To celebrate the initial release of Fregata, all trial license keys will remain valid until October 31, 2026! 🎉
Native NVR for Apple Silicon
Fregata is a private, local-first network video recorder for macOS built on the fantastic open source Frigate NVR. Object detection on the Apple Neural Engine. Hardware accelerated decode and encode through VideoToolbox. One app - drag to Applications, done.
30-day free trial · One-time payment · No subscription · Works offline
localhost:8971
Live Review Export
Default 11 / 12 live · 1.6 ms/frame
REC
Front Porch
2160p · 30fps
person · 0.94
REC
Driveway
1440p · 20fps
car · 0.93
REC
Backyard
1080p · 15fps
REC
Garage
1080p · 15fps
car · 0.97
REC
Side Gate
1080p · 15fps
01
Video, object detection, recordings - none of it leaves your Mac. No Fregata account exists to hand your data to.
02
Detection runs on the Neural Engine via CoreML. Video Decode and encode run on the dedicated Media Engine via VideoToolbox.
03
$10 one-time. A full year of updates that never stop working even if your license expires. No subscription, no price per camera, no features hidden behind paywalls.
Setup
1
Any RTSP-capable camera - Reolink, Amcrest, Hikvision, Unifi, Dahua. Fregata also speaks WebRTC and MSE for low-latency live view.
rtsp://192.168.1.42:554/stream
connected · 2160p · 30fps
connected · 1440p · 20fps
connected · 1080p · 15fps
2
Point Fregata at a recordings folder. Define zones and detection rules in YAML, or define them in the web UI.
cameras: front_yard: detect: objects: [person, car, dog] zones: walkway: coordinates: 0,420,640,... objects: [person] record: retain: { days: 14 }
3
Open the menu bar icon. Click Open Web UI, or hit localhost:8971 from any device. Multi-camera scrubbing, event timeline, motion masks - the works.
Local LAN192.168.X.X:8971
Browser - Externalfregata.yourdomain.com
Home Assistantvia Frigate HACS
Built for M-Series Apple Silicon
Apple Neural Engine - CoreML
Object detection runs on the Apple Neural Engine via a custom CoreML detector written in Rust - not your CPU, not your GPU. Lower latency, lower power, cooler fans.
~1ms
per-frame detection latency · M4 · YOLOv9-tiny 320
Bundled model: YOLOv9-tiny, 320×320. Drop in your own ONNX model anytime - including full support for Frigate+ models.
Media Engine - VideoToolbox
Hardware accelerated H.264 and HEVC decode and encode on the dedicated media engine, no low-resolution detection sub-streams required. Your CPU stays free for other apps.
4K@15fps · <2% CPU
per camera, M4, decode + detect pipeline
Auto-detected at first launch - no codec configuration, no accelerator planning, no external GPU.
CPU cluster
P-cores + E-cores. Mostly idle while Fregata runs.
Neural Engine
Object detection, every frame. CoreML.
GPU
Available for the OS and other apps.
Media Engine
VideoToolbox H.264/HEVC decode + encode.
Features
Synchronized scrubbing across cameras. WebRTC and MSE for sub-second latency in the browser.
Only alert on motion that matters. Pixel-precise polygons, per-object thresholds, ignore-zones.
Retention rules per camera and per object. Continuous, motion-only, or event-only - your choice.
People, vehicles, animals, packages, and more - all on-device, on the Neural Engine.
Full support via the official Frigate HACS integration. MQTT-native. Works out of the box.
Sub-second latency live view in any browser. No Flash, no plugin, no transcoding hop.
One connection per camera, fanned out via go2rtc - fewer streams to your hardware.
Start, stop, status. Fregata settings. The whole thing lives in your menu bar, not your dock.
No Fregata account, no cloud. Pull the network cable - it keeps recording.
Built on the open-source Frigate project. Inspect the engine, contribute upstream.
The interface
localhost:8971
Default 11 / 12 live · 1.6 ms/frame
REC
Front Porch
2160p · 30fps
person · 0.94
REC
Driveway
1440p · 20fps
car · 0.93
REC
Backyard
1080p · 15fps
REC
Garage
1080p · 15fps
car · 0.97
REC
Side Gate
1080p · 15fps
Doorbell
offline · 4 min
localhost:8971/#driveway
Review Recordings Today All cameras · 4
Driveway · 2:14:08 PM car · 0.87
00:42 / 03:24 1×
2:002:152:302:453:00
Front Porch
Driveway
Backyard
Garage
Alert Detection Motion
localhost:8971/explore
Snapshot Clip Sub labels
Front Porch 2:14:08 PM person · 0.94
Compare
If you’re on a Mac, this is what the landscape looks like. We’ve tried to be fair - corrections welcome on GitHub.
