[GitHub Trending] ruvnet/RuView
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
WiFi-based spatial intelligence is novel but not directly relevant to the reader's focus on AI/cloud engineering.
RuView is an open-source WiFi sensing platform that uses Channel State Information from low-cost ESP32 sensors to detect presence, vital signs, and activity through walls without cameras or wearables. It runs entirely on edge hardware (as low as $9 per node), leveraging spiking neural networks that adapt in under 30 seconds, and cryptographically attests every measurement via an Ed25519 witness chain. The pretrained presence model achieves 100% validation accuracy in 8 KB (4-bit quantized), and the system can harness neighboring routers as free radar illuminators across 6 WiFi channels.
Evaluate RuView for contactless sensing workloads that demand privacy, low latency, and zero cloud dependency — its $9-per-node edge architecture and 100% accurate presence detection make it a strong candidate for ambient monitoring systems.
For a solutions architect focused on edge AI, privacy-first sensing, and IoT infrastructure, RuView demonstrates a production-ready pattern: combining commodity hardware (ESP32), local spiking NN adaptation, and cryptographic attestation to build a scalable, cloud-free spatial intelligence layer — directly applicable to healthcare, smart building, and security use cases.
π RuView Beta Software — Under active development. APIs and firmware may change. Known limitations: ESP32-C3 and original ESP32 are not supported (single-core, insufficient for CSI DSP) Single ESP32 deployments have limited spatial resolution — use 2+ nodes or add a Cognitum Seed for best results Camera-free pose accuracy is limited (PCK@20 ≈ 2.5% with proxy labels) — camera ground-truth training targets 35%+ PCK@20 ; the pipeline is implemented, but the data-collection and evaluation phases (ADR-079 P7–P9) are still pending, so no measured camera-supervised PCK@20 has been published yet