# roflcoopter/viseron

Self-hosted, local only NVR and AI Computer Vision software.  With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.

Repository: https://github.com/roflcoopter/viseron
Canonical: https://ross.abutalabs.com/products/viseron
Language: Python
License: MIT
License Family: permissive
Topics: nvr, network-video-capture, network-video-recorder, tensorflow, darknet, yolo, hardware-acceleration, object-detection, motion-detection, cuda, surveillance, rtsp, ip-camera, viseron, coral, edgetpu, google-coral, hacktoberfest, face-recognition, license-plate-recognition
Last push: 2026-08-26T20:12:46+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 100
- inputs: {"age_days": 2194, "days_push": 7, "days_rel": 23, "gap_med": 23.5, "n_releases_24m": 17}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3431, forks 422 (observed 2026-08-28T04:08:04.027634+00:00)

## What it is
Viseron is a self-hosted, local-only network video recorder (NVR) with built-in AI computer vision capabilities. It supports object detection, motion detection, face recognition, and license plate recognition on RTSP IP camera streams, with hardware acceleration via CUDA, Google Coral, and other backends.

## Use cases
- monitor my home security cameras with AI object detection
- self-hosted NVR for IP cameras without cloud
- detect people and cars on RTSP camera streams
- face recognition on my surveillance cameras
- license plate recognition for my driveway camera
- motion-triggered camera recording with local AI
- run object detection on cameras using a Google Coral accelerator

## When to choose
- you want a privacy-focused, fully local NVR with no cloud dependency
- you have RTSP-capable IP cameras and want AI-based detection and recording
- you have compatible hardware (CUDA GPU, Google Coral) for accelerated inference
- you want a Docker-deployable surveillance system with a built-in web interface

## When to avoid
- you need a plug-and-play consumer NVR with vendor support
- you want cloud storage or remote cloud-based AI analysis
- you don't have hardware for AI inference and only need basic recording
- you need support for non-RTSP proprietary camera protocols

## Facets
- artifact type: application
- maturity: active
- function: computer-vision, object-storage, self-hosted, video-processing, image-processing, monitoring
- domain: computer-vision, self-hosted, security, privacy, media
- platform: self-hosted, python
- tags: nvr, surveillance, ip-camera, rtsp, object-detection, motion-detection, face-recognition, license-plate-recognition, yolo, tensorflow, google-coral, edgetpu, cuda, hardware-acceleration, home-security, docker, linux, web-server, gpu

## Member repositories
- roflcoopter/viseron (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.027634+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:46.729530+00:00, confidence not recorded.
  - readme: https://github.com/roflcoopter/viseron (fetched 2026-08-28T04:08:04.027634+00:00, sha 2ad0ba281bf6)
- Data as of 2026-08-30T08:39:29.467469+00:00.