π RuView

See through walls with WiFi

Turn ordinary WiFi into a spatial intelligence / sensing system. Detect people, measure breathing and heart rate, track movement, and monitor rooms — through walls, in the dark, with no cameras or wearables. Just physics.

Works natively with the four major smart-home ecosystems: Home Assistant via the HA-DISCO MQTT publisher, Apple Home & HomePod as a discoverable HAP-1.1 bridge, Google Home + Amazon Alexa via the same HA bridge or a Matter endpoint. Siri, Google Assistant, and Alexa can voice presence and vitals by room with zero custom skills.

Drop into any Home Assistant install with one --mqtt flag. Or pair into Apple Home / Google Home / Alexa / SmartThings as a Matter Bridge. Ships 21 entities per node (11 raw signals + 10 inferred semantic states: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting-in-progress, bathroom-occupied, fall-risk-elevated, bed-exit, no-movement, multi-room-transition) plus 3 starter HA Blueprints. See docs/integrations/home-assistant.md · ADR-115.

π RuView is a WiFi sensing platform that turns radio signals into spatial intelligence.

Every WiFi router already fills your space with radio waves. When people move, breathe, or even sit still, they disturb those waves in measurable ways. RuView captures these disturbances using Channel State Information (CSI) from low-cost ESP32 sensors and turns them into actionable data: who's there, what they're doing, and whether they're okay.

What it senses:

• Presence and occupancy — detect people through walls, count them, track entries and exits

• Vital signs — breathing rate and heart rate, contactless, while sleeping or sitting

• Activity recognition — walking, sitting, gestures, falls — from temporal CSI patterns

• Environment mapping — RF fingerprinting identifies rooms, detects moved furniture, spots new objects

• Sleep quality — overnight monitoring with sleep stage classification and apnea screening

Built on RuVector and Cognitum Seed, RuView runs entirely on edge hardware — an ESP32 mesh (as low as $9 per node) paired with a Cognitum Seed for persistent memory, cryptographic attestation, and AI integration. No cloud, no cameras, no internet required.

The system learns each environment locally using spiking neural networks that adapt in under 30 seconds, with multi-frequency mesh scanning across 6 WiFi channels that uses your neighbors' routers as free radar illuminators. Every measurement is cryptographically attested via an Ed25519 witness chain.

RuView turns ordinary WiFi into a contactless sensor. A $9 ESP32 board reads the radio reflections off the people in a room, and a small pretrained model — published on Hugging Face at ruvnet/wifi-densepose-pretrained — tells you who's there, how they're breathing, and how their heart rate is trending. The model fits in 8 KB (4-bit quantized) and runs in microseconds on a Raspberry Pi. (The v2 encoder reports an honest, label-free held-out temporal-triplet accuracy of 82.3% — up from 66.4% raw; the older "100% presence" figure was measured on a single-class recording and has been retracted in favor of this.) No cameras, no wearables, no app on the user's phone.

Built for low-power edge applications

Edge modules are small programs that run directly on the ESP32 sensor — no internet needed, no cloud fees, instant response.

WhatHowSpeed / scale🫁 Breathing rateBandpass 0.1–0.5 Hz on wrapped phase, circular variance, zero-crossing BPM (#593)6–30 BPM, real-time💓 Heart rateBandpass 0.8–2.0 Hz, zero-crossing BPM40–120 BPM, real-time👤 Presence detectionTrained head on Hugging Face (ruvnet/wifi-densepose-pretrained; v2 encoder = 82.3% held-out temporal-triplet acc, honestly re-benchmarked) + a phase-variance fallback that needs no model< 1 ms, ~30 s ambient calibration🧬 CSI embeddings128-dim contrastive encoder shipped on Hugging Face, 4-bit quantised variant fits in 8 KB164,183 emb/s on M4 Pro🦴 17-keypoint pose estimationcog-pose-estimation Cog v0.0.1 — signed aarch64 + x86_64 binaries on GCS, loads pose_v1.safetensors via Candle. Train your own from paired data in 2.1 s on an RTX 5080 (ADR-101, benchmarks). SOTA on MM-Fi: ruvnet/wifi-densepose-mmfi-pose hits 82.69% torso-PCK@20 (ensemble 83.59%), beating MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched MM-Fi random_split protocol — self-corrected and auditable on AetherArena8.4 ms cold-start on a Pi 5🚶 Motion / activityMotion-band power + phase accelerationReal-time🤸 Fall detectionPhase-acceleration threshold + 3-frame debounce + 5 s cooldown (#263)< 200 ms🧮 Multi-person countAdaptive P95 normalisation + runtime-tunable dedup factor (/api/v1/config/dedup-factor, #491). Six specialised learned counters available as Cogs: occupancy-zones, elevator-count, queue-length, customer-flow, clean-room, person-matchingReal-time, self-calibrating🌍 World model predictionOccWorld TransVQVAE — 15-frame future occupancy prediction, 209 ms inference, 3.4 GB VRAM on RTX 5080; fine-tune on your space with occworld_retrain.py (ADR-147)15 frames × 200×200×16 vox🧱 Through-wall sensingFresnel-zone geometry + multipath modelingUp to ~5 m, signal-dependent🧠 Edge intelligence105-cog catalog (ADR-102) live from app-registry.json — health, security, building, retail, industrial, research, AI, swarm, signal, network, and developer modules. Optional Cognitum Seed adds persistent vector store + kNN + witness chain$140 total BOM🎯 Camera-free pre-trainingSelf-supervised contrastive encoder, 12.2M training steps on 60K frames, shipped on Hugging Face84 s/epoch retrain on M4 Pro📷 Camera-supervised fine-tuneMediaPipe + ESP32 CSI paired training, end-to-end Candle pipeline on RTX 5080 (ADR-079)2.1 s for 400 epochs (~5 ms/epoch)📡 Multi-frequency meshChannel hopping across 6 bands, TDM slot scheduling (ADR-029)3× sensing bandwidth🌐 3D point cloud fusionCamera depth (MiDaS) + WiFi CSI + mmWave radar → unified spatial model22 ms pipeline · 19K+ points/frame

Browse the full 105-module catalog (with practical descriptions, sizes, and difficulty) below in 🧩 Edge Module Catalog, or visit seed.cognitum.one/store.