Recommended on macOS
Fregata
Performance on Apple Silicon
ANE detection + VideoToolbox decode/encode, fully native arm64.
Ease of use on macOS
Drag to Applications. Menu bar icon. No Docker, no VMs, no terminal.
FrigateDocker on Mac
Performance on Apple Silicon
Docker Desktop’s Linux VM blocks access to the Neural Engine and VideoToolbox. Coral USB helps but can be hard to configure on Mac.
Ease of use on macOS
Docker Desktop running a Virtual Machine, hardware planning for accelerators, manual model setup.
Scrypted
Performance on Apple Silicon
Runs natively on macOS; the CoreML plugin uses the Apple Neural Engine. Recording requires the separate paid Scrypted NVR subscription.
Ease of use on macOS
Homebrew install or a native desktop app. HomeKit Secure Video bridging is the strong point.
Blue Iris
Performance on Apple Silicon
Windows-only. No native path on Apple Silicon Macs — access is via a web UI pointed at a separate Windows PC.
Ease of use on macOS
Requires a separate Windows PC running Blue Iris. The web UI is accessible from any Mac browser.
SynologySurveillance Station
Performance on Apple Silicon
Runs on the Synology NAS, not on the Mac. Performance is bound to NAS hardware.
Ease of use on macOS
Setup requires configuration in the Synology UI. However the Web UI is perfectly accessible from macOS.
| Frigate Docker | Scrypted | Blue Iris | Synology | |
|---|---|---|---|---|---|
| Native macOS app | ✓ Signed .app | ✗ Docker only | ✓ Desktop app / Homebrew | ✗ Windows only | ✗ Runs on NAS |
| Apple Neural Engine (CoreML) | ✓ Built-in | ✗ Blocked by Docker VM | — Via CoreML plugin | ✗ | ✗ |
| VideoToolbox decode/encode | ✓ Auto-detected | ✗ Blocked by Docker VM | — Via ffmpeg | ✗ | ✗ |
| No detection sub-streams required | ✓ Full-res detection | ✗ Sub-stream needed | ✗ Sub-stream needed | ✗ Sub-stream needed | ✗ Sub-stream needed |
| Custom Trained AI Models | ✓ (Frigate+) | ✓ (Frigate+) | — Via ONNX plugin | ✗ | ✗ |
| RTSP camera support | ✓ | ✓ | ✓ | ✓ | ✓ |
| Local-only / no cloud required | ✓ | ✓ | ✓ | ✓ | ✓ |
| Open-source core | ✓ Frigate upstream (MIT) | ✓ MIT | — Core only; NVR plugin paid & proprietary | ✗ Proprietary | ✗ Proprietary |
| Home Assistant integration | ✓ Frigate HACS | ✓ Frigate HACS | ✓ Plugin | ✓ via MQTT | ✗ Community via Scrypted |
| HomeKit Live View | ✓ Via go2rtc HAP | ✓ Via go2rtc HAP | ✓ +HKSV | ✗ | ✗ |
| Pricing | $10 one-time | Free | $10 per cam per year NVR subscription | $39.95–99.95 + $44.95/yr for updates | 2 cameras free, then ~$50–60 / camera |
| Best for | Mac users who want Frigate with extreme performance and without Docker | Linux users with Coral or NVIDIA hardware | HomeKit-first households unifying many brands | Windows users with large deployments | Existing Synology NAS owners |
If you’re already happy on Frigate, Scrypted, Blue Iris, or Synology - keep what works. Fregata exists for Mac owners who want the Frigate engine, hardware accelerated by Apple Silicon and packaged the way macOS apps should be packaged.
Pricing
$ 10 USD
Pay once. All updates released within 12 months of purchase never stop working, yours forever.
