigger lighting or HVAC automation without relying on cameras.\n- Researchers can explore WiFi-based activity and vital-sign sensing using ESP32 nodes or research NICs, then validate results against their own data.\n- Care and building teams can prototype contactless room monitoring, provided they independently validate measurements before operational use.\n- Edge-computing developers can test local sensing pipelines and Home Assistant integrations without sending sensor data to a cloud service.\n\n## Our Take\n\nRuView is an unusually broad, actively maintained WiFi-sensing project, but its sensing claims and hardware-dependent models need careful validation, and development is concentrated around one contributor.\n\n**Good fit if:**\n- You want to prototype camera-free sensing and can provide CSI-capable hardware such as ESP32 nodes.\n- Your project needs local processing or Home Assistant integration, and you are prepared to test performance in the target room.\n- You want an MIT-licensed codebase with frequent commits and releases and a short recent median time to merge pull requests.\n\n**Look elsewhere if:**\n- You need validated medical, emergency, or safety-critical measurements. The project explicitly describes these uses as prototypes, not certified systems.\n- You need reliable live 17-keypoint pose estimation from a single ESP32. The README identifies that path as a weak first-cut model with a runtime stub.\n- You need a project whose maintenance is broadly distributed, rather than one where most contributions come from a single person.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **Active**: regular commits and releases |\n| Last commit | 2026-10-26 (2 days ago) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 100+ (latest v3422, 2026-10-26) |\n| Contributors | 40 (top contributor: 79% of commits) |\n| Issues closed, last 90 days | 14+ (typically closed in 0 days) |\n| Pull requests merged, last 90 days | 52 (typically merged in 3 days) |\n| Project age | 17 months |\n\nChecked on 2026-10-29 with the GitHub API.\n\n## Project Facts\n\n- Language: Rust\n- License: MIT\n- Stars: 101k\n- Forks: 13.2k\n- Topics: awesome, claude, densepose, esp32, firmware, home-assistant, home-automation, iot\n- Website: https://Cognitum.One/RuView\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Python >=3.9 (from pyproject.toml)\n- A test suite and automated checks on GitHub Actions\n\n## Getting Started\n\nFor the Python package, install with:\n\n```bash\npip install ruview\n```\n\nSee the [README](https://github.com/ruvnet/RuView) and [user guide](https://github.com/ruvnet/RuView/blob/main/docs/user-guide.md) for hardware setup, Docker evaluation, and integration details.\n\n## License in Plain Words\n\n**MIT** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the copyright and license notice\n- Share your changes: no\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Considerations\n\n- Presence, vital-sign, and advanced sensing features need CSI data from compatible hardware. Docker's simulated input is useful for evaluating the software pipeline, but does not demonstrate real-world sensing performance.\n- Results depend on the hardware, room, subjects, and capture conditions. The README cautions that vital-sign and pose outputs need independent validation before operational use.\n- The project distinguishes published benchmark results from live device performance. In particular, the current single-ESP32 pose path is below its stated target and is not wired to produce validated pose output.\n- The repository is active, with frequent recent commits and releases, but contributor activity is highly concentrated in one person. Teams adopting it should account for that maintenance dependency.","metrics":{"detailViews":2,"githubClicks":0},"dates":{"published":null,"modified":"2026-10-29T00:34:22.000Z"}}