🤗 Pretrained weights: download from ruvnet/wifi-densepose-pretrained — see Loading the pretrained model below for one-command setup.

# Option 1: Docker (simulated data, no hardware needed)
docker pull ruvnet/wifi-densepose:latest
docker run -p 3000:3000 ruvnet/wifi-densepose:latest
# Open http://localhost:3000

# Option 2a: Live sensing with ESP32-S3 hardware ($9)
# Flash firmware, provision WiFi, and start sensing:
python -m esptool --chip esp32s3 --port COM9 --baud 460800 \
  write_flash 0x0 bootloader.bin 0x8000 partition-table.bin \
  0xf000 ota_data_initial.bin 0x20000 esp32-csi-node.bin
python firmware/esp32-csi-node/provision.py --port COM9 \
  --ssid "YourWiFi" --password "secret" --target-ip 192.168.1.20

# Option 2b: WiFi 6 + 802.15.4 research sensing with ESP32-C6 ($6-10, ADR-110)
# Same csi-node firmware compiled for the C6 target — picks up the C6
# overlay (sdkconfig.defaults.esp32c6) automatically.
cd firmware/esp32-csi-node
idf.py set-target esp32c6 && idf.py build
idf.py -p COM6 flash
# C6 boot extras (vs S3): HE-LTF subcarrier tagging in ADR-018 bytes 18-19,
#   802.15.4 mesh time-sync on channel 15, TWT setup when the AP supports it,
#   opt-in LP-core wake-on-motion for ~5 µA battery seed nodes.
# v0.6.7 adds: real LP-core RISC-V motion-gate program (debounce + motion
#   counter) and a Wi-Fi 6 soft-AP with TWT Responder so two C6 boards can
#   benchmark real iTWT without buying an 11ax router. Both default off,
#   flip CONFIG_C6_{LP_CORE,SOFTAP_HE}_ENABLE to turn them on.

# Option 3: Full system with Cognitum Seed ($140)
# ESP32 streams CSI → bridge forwards to Seed for persistent storage + kNN + witness chain
node scripts/rf-scan.js --port 5006           # Live RF room scan
node scripts/snn-csi-processor.js --port 5006  # SNN real-time learning
node scripts/mincut-person-counter.js --port 5006  # Correct person counting

# Option 4: Python — live on PyPI (ADR-117)
pip install ruview                        # or: pip install wifi-densepose
# Both ship the same compiled PyO3 wheel (~250 KB, abi3-py310, Linux/macOS/Windows).
# Add [client] for the asyncio WebSocket + paho-mqtt clients:
pip install "ruview[client]"              # or: pip install "wifi-densepose[client]"

# from ruview import BreathingExtractor, HeartRateExtractor   # equivalent to:
# from wifi_densepose import BreathingExtractor, HeartRateExtractor
# from ruview.client import SensingClient, RuViewMqttClient

[!NOTE] CSI-capable hardware recommended. Presence, vital signs, through-wall sensing, and all advanced capabilities require Channel State Information (CSI) from an ESP32-S3 ($9) or research NIC. The Docker image runs with simulated data for evaluation. Consumer WiFi laptops provide RSSI-only presence detection.

Hardware options for live CSI capture:

OptionHardwareCostFull CSICapabilitiesESP32 + Cognitum Seed (recommended)ESP32-S3 + Cognitum Seed~$140YesPresence, motion, breathing, heart rate, fall detection, multi-person counting, 17-keypoint pose (signed Cog binary), 105-cog catalog, persistent vector store, kNN search, witness chain, MCP proxyESP32 Mesh3-6× ESP32-S3 + WiFi router~$54YesSame capabilities as above without the persistent-memory featuresESP32-C6 research node (ADR-110, witness, reviewer guide, firmware v0.7.0)ESP32-C6-DevKit ($6–10)~$10Yes (Wi-Fi 6 capable)Same CSI pipeline as S3 with the dual-target firmware. Firmware-side ADR-110 substrate now closed (v0.7.0): ESP-NOW cross-board mesh quantified at 99.56 % match / 104 µs smoothed offset stdev / 3.95× EMA suppression over a 5-min two-board soak (witness §A0.10), 32-byte UDP sync packet with operator-tunable cadence (§A0.12), ADR-018 byte 19 bit 4 wire-fix sourced from the working ESP-NOW path (§A0.13). Wire format ready for HE-LTF PPDU tagging in ADR-018 bytes 18-19 (firmware encoder + Rust + Python decoders verified end-to-end across 23 unit tests). LP-core motion-gate RISC-V program and Wi-Fi 6 soft-AP with TWT Responder both ship as opt-in code paths (default off). Hardware-gated for measurement: HE-LTF live subcarrier capture needs an 11ax AP (IDF v5.4 doesn't expose AP-side HE config — §A0.6); ~5 µA LP-core hibernation needs an INA meter to capture; 802.15.4 raw RX is broken in IDF v5.4 (workaround: ESP-NOW transport, shipped + measured). See witness log for the empirical / claimed split.Research NICIntel 5300 / Atheros AR9580~$50-100YesFull CSI with 3x3 MIMOAny WiFiWindows, macOS, or Linux laptop$0NoRSSI-only: coarse presence and motion (see tutorial #36)

No hardware? Verify the signal processing pipeline with the deterministic reference signal: python archive/v1/data/proof/verify.py

---

The server is optional for visualization and aggregation — the ESP32 runs independently for presence detection, vital signs, and fall alerts.

