NVR with realtime local object detection for IP cameras
Go to file
Josh Hawkins 592141daaa
Increase ffmpeg timeout to 10 seconds (#17831)
FFmpeg adds an extra delay for the first start of the stream. For some cameras the stream start can be 1 second, for some cameras it can be more than 5 seconds. Frigate by default used a timeout of 5 seconds and drops the connection without waiting for a response from go2rtc. Originally suggested by @AlexxIT in https://github.com/AlexxIT/go2rtc/issues/1633
2025-04-21 07:38:51 -05:00
.cspell Various fixes (#17342) 2025-03-24 12:25:36 -05:00
.devcontainer
.github Move database and config from homeassistant /config to addon /config (#16337) 2025-03-24 09:05:59 -05:00
.vscode Fix vscode launch configuration (#13795) 2024-09-17 10:42:10 -05:00
config
docker Increase ffmpeg timeout to 10 seconds (#17831) 2025-04-21 07:38:51 -05:00
docs Link fixed in restream docs (#17814) 2025-04-19 16:49:52 -05:00
frigate Increase ffmpeg timeout to 10 seconds (#17831) 2025-04-21 07:38:51 -05:00
migrations Small tweaks (#17168) 2025-03-15 07:11:45 -06:00
notebooks Update yolonas docs (#17736) 2025-04-16 09:01:15 -06:00
web Move another username to i18n key (#17820) 2025-04-19 20:53:23 -05:00
.dockerignore
.gitignore
.pylintrc
audio-labelmap.txt
benchmark_motion.py
benchmark.py Improve async object detector support (#17712) 2025-04-15 08:55:38 -05:00
CODEOWNERS
cspell.json
docker-compose.yml Devcontainer: update Mosquitto from 1.6 to 2.0 (#17415) 2025-03-27 10:33:49 -06:00
labelmap.txt
LICENSE
Makefile
netlify.toml
package-lock.json
process_clip.py Improve async object detector support (#17712) 2025-04-15 08:55:38 -05:00
pyproject.toml
README_CN.md Update README_CN (#17581) 2025-04-07 08:32:43 -06:00
README.md Small Tweaks (#17652) 2025-04-11 08:21:01 -06:00

logo

Frigate - NVR With Realtime Object Detection for IP Cameras

Translation status
English

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 GPU or AI accelerator such as a Google Coral or Hailo is highly recommended. AI accelerators will outperform even the best CPUs 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

Translations

We use Weblate to support language translations. Contributions are always welcome.

Translation status