Everything you need to go from download to live cameras with AI detection. Most setups complete in under 15 minutes.
This guide walks you through installing LookoutNVR, connecting your first camera, and enabling AI detection. The whole process typically takes 10-15 minutes.
Windows (10/11, 64-bit): Download the installer from the download page and run it. LookoutNVR installs as a Windows service and opens automatically in your browser.
Linux (Ubuntu 22.04+ / Debian 11+):
wget https://lookoutnvr.com/dist/lookoutnvr-3.51-amd64.deb
sudo dpkg -i lookoutnvr-3.51-amd64.deb
sudo systemctl enable --now lookoutnvr
After install, the service starts automatically. Open your browser:
http://localhost:8088
http://192.168.1.50:8088Go to Settings → Cameras → Add Camera. You have two options:
After adding, select a recording mode: Continuous, Motion-triggered, or AI-event-only. The camera appears in your live view immediately.
Go to Settings → AI Engine. Select your GPU from the dropdown (NVIDIA CUDA, AMD ROCm, Intel OpenVINO, or CPU). Click Load Model — the YOLO model downloads once (~80 MB) and is cached locally.
# GPU detected automatically. Example output:
AI Engine: NVIDIA RTX 3070 (CUDA)
Model: YOLOv8m — loaded in 2.1s
Inference: 14ms avg · 34 cameras active
Enable detection per camera under Settings → Cameras → [Camera Name] → AI. Choose which classes to detect (Person, Vehicle, Animal) and set confidence thresholds.
Your cameras are recording, AI is running, and events are being logged. From here you can set up motion zones, configure push notifications, or set up storage retention policies.