Live ESP32 pipeline: Connect an ESP32-S3 node → run the sensing server → open the pose fusion demo for real-time dual-modal pose estimation (webcam + WiFi CSI). See ADR-059.

three.js scene gallery at /three.js/ — five progressively richer ADR-097 demos: helpers, cinematic, GLTF skinned, FBX skinned, and a live MediaPipe→Mixamo retargeting feed driven by ESP32 CSI. Demos 04 and 05 require a local Mixamo X Bot.fbx (license boundary — not redistributed).

🤗 Pretrained model on Hugging Face

Pretrained CSI weights live at ruvnet/wifi-densepose-pretrained — 12.2M training steps on 60K frames / 610K contrastive triplets, 82.3% held-out temporal-triplet accuracy (up from 66.4% raw; the older "100% presence" figure was measured on a single-class recording and has been retracted), 4-bit quantized variant fits in 8 KB. The release includes a contrastive CSI encoder producing 128-dim embeddings (164,183 emb/s on M4 Pro) and a presence-detection head. Per-node LoRA adapters are included for environment-specific fine-tuning.

# Download the model bundle
pip install huggingface_hub
huggingface-cli download ruvnet/wifi-densepose-pretrained --local-dir models/wifi-densepose-pretrained

What works today vs. what's pending wiring:

ConsumerFormat usedStatusPython training / evaluation / embedding extractionmodel.safetensors✅ Works — load with safetensors.torch.load_fileInspect / re-export the bundlemodel.rvf.jsonl (line-by-line JSON)✅ Works — plain JSONLSensing-server --model <PATH> flagbinary RVF (RVFS magic)⚠️ Loader does not yet accept the JSONL container

Known gap: the HF model ships in JSONL RVF format, but v2/crates/wifi-densepose-sensing-server/src/rvf_container.rs only parses the binary RVF segment format. Pointing --model at model.rvf.jsonl currently errors with invalid magic at offset 0: expected 0x52564653, got 0x7974227B and the live pipeline degrades to null output rather than falling back to heuristic mode — so for the live sensing-server, run without --model until a JSONL adapter lands (or the model is re-published as binary RVF). Use the weights from Python / training in the meantime.

Quantization choices (all in the HF repo): model-q2.bin (4 KB) · model-q4.bin ⭐ recommended (8 KB) · model-q8.bin (16 KB) · model.safetensors full (48 KB)

The separate 17-keypoint pose-estimation model is now published at ruvnet/wifi-densepose-mmfi-pose — 82.69% torso-PCK@20 on MM-Fi (single model) / 83.59% (3-model ensemble + TTA), beating the prior published SOTA MultiFormer (72.25%) and CSI2Pose (68.41%) on the matched random_split protocol. See Results & proof below.

Results & proof

WhatWhereNumbersMM-Fi pose model (SOTA)ruvnet/wifi-densepose-mmfi-pose82.69% torso-PCK@20 (single) · 83.59% (ensemble+TTA) · 75K-param micro variant 74.30%AetherArena benchmark Spaceruvnet/aether-arenaself-correcting, auditable MM-Fi leaderboardFull MM-Fi study (honest picture)docs/benchmarks/mmfi-wifi-sensing-study.mdpose + action; zero-shot cross-subject ~64%, +~30 s in-room calibration → 72.2%Efficiency frontierdocs/benchmarks/wifi-pose-efficiency-frontier.mdSOTA-beating WiFi pose in a 20 KB int4 edge modelPretrained encoderruvnet/wifi-densepose-pretrained82.3% held-out temporal-triplet, 8 KB int4Reproducible proof (Trust Kill Switch)archive/v1/data/proof/verify.py + expected_features.sha256one-command deterministic pipeline replay (SHA-256 of output vs published hash)Benchmark-proof ADRADR-147how the numbers are produced and verifiedWitness attestationdocs/WITNESS-LOG-028.md33-row capability attestation matrix with per-claim evidence

# Reproduce the deterministic pipeline proof yourself (must print VERDICT: PASS):
python archive/v1/data/proof/verify.py

Tracked in #509; see ADR-079 phases P7–P9 for the camera-supervised fine-tune path.

🧩 Edge Module Catalog

Each module is a small signed binary (~400 KB) that runs alongside the WiFi-DensePose sensing stack on a Cognitum-V0 appliance. The catalog updates over the air — your appliance fetches it via GET /api/v1/edge/registry (ADR-102) and verifies each binary against an Ed25519 signature (ADR-100) before install.

🫀 Health — 14 modules

IDWhat it doesSizeDifficultyair-quality-indexTrack indoor air quality with CO2 and particle sensors8 KBEasybaby-crySustained mid-band energy detector for nursery / infant monitoring. Audio-only, no camera.451 KBEasybreathing-syncDetects when two people breathe in sync10 KBHardcardiac-arrhythmiaSpots irregular heartbeats and abnormal heart rhythms8 KBHardcough-detectAcoustic transient + spectral cough detector with 30s cluster aggregation. Early-warning signal for respiratory illness.451 KBEasydream-stageTracks your sleep stages — light, deep, and dreaming14 KBHardfall-detectTwo-stage impact + stillness fall detector over ambient feature stream (ESP32 motion / mic). Optional ruview-mode for CSI-based pose reinforcement.402 KBEasygait-analysisDetects walking problems and scores fall risk12 KBHardhealth-monitorContactless heart rate, breathing, sleep, and fall alerts30 KBMedrespiratory-distressAlerts when breathing becomes labored or dangerously fast10 KBHardseizure-detectRecognizes seizures and sends immediate alerts10 KBHardsleep-apneaDetects when someone stops breathing during sleep4 KBEasysnore-monitorPeriodic low-band energy tracker for sleep-quality / apnea-risk trending. Companion to sleep-apnea cog.451 KBEasyvital-trendTracks breathing and heart rate trends over weeks6 KBMed

