Apps / Security
Frigate
NVR with realtime local object detection for IP cameras
A complete and local NVR designed for Home Assistant with AI object detection. Uses OpenCV and Tensorflow to perform realtime object detection locally for IP cameras.
CategorySecurity
Memory~2GB
Module
frigateInstalling it
Open the dashboard, go to Apps, press Add on it and apply the change. Or from a terminal on the box:
sudo homebox install frigateWhere to open it
| Service | Port | First login |
|---|---|---|
| Frigate | :5001 | No account by default. Set one in config.yml before this is reachable from anywhere but your LAN. |
Open it at your box's address with that port — the dashboard links to it directly once it is running.
Good to know
- Until you add a camera it runs in SAFE MODE: the page opens and reports healthy, but it is running on defaults, because
camerasis a required field. Use the config editor in the UI to add one, then restart the app - Detection on the CPU is expensive: roughly one core per camera. A Coral TPU on USB turns that into almost nothing, and is the single upgrade that matters here
- Recordings go to the media pool under frigate/, so they land on the NAS rather than filling the system disk
- Use each camera's SUB stream for detection and the main stream for recording. Running detection on 4K is how people conclude Frigate is slow