.appSecure checkout
Signed & notarized by Apple Stripe checkout Made on a Mac
FAQ
Frigate is the open-source, Docker-based NVR project. Fregata is a commercial native macOS port of Frigate, repackaged as a signed, notarized .app that runs natively on Apple Silicon with extreme performance - no Docker, no VMs, no terminal setup. (New here? See how to run Frigate on a Mac.)
Fregata adds Apple Neural Engine detection, VideoToolbox hardware accelerated video decode/encode, and hundreds of other performance optimizations for Apple Silicon (see docs.fregata.app for more). The Frigate Python core is open source; the macOS runtime port, Apple Silicon optimizations, and the Fregata brand are proprietary.
You’re paying for the performance and ease of use of the macOS port, the bundle, the Apple Silicon work - a custom CoreML detector written in Rust, VideoToolbox integration for hardware accelerated video decoding and encoding, a native process supervisor, hardware accelerated frame crop and zoom for object detection - and ongoing maintenance and updates.
If you’d rather run Docker, Frigate is free and excellent - go to frigate.video.
An Apple Silicon Mac (M1 or later) running macOS 13 (Ventura) or newer. Fregata does not support Intel Macs - the whole point of the port is leveraging the Apple Neural Engine and the hardware accelerated video decoding/encoding provided by Apple Silicon.
Anything that speaks RTSP - that’s almost every IP camera on the market today, including Reolink, Amcrest, Hikvision, Dahua, and Unifi Protect. The bundled go2rtc proxy also handles WebRTC, ONVIF, RTMP, and HLS, plus cloud-API cameras directly: Ring, Google Nest, Wyze, Tapo / TP-Link, Tuya, and HomeKit-paired cameras all work without RTSP. The full source-type list is on go2rtc’s README.
Yes. Fregata performs a license check periodically, but can operate without any contact with our license servers once the license is validated on startup. All detection, recording, and playback happens entirely on your Mac.
License validation pings only. We never see your video, your camera URLs, or your detection events. There is no Fregata cloud account.
Yes, Fregata uses Frigate as its core and is fully compatible with Frigate+ and Frigate+ custom trained models. For more information about Frigate+, see https://frigate.video/plus/
No. Due to the performance of Apple Silicon, a Mac can easily decode full-resolution streams from your cameras and run object detection on the full-resolution frames allowing object detection to run with greater accuracy and capture small or distant objects. In our testing, Fregata can easily handle object detection on 8x (or more) 4K cameras using only a base M4 Mac Mini.
Yes. Drop any compatible ONNX model into your config directory and point Fregata at it. The bundled default is YOLOv9-tiny at 320×320, optimized for the Neural Engine. Fregata also works with Frigate+ models natively.
Yes. A license activates on one Mac at a time, and you can transfer it between Macs up to 3 times per 30 days from your license page - no support ticket required. For larger or fleet deployments, get in touch.
No. App Store sandboxing forbids spawning child processes like we need to - Fregata needs to run ffmpeg, nginx, and go2rtc as subprocesses to do its job. We also need to manage the RAM disk and shared memory in a way App Store apps cannot. Direct DMG distribution with Apple notarization is the right model for software like this.
Your installed version keeps working forever. You stop receiving new updates unless you renew for another year of updates (also $10) - but nothing breaks, no features are remotely disabled, and your existing recordings remain fully accessible.
Community discussion and bug reports happen on GitHub Discussions. Paid customers also get email support - reply to your license email for direct support.
Yes. Fregata is fully compatible with the official Frigate Home Assistant integration. Install it from HACS, point it at your Mac’s IP, done.
A note on the name
Frigate is the open-source NVR project by Frigate, Inc. that this software is built on. Frigate relies on a Docker-based system and has set the standard for local, AI-powered camera recording.
Fregata is a native macOS port of Frigate and the docker runtime that manages the external process supervisor, RAM disk, shared memory system and much more. All redesigned and optimized to run as a self-contained .app bundle and unlock the raw power of Apple Silicon - no Docker, no Virtual Machines, no terminal required.
Fregata is the scientific genus that frigatebirds belong to. They have the highest wing-to-body weight ratio of any bird, soar for weeks without landing, always watching for prey.
Frigate® and the Frigate NVR brand are trademarks of Frigate, Inc. Fregata is an independent derivative - not affiliated with or endorsed by Frigate, Inc.
Ready when you are
macOS 13 or later · Apple Silicon · Signed by Apple
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。