🔒 Security — 14 modules

IDWhat it doesSizeDifficultyaudit-loggerRecord every action for compliance — tamper-proof log8 KBEasybehavioral-profilerLearns normal behavior and flags anything unusual12 KBHardfleet-authManage device certificates and access across all seeds12 KBMedglass-breakTwo-phase bang + shatter acoustic detector. Distinguishes glass break from ordinary impulse noise.451 KBEasygunshot-detectSaturating peak + exponential decay acoustic detector with optional ruview CSI motion-drop reinforcement.451 KBEasyintrusionAlerts when an unauthorized person enters a room6 KBMedintrusion-detect-mlDetect network attacks using machine learning14 KBHardloiteringAlerts when someone lingers too long in one spot3 KBEasynetwork-firewallBlock unauthorized network access per cog6 KBEasypanic-motionDetects sudden panicked or erratic movement6 KBMedperimeter-breachGuards multiple zones and shows entry direction10 KBMedprompt-shieldBlocks signal replay and injection attacks on the seed10 KBMedtailgatingCatches when someone sneaks in behind a badge holder6 KBMedweapon-detectDetects concealed metal objects on a person8 KBHard

🏢 Building — 11 modules

IDWhat it doesSizeDifficultybeehive-monitorAcoustic hive state classifier. Detects healthy / chaotic / queenless / swarming / robbing via hum-band energy + chaos + piping autocorr.451 KBEasyelevator-countCounts how many people are in an elevator8 KBMedenergy-auditLearns your schedule and cuts wasted energy6 KBMedfrost-warningPredicts frost 6 hours ahead via temperature trend + dewpoint-depression gate. Field/orchard agriculture.451 KBEasyhvac-presenceTurns heating and cooling on when you arrive3 KBEasylighting-zonesTurns lights on and off as people move between rooms4 KBEasymeeting-roomShows if a meeting room is free or occupied5 KBEasyoccupancy-zonesCounts people in each room through walls8 KBMedpredictive-maintenanceVibration harmonic analyzer for rotating equipment. Tracks F1 / 2×F1 / high-order / sideband energy to score degradation severity.451 KBEasysmoke-fireMulti-signal smoke and fire detector. Fuses acoustic crackle, thermal drift proxy, and optional ruview CSI plume signature. Not a UL-listed replacement for code-required smoke alarms.451 KBEasywater-leakPersistent low-amplitude hiss + periodic drip acoustic detector with multi-minute persistence gate. Two-stage likely → confirmed.451 KBEasy

🛍️ Retail — 7 modules

IDWhat it doesSizeDifficultycustomer-flowCounts foot traffic in and out of each entrance8 KBMeddwell-heatmapShows where customers spend the most time6 KBMedpackage-detectSustained CSI-shift detector for porch / loading bay package arrivals and departures. Requires ESP32 CSI ruview input.451 KBEasyparking-occupancyPer-zone parking occupancy via ESP32 CSI subcarrier-amplitude shift. Tracks utilization and churn-per-hour. Requires ruview.451 KBEasyqueue-lengthEstimates line length and wait time6 KBMedshelf-engagementDetects when customers interact with products6 KBMedtable-turnoverTracks which restaurant tables are free or occupied4 KBEasy

🏭 Industrial — 7 modules

IDWhat it doesSizeDifficultyclean-roomEnforces max headcount in controlled environments4 KBEasyconfined-spaceMonitors workers in tight spaces for safety5 KBMedforklift-proximityWarns if a forklift gets too close to workers10 KBHardlivestock-monitorMonitors animals for distress, escape, or illness6 KBMedppe-complianceCog-composition layer: alerts when ruview-densepose detects presence in a restricted zone without an accompanying PPE-camera-cog confirmation vector.387 KBEasyslip-fall-zonePre-fall risk detector. Fires when motion-variance drop, splash audio, and optional cautious-gait CSI all signal elevated slip risk.451 KBEasystructural-vibrationDetects dangerous vibrations in buildings or machines8 KBHard

🔬 Research — 12 modules

IDWhat it doesSizeDifficultyemotion-detectReads stress and calm from body language and breathing10 KBHardenergy-harvesterOptimize solar and battery for off-grid seed deployment6 KBMedgesture-languageRecognizes sign language gestures in real time12 KBHardghost-hunterFinds unexplained environmental anomalies — for fun10 KBHardhappiness-scoreEstimates well-being from movement and mood signals8 KBMedhyperbolic-spaceMaps data into curved space for tree-like structures12 KBHardmusic-conductorReads a conductor's gestures for tempo and dynamics12 KBHardplant-growthTracks plant growth rate and day/night cycles8 KBMedrain-detectDetects when rain starts, stops, and how heavy it is6 KBMedruview-denseposeFull body pose tracking from WiFi — no cameras needed50 KBHardsound-classifierIdentify sounds like glass break, alarm, or baby cry16 KBHardtime-crystalExperiments with repeating time-pattern symmetry12 KBHard

