Object Detection
Finds and labels every object in view.
Features
One App for Cameras, Detections and Actions.
AI Vision Bots is the AiServa app that runs your site cameras. Every setting lives in the cloud with history, and a signed copy runs on the AI Vision Bot so the site keeps working when the internet does not.
Feature Areas
Five Areas, One Place to Manage Them.
Cameras and NVR
ONVIF and RTSP cameras, 24/7 recording, clips and timeline playback.
Read more
Detections and Models
Trained models with their classes, on the bot or on AiServa.
Read more
Rules and Automation
Rules, jobs, workflows and an AI assistant that writes them.
Read more
Live View
WebRTC straight from the site, relay only when needed, PTZ.
Read more
Security
Signed updates and config, sealed passwords, audited remote access.
Read morePlatform
What Every Site Gets
One Command Pairing
Windows, macOS or Linux, x86 or ARM, with or without a GPU. The installer sets up a boot service and the AI Vision Bot appears in AiServa.
Configured in the Cloud
Cameras, Detections, rules and storage are set in AiServa, signed, and sent to the AI Vision Bot. Every change is kept with who made it.
Runs on Site
Detection, recording and the rule engine run on the AI Vision Bot, so alerts still fire when the site is offline.
Full NVR
Continuous 24/7 recording, event clips with pre and post roll, schedules, timeline playback and MP4 export.
AI Rule Assistant
Describe a rule in plain words. The assistant proposes it, you confirm, then it is saved.
Secure by Design
Outbound only connection, signed updates and configuration, sealed camera passwords and an audit log.
Core Capabilities
Twelve Building Blocks, Every Use Case.
Every use case combines these twelve capabilities. We build each one once and reuse it everywhere, so a new use case is configuration and training, not a new product.
Object Tracking
Keeps one ID per object across frames.
Counting
Counts items, animals or vehicles across a line or zone.
Classification
Grades ripeness, quality, colour or condition.
Segmentation
Marks exact pixels of cracks, smoke or water.
OCR and Codes
Reads containers, meters, barcodes and labels.
Pose Estimation
Finds body keypoints for falls, gestures and exercise.
Action Recognition
Understands falling, tipping, smoking and drowsiness.
Anomaly Detection
Learns normal and flags anything else.
Thermal and Depth
Sees heat in the dark and measures distance.
Visual Measurement
Estimates level, volume and size from calibrated views.
Sound and Vision
Combines audio cues like an alarm call or a cry with video.
The VYROX Vision Engine
Ten Engines, One Brain.
Every layer is a VYROX AI engine, tuned on your own footage and tested with you before anything ships. Inference runs on an edge box at your site, so video can stay where it is.
| Layer | VYROX Engine | Best For |
|---|---|---|
| Object Detection | VYROX HawkEyeNano, Swift, Pro | Fast, accurate boxes on every frame |
| Open Vocabulary | VYROX OmniSightFind anything you describe | New objects described in words |
| Segmentation | VYROX PixelBladePixel-exact masks | Cracks, smoke, water lines, labelling |
| Tracking | VYROX TrailLockOne ID, start to finish | Counting, dwell time, IDs through occlusion |
| Vision Language | VYROX VisionMindAsk your cameras | Grounded queries and incident descriptions |
| Pose and Action | VYROX MotionIQBody, face and hands | Falls, gestures, drowsiness, exercise |
| OCR | VYROX ReadSightReads what it sees | Containers, meters, labels, spines |
| Anomaly | VYROX FlawHunterFinds the odd one out | Defects with few bad samples |
| Inference | VYROX EdgeCoreRuns on site | Many cameras per edge box |
| Data and Training | VYROX ModelForgeLearns from your site | Labelling, error review, retraining on your site |
Show Us One Camera. We Will Show You What AI Can See.
AI Vision Bots is available at selected sites. Send a short clip from your site and one sentence on the problem, and the VYROX AI team will tell you what a Detection could do there.