Skip to content
Fregata

Add your first camera

Once the app is activated, the next step is to point it at one camera and verify the whole pipeline — capture, decode, detect, record — is working.

What you’ll need

Section titled “What you’ll need”
  • An IP camera that exposes an RTSP stream (most do — typical URL shapes are rtsp://user:pass@CAMERA_IP:554/h264Preview_01_main for Reolink, rtsp://user:pass@CAMERA_IP:554/cam/realmonitor?channel=1&subtype=0 for Dahua/Amcrest, etc. — see Cameras for a brand-by-brand cheatsheet).
  • The camera’s IP address and credentials.
  • A network path between the Mac and the camera. LAN is the common case; if your camera is on a separate VLAN you’ll need a route or firewall hole between them.

Steps

Section titled “Steps”
  1. Open the Fregata web UI from the menu-bar tray (Open Frigate Web UI, or ⌘O). It opens http://localhost:8971 in your default browser.
  2. In the web UI, go to Settings → Camera Management.
  3. Click + Add camera. The camera wizard opens.
  4. Give the camera a short, lowercase name (front_porch, driveway, garage — whatever you want it called in URLs and recordings).
  5. Paste the RTSP URL of the main (high-resolution) stream.
  6. If the camera offers a sub-stream (lower resolution, separate URL), paste that too — Fregata uses the sub-stream for detection and the main stream for recordings, which keeps CPU and disk usage way down.
  7. Save. Fregata reloads its config and the camera tile appears on the live dashboard.

Add-camera wizard with RTSP URL field

The camera should appear in the live tile grid within a few seconds. Detection runs automatically on every camera by default; you’ll see green bounding boxes around moving objects with the class label and confidence score.

Verifying detection is on the ANE

Section titled “Verifying detection is on the ANE”

The first time a model runs, Fregata times two warmup inferences and classifies the result. Look at the Detector row in the menu-bar tray (or the System tab in the web UI):

  • ~1–4 ms per frame — detection is on the Apple Neural Engine. This is the correct, intended path.
  • 5–15 ms per frame — detection is on the GPU (Metal). This happens if the bundled model uses ops the ANE doesn’t support, or if you forced inference_backend: gpu in config.
  • 50+ ms per frame — detection has fallen back to CPU. Something went wrong; restart the app and check the Open Crash Log entry in the tray for an ane_init or coreml_session error.

For a deeper look, see Performance.

Where Fregata stores recordings

Section titled “Where Fregata stores recordings”

By default, recordings live under:

~/Fregata/media/recordings/

with sub-paths organised by camera and date. Event clips live under ~/Fregata/media/clips/ and exports under ~/Fregata/media/exports/.

You can change the Media location at any time from Settings → Folders → Change Media Location… in the tray menu. Fregata will move existing files for you on the next launch.

Retention is per-camera and configured in config.yml; defaults are 14 days for recordings and longer for event clips. See Recordings & retention to tune this for your disk budget.

Next steps

Section titled “Next steps”