🤖 Ai — 15 modules

IDWhat it doesSizeDifficultyanomaly-attractorLearns what's normal and catches anything weird10 KBHardcognitive-pipelineFastGRNN anomaly gate + SmolLM2 sparse-LLM inference for on-device Pi Zero 2W cognitive events320 KBHarddtw-gesture-learnTeach custom hand gestures by showing examples14 KBMedewc-lifelongLearns new things without forgetting old lessons8 KBHardfederated-learningTrain AI across seeds without sharing raw data18 KBHardgoap-autonomyPlans and executes goals on its own14 KBHardmeta-adaptAutomatically tunes itself for best performance10 KBHardmicro-hnswFast on-device fingerprinting and classification12 KBMedneural-traderSpot market patterns and trends from live data20 KBHardpagerank-influenceFinds the most influential person in a group12 KBMedpattern-sequenceDetects daily routines and repeated habits10 KBMedrag-localSearch your documents using AI — runs on the seed14 KBMedspiking-trackerBrain-inspired tracker that runs on tiny hardware16 KBHardtemporal-logicEnforces safety rules on live event streams12 KBHardtime-series-forecastPredict sensor trends using historical patterns12 KBMed

🐝 Swarm — 11 modules

IDWhat it doesSizeDifficultyswarm-backup-restoreAuto-backup data to other seeds — one-click restore8 KBEasyswarm-cluster-monitorLive dashboard of every seed's health and status6 KBEasyswarm-consensusSeeds vote before making critical changes together16 KBHardswarm-delta-syncAuto-sync data between seeds — only sends changes8 KBMedswarm-deployInstall or remove cogs on all seeds at once10 KBMedswarm-distributed-storeSpread data across seeds and search them all at once14 KBHardswarm-edge-orchestratorManage all ESP32 sensor nodes from one place14 KBHardswarm-load-balancerSpread queries across seeds so no single one overloads10 KBMedswarm-mesh-managerFind, connect, and monitor all seeds on your network12 KBEasyswarm-mqtt-bridgeShare events between seeds over MQTT messaging6 KBEasyswarm-witness-federationShare tamper-proof audit trails across seeds12 KBHard

📡 Signal — 6 modules

IDWhat it doesSizeDifficultycoherence-gateFilters out noisy signals and keeps clean ones8 KBMedflash-attentionFocuses sensing on specific areas for better accuracy12 KBMedoptimal-transportMeasures motion using shape-aware signal comparison12 KBHardperson-matchingTells apart multiple people in the same room18 KBHardsparse-recoveryRecovers missing signal data from partial readings16 KBHardtemporal-compressShrinks old data to save memory without losing meaning14 KBMed

🌐 Network — 1 modules

IDWhat it doesSizeDifficultytailscaleReach the seed from anywhere via a private WireGuard mesh (Tailscale). Userspace mode — no root.700 KBMed

🛠️ Developer — 7 modules

IDWhat it doesSizeDifficultyadversarialDetects tampered or spoofed sensor signals4 KBEasycoherenceMonitors signal quality across multiple channels4 KBEasygestureCore gesture recognition building block for cogs6 KBMedinterference-searchSearches many possibilities at once for fast answers14 KBHardpsycho-symbolicReasons over knowledge graphs with multiple styles16 KBHardquantum-coherenceQuantum-inspired model for advanced signal states16 KBHardself-healing-meshKeeps sensor mesh running even when nodes drop out14 KBHard

ℹ️ Build your own cog: see ADR-100 for the packaging spec. The first cog this repo ships into the catalog lives in v2/crates/cog-pose-estimation/ (17-keypoint WiFi pose, ADR-101).

🔬 How It Works

WiFi routers flood every room with radio waves. When a person moves — or even breathes — those waves scatter differently. WiFi DensePose reads that scattering pattern and reconstructs what happened:

WiFi Router → radio waves pass through room → hit human body → scatter
    ↓
ESP32 mesh (4-6 nodes) captures CSI on channels 1/6/11 via TDM protocol
    ↓
Multi-Band Fusion: 3 channels × 56 subcarriers = 168 virtual subcarriers per link
    ↓
Multistatic Fusion: N×(N-1) links → attention-weighted cross-viewpoint embedding
    ↓
Coherence Gate: accept/reject measurements → stable for days without tuning
    ↓
Signal Processing: Hampel, SpotFi, Fresnel, BVP, spectrogram → clean features
    ↓
AI Backbone (RuVector): attention, graph algorithms, compression, field model
    ↓
Signal-Line Protocol (CRV): 6-stage gestalt → sensory → topology → coherence → search → model
    ↓
Neural Network: processed signals → 17 body keypoints + vital signs + room model
    ↓
Output: real-time pose, breathing, heart rate, room fingerprint, drift alerts

No training cameras required — the Self-Learning system (ADR-024) bootstraps from raw WiFi data alone. MERIDIAN (ADR-027) ensures the model works in any room, not just the one it trained in.

---

🏢 Use Cases & Applications

WiFi sensing works anywhere WiFi exists. No new hardware in most cases — just software on existing access points or a $8 ESP32 add-on. Because there are no cameras, deployments avoid privacy regulations (GDPR video, HIPAA imaging) by design.

Scaling: Each AP distinguishes ~3-5 people (56 subcarriers). Multi-AP multiplies linearly — a 4-AP retail mesh covers ~15-20 occupants. No hard software limit; the practical ceiling is signal physics.

