NVR with realtime local object detection for IP cameras
Go to file
Jan Čermák cffd71906a
Update Hailo library to v4.20.1
The upcoming HAOS 15.0 will use Hailo driver v4.20.1. The current dev
has the older patch release (v4.20.0) staged for future versions, but
since new Frigate build will be needed for future compatibility, it
makes sense to sync at the latest one.

Link: https://github.com/home-assistant/operating-system/pull/3922
2025-03-11 15:56:41 +01:00
.cspell Improve notifications (#16632) 2025-02-17 07:19:03 -07:00
.devcontainer Initial implementation of D-FINE model via ONNX (#16772) 2025-02-24 08:56:01 -07:00
.github Bump actions/setup-python from 5.3.0 to 5.4.0 (#16184) 2025-03-07 06:47:15 -07:00
.vscode
config
docker Update Hailo library to v4.20.1 2025-03-11 15:56:41 +01:00
docs Add docs for user roles (#17093) 2025-03-11 08:05:42 -06:00
frigate Add self return for pydantic (#17091) 2025-03-11 07:57:00 -05:00
migrations UI viewer role (#16978) 2025-03-08 10:01:08 -06:00
notebooks Added code to download weights from new host (#15087) 2024-11-20 05:06:22 -06:00
web Face multi select (#17068) 2025-03-10 10:01:52 -05:00
.dockerignore
.gitignore
.pylintrc
audio-labelmap.txt
benchmark_motion.py
benchmark.py Simplify plus submit (#15941) 2025-01-11 07:04:11 -07:00
CODEOWNERS
cspell.json
docker-compose.yml Fix prometheus client exporter (#16620) 2025-02-17 06:17:15 -07:00
labelmap.txt
LICENSE
Makefile Update version 2025-02-08 12:47:01 -06:00
netlify.toml
package-lock.json
process_clip.py Simplify plus submit (#15941) 2025-01-11 07:04:11 -07:00
pyproject.toml
README.md

logo

Frigate - NVR With Realtime 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.

Use of a Google Coral Accelerator is optional, but highly recommended. The Coral will outperform even the best CPUs and can process 100+ FPS with very little overhead.

  • Tight integration with Home Assistant via a custom component
  • Designed to minimize resource use and maximize performance by only looking for objects when and where it is necessary
  • Leverages multiprocessing heavily with an emphasis on realtime over processing every frame
  • Uses a very low overhead motion detection to determine where to run object detection
  • Object detection with TensorFlow runs in separate processes for maximum FPS
  • Communicates over MQTT for easy integration into other systems
  • Records video with retention settings based on detected objects
  • 24/7 recording
  • Re-streaming via RTSP to reduce the number of connections to your camera
  • WebRTC & MSE support for low-latency live view

Documentation

View the documentation at https://docs.frigate.video

Donations

If you would like to make a donation to support development, please use Github Sponsors.

Screenshots

Live dashboard

Live dashboard

Streamlined review workflow

Streamlined review workflow

Multi-camera scrubbing

Multi-camera scrubbing

Built-in mask and zone editor

Multi-camera scrubbing