Why WiFi sensing winsTraditional alternative🔒No video, no GDPR/HIPAA imaging rulesCameras require consent, signage, data retention policies🧱Works through walls, shelving, debrisCameras need line-of-sight per room🌙Works in total darknessCameras need IR or visible light💰$0-$8 per zone (existing WiFi or ESP32)Camera systems: $200-$2,000 per zone🔌WiFi already deployed everywherePIR/radar sensors require new wiring per room

Use CaseWhat It DoesHardwareKey MetricEdge ModuleElderly care / assisted livingFall detection, nighttime activity monitoring, breathing rate during sleep — no wearable compliance needed1 ESP32-S3 per room ($8)Fall alert <2sSleep Apnea, Gait AnalysisHospital patient monitoringContinuous breathing + heart rate for non-critical beds without wired sensors; nurse alert on anomaly1-2 APs per wardBreathing: 6-30 BPMRespiratory Distress, Cardiac ArrhythmiaEmergency room triageAutomated occupancy count + wait-time estimation; detect patient distress (abnormal breathing) in waiting areasExisting hospital WiFiOccupancy accuracy >95%Queue Length, Panic MotionRetail occupancy & flowReal-time foot traffic, dwell time by zone, queue length — no cameras, no opt-in, GDPR-friendlyExisting store WiFi + 1 ESP32Dwell resolution ~1mCustomer Flow, Dwell HeatmapOffice space utilizationWhich desks/rooms are actually occupied, meeting room no-shows, HVAC optimization based on real presenceExisting enterprise WiFiPresence latency <1sMeeting Room, HVAC PresenceHotel & hospitalityRoom occupancy without door sensors, minibar/bathroom usage patterns, energy savings on empty roomsExisting hotel WiFi15-30% HVAC savingsEnergy Audit, Lighting ZonesRestaurants & food serviceTable turnover tracking, kitchen staff presence, restroom occupancy displays — no cameras in dining areasExisting WiFiQueue wait ±30sTable Turnover, Queue LengthParking garagesPedestrian presence in stairwells and elevators where cameras have blind spots; security alert if someone lingersExisting WiFiThrough-concrete wallsLoitering, Elevator Count

Use CaseWhat It DoesHardwareKey MetricEdge ModuleSmart home automationRoom-level presence triggers (lights, HVAC, music) that work through walls — no dead zones, no motion-sensor timeouts2-3 ESP32-S3 nodes ($24)Through-wall range ~5mHVAC Presence, Lighting ZonesFitness & sportsRep counting, posture correction, breathing cadence during exercise — no wearable, no camera in locker rooms3+ ESP32-S3 meshPose: 17 keypointsBreathing Sync, Gait AnalysisChildcare & schoolsNaptime breathing monitoring, playground headcount, restricted-area alerts — privacy-safe for minors2-4 ESP32-S3 per zoneBreathing: ±1 BPMSleep Apnea, Perimeter BreachEvent venues & concertsCrowd density mapping, crush-risk detection via breathing compression, emergency evacuation flow trackingMulti-AP mesh (4-8 APs)Density per m²Customer Flow, Panic MotionStadiums & arenasSection-level occupancy for dynamic pricing, concession staffing, emergency egress flow modelingEnterprise AP grid15-20 per AP meshDwell Heatmap, Queue LengthHouses of worshipAttendance counting without facial recognition — privacy-sensitive congregations, multi-room campus trackingExisting WiFiZone-level accuracyElevator Count, Energy AuditWarehouse & logisticsWorker safety zones, forklift proximity alerts, occupancy in hazardous areas — works through shelving and palletsIndustrial AP meshAlert latency <500msForklift Proximity, Confined SpaceCivic infrastructurePublic restroom occupancy (no cameras possible), subway platform crowding, shelter headcount during emergenciesMunicipal WiFi + ESP32Real-time headcountCustomer Flow, LoiteringMuseums & galleriesVisitor flow heatmaps, exhibit dwell time, crowd bottleneck alerts — no cameras near artwork (flash/theft risk)Existing WiFiZone dwell ±5sDwell Heatmap, Shelf Engagement

WiFi sensing gives robots and autonomous systems a spatial awareness layer that works where LIDAR and cameras fail — through dust, smoke, fog, and around corners. The CSI signal field acts as a "sixth sense" for detecting humans in the environment without requiring line-of-sight.

Use CaseWhat It DoesHardwareKey MetricEdge ModuleCobot safety zonesDetect human presence near collaborative robots — auto-slow or stop before contact, even behind obstructions2-3 ESP32-S3 per cellPresence latency <100msForklift Proximity, Perimeter BreachWarehouse AMR navigationAutonomous mobile robots sense humans around blind corners, through shelving racks — no LIDAR occlusionESP32 mesh along aislesThrough-shelf detectionForklift Proximity, LoiteringAndroid / humanoid spatial awarenessAmbient human pose sensing for social robots — detect gestures, approach direction, and personal space without cameras always onOnboard ESP32-S3 module17-keypoint poseGesture Language, Emotion DetectionManufacturing line monitoringWorker presence at each station, ergonomic posture alerts, headcount for shift compliance — works through equipmentIndustrial AP per zonePose + breathingConfined Space, Gait AnalysisConstruction site safetyExclusion zone enforcement around heavy machinery, fall detection from scaffolding, personnel headcountRuggedized ESP32 meshAlert <2s, through-dustPanic Motion, Structural VibrationAgricultural roboticsDetect farm workers near autonomous harvesters in dusty/foggy field conditions where cameras are unreliableWeatherproof ESP32 nodesRange ~10m open fieldForklift Proximity, Rain DetectionDrone landing zonesVerify landing area is clear of humans — WiFi sensing works in rain, dust, and low light where downward cameras failGround ESP32 nodesPresence: >95% accuracyPerimeter Breach, TailgatingClean room monitoringPersonnel tracking without cameras (particle contamination risk from camera fans) — gown compliance via poseExisting cleanroom WiFiNo particulate emissionClean Room, Livestock Monitor

These scenarios exploit WiFi's ability to penetrate solid materials — concrete, rubble, earth — where no optical or infrared sensor can reach. The WiFi-Mat disaster module (ADR-001) is specifically designed for this tier.

Use CaseWhat It DoesHardwareKey MetricEdge ModuleSearch & rescue (WiFi-Mat)Detect survivors through rubble/debris via breathing signature, START triage color classification, 3D localizationPortable ESP32 mesh + laptopThrough 30cm concreteRespiratory Distress, Seizure DetectionFirefightingLocate occupants through smoke and walls before entry; breathing detection confirms life signs remotelyPortable mesh on truckWorks in zero visibilitySleep Apnea, Panic MotionPrison & secure facilitiesCell occupancy verification, distress detection (abnormal vitals), perimeter sensing — no camera blind spotsDedicated AP infrastructure24/7 vital signsCardiac Arrhythmia, LoiteringMilitary / tacticalThrough-wall personnel detection, room clearing confirmation, hostage vital signs at standoff distanceDirectional WiFi + custom FWRange: 5m through wallPerimeter Breach, Weapon DetectionBorder & perimeter securityDetect human presence in tunnels, behind fences, in vehicles — passive sensing, no active illumination to reveal positionConcealed ESP32 meshPassive / covertPerimeter Breach, TailgatingMining & undergroundWorker presence in tunnels where GPS/cameras fail, breathing detection after collapse, headcount at safety pointsRuggedized ESP32 meshThrough rock/earthConfined Space, Respiratory DistressMaritime & navalBelow-deck personnel tracking through steel bulkheads (limited range, requires tuning), man-overboard detectionShip WiFi + ESP32Through 1-2 bulkheadsStructural Vibration, Panic MotionWildlife researchNon-invasive animal activity monitoring in enclosures or dens — no light pollution, no visual disturbanceWeatherproof ESP32 nodesZero light emissionLivestock Monitor, Dream Stage

---

Every WiFi signal that passes through a room creates a unique fingerprint of that space. WiFi-DensePose already reads these fingerprints to track people, but until now it threw away the internal "understanding" after each reading. The Self-Learning WiFi AI captures and preserves that understanding as compact, reusable vectors — and continuously optimizes itself for each new environment.

What it does in plain terms:

• Turns any WiFi signal into a 128-number "fingerprint" that uniquely describes what's happening in a room

• Learns entirely on its own from raw WiFi data — no cameras, no labeling, no human supervision needed

• Recognizes rooms, detects intruders, identifies people, and classifies activities using only WiFi

• Runs on an $8 ESP32 chip (the entire model fits in 55 KB of memory)

• Produces both body pose tracking AND environment fingerprints in a single computation

Key Capabilities

WhatHow it worksWhy it mattersSelf-supervised learningThe model watches WiFi signals and teaches itself what "similar" and "different" look like, without any human-labeled dataDeploy anywhere — just plug in a WiFi sensor and wait 10 minutesRoom identificationEach room produces a distinct WiFi fingerprint patternKnow which room someone is in without GPS or beaconsAnomaly detectionAn unexpected person or event creates a fingerprint that doesn't match anything seen beforeAutomatic intrusion and fall detection as a free byproductPerson re-identificationEach person disturbs WiFi in a slightly different way, creating a personal signatureTrack individuals across sessions without camerasEnvironment adaptationMicroLoRA adapters (1,792 parameters per room) fine-tune the model for each new spaceAdapts to a new room with minimal data — 93% less than retraining from scratchMemory preservationEWC++ regularization remembers what was learned during pretrainingSwitching to a new task doesn't erase prior knowledgeHard-negative miningTraining focuses on the most confusing examples to learn fasterBetter accuracy with the same amount of training data

Architecture

WiFi Signal [56 channels] → Transformer + Graph Neural Network
                                  ├→ 128-dim environment fingerprint (for search + identification)
                                  └→ 17-joint body pose (for human tracking)

Quick Start

# Step 1: Learn from raw WiFi data (no labels needed)
cargo run -p wifi-densepose-sensing-server -- --pretrain --dataset data/csi/ --pretrain-epochs 50

# Step 2: Fine-tune with pose labels for full capability
cargo run -p wifi-densepose-sensing-server -- --train --dataset data/mmfi/ --epochs 100 --save-rvf model.rvf

# Step 3: Use the model — extract fingerprints from live WiFi
cargo run -p wifi-densepose-sensing-server -- --model model.rvf --embed

# Step 4: Search — find similar environments or detect anomalies
cargo run -p wifi-densepose-sensing-server -- --model model.rvf --build-index env

Training Modes

ModeWhat you needWhat you getSelf-SupervisedJust raw WiFi dataA model that understands WiFi signal structureSupervisedWiFi data + body pose labelsFull pose tracking + environment fingerprintsCross-ModalWiFi data + camera footageFingerprints aligned with visual understanding

Fingerprint Index Types

IndexWhat it storesReal-world useenv_fingerprintAverage room fingerprint"Is this the kitchen or the bedroom?"activity_patternActivity boundaries"Is someone cooking, sleeping, or exercising?"temporal_baselineNormal conditions"Something unusual just happened in this room"person_trackIndividual movement signatures"Person A just entered the living room"

Model Size

ComponentParametersMemory (on ESP32)Transformer backbone~28,00028 KBEmbedding projection head~25,00025 KBPer-room MicroLoRA adapter~1,8002 KBTotal~55,00055 KB (of 520 KB available)

The self-learning system builds on the AI Backbone (RuVector) signal-processing layer — attention, graph algorithms, and compression — adding contrastive learning on top.

See docs/adr/ADR-024-contrastive-csi-embedding-model.md for full architectural details.

---

🧩 Claude Code & Codex Plugin

RuView ships a Claude Code plugin (and Codex prompt mirror) that wraps the whole workflow — onboarding, ESP32 setup, configuration, sensing apps, model training, advanced multistatic sensing, CLI/API/WASM, mmWave radar, and witness verification — as 9 skills, 7 /ruview-* commands, and 3 agents. It lives in plugins/ruview/; the marketplace manifest is .claude-plugin/marketplace.json at the repo root.

# In Claude Code — add this repo as a plugin marketplace, then install:
/plugin marketplace add ruvnet/RuView
/plugin install ruview@ruview

# Or try it for one session without installing (from a local clone of the repo):
claude --plugin-dir ./plugins/ruview

# Then, in Claude Code:
#   /ruview-start      → onboarding (Docker demo / repo build / live ESP32)
#   /ruview-flash      → build + flash ESP32 firmware
#   /ruview-provision  → provision WiFi creds, sink IP, channel/MAC, mesh slots
#   /ruview-app        → run a sensing application (presence / vitals / pose / sleep / MAT / point cloud)
#   /ruview-train      → train / evaluate / publish a model (incl. GPU on GCloud)
#   /ruview-advanced   → multistatic / tomography / cross-viewpoint / mesh-security
#   /ruview-verify     → tests + deterministic proof + witness bundle

Codex (OpenAI CLI): cp plugins/ruview/codex/prompts/*.md ~/.codex/prompts/ — the seven /ruview-* commands are mirrored as Codex prompts; plugins/ruview/codex/AGENTS.md carries the project rules. See plugins/ruview/codex/README.md.

Verify the plugin structure: bash plugins/ruview/scripts/smoke.sh. Full details: plugins/ruview/README.md.

---

📖 Documentation

DocumentDescriptionUser GuideStep-by-step guide: installation, first run, API usage, hardware setup, trainingBuild GuideBuilding from source (Rust and Python)Home Assistant + Matter IntegrationWorks with Home Assistant via MQTT auto-discovery + Works with Matter (Apple Home / Google Home / Alexa / SmartThings) — full entity catalog, 3 starter blueprints, Lovelace dashboards, privacy mode, threshold tuning (ADR-115).BFLD — Beamforming Feedback Layer for DetectionNew privacy-gated WiFi sensing layer that measures + structurally prevents identity leakage from 802.11ac/ax Beamforming Feedback Information. Three type-enforced invariants (raw BFI never exits node, identity embedding is in-RAM-only, cross-site correlation cryptographically impossible via per-site BLAKE3 keyed hash + daily rotation). Ships full operator surface (BfldPipeline, BfldPipelineHandle, Soul Signature SoulMatchOracle integration), MQTT topic router + HA-DISCO + availability + LWT, 3 operator HA blueprints, two runnable examples, eclipse-mosquitto:2 CI service container. 327+ tests. ADR-118 umbrella + sub-ADRs 119/120/121/122/123. Research dossier: docs/research/BFLD/ (11 files, 13,544 words).SENSE-BRIDGE — rvagent MCP serverDual-transport MCP server (@ruvnet/rvagent) bridging the RuView sensing stack to AI agents (Claude Code, Cursor, ruflo swarms). 6 tools wired: ruview.presence.now, ruview.vitals.get_{breathing,heart_rate,all}, ruview.bfld.last_scan, ruview.bfld.subscribe. stdio + Streamable HTTP (POST /mcp, Origin-validated, bearer-token auth, 127.0.0.1 bind). Full 20-tool Zod schema barrel + 5 RUVIEW-POLICY governance tools. 93 tests. ADR-124. Try: npx @ruvnet/rvagent stdio.Semantic Primitives — Precision/RecallPer-primitive F1 on the held-out paired-capture set: someone-sleeping, possible-distress, room-active, elderly-inactivity-anomaly, meeting, bathroom, fall-risk, bed-exit, no-movement, multi-room.Claude Code / Codex PluginThe ruview plugin + marketplace — skills, /ruview-* commands, agents, and the Codex prompt mirrorArchitecture Decisions96 ADRs — why each technical choice was made, organized by domain (hardware, signal processing, ML, platform, infrastructure)Domain Models8 DDD models (RuvSense, Signal Processing, Training Pipeline, Hardware Platform, Sensing Server, WiFi-Mat, CHCI, rvCSI) — bounded contexts, aggregates, domain events, and ubiquitous languagervCSI — edge RF sensing runtimeRust-first / TypeScript-accessible / hardware-abstracted CSI runtime: multi-source ingestion (incl. real nexmon_csi .pcap from a Raspberry Pi 5 / Pi 4 / Pi 3B+ — CYW43455 / BCM43455c0) → validation → DSP → typed events → RuVector RF memory (ADR-095, ADR-096, domain model). Now its own repo — ruvnet/rvcsi — vendored here under vendor/rvcsi; 9 rvcsi-* crates on crates.io, @ruv/rvcsi on npm, plus a Claude Code plugin.Desktop AppWIP — Tauri v2 desktop app for node management, OTA updates, WASM deployment, and mesh visualizationruview-swarmDrone swarm control system (ADR-148) — hierarchical-mesh topology, Raft consensus, MARL, CSI sensing payload, MAVLink/PX4/ArduPilot compatibility, Ruflo AI-agent integrationMedical ExamplesContactless blood pressure, heart rate, breathing rate via 60 GHz mmWave radar — $15 hardware, no wearableExtended DocumentationLatest additions, key features, installation, quick start, signal processing, training, CLI, testing, deployment, and changelog

---

🚧 Beta software

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.

Contributions and bug reports welcome at Issues.

📄 License

MIT License — see LICENSE for details.

🤝 Creator Affiliate Program

For TikTok · Instagram · YouTube creators — earn 25% on every Cognitum sale you refer. The RuFlo, RuView, and RuVector videos you're already making have done millions of views; get paid for the orders they drive. Click-tracking activates instantly; commissions activate after a quick manual review (usually under 24 hours).

Apply now → cognitum.one/affiliate

📞 Support

GitHub Issues | Discussions | PyPI

---

WiFi DensePose — Privacy-preserving human pose estimation through WiFi signals.