OpenNVR is an AGPLv3, offline-first network video recorder that runs on hardware owned by the operator. It isolates cameras and uses an adapter architecture to connect models such as YOLO and BLIP for governed detection and scene analysis, with an API for inference.
It focuses on monitoring cameras with AI without sending video or inference data to a vendor cloud. It is built as an open-source project for security-conscious organizations and developers managing self-hosted camera systems. The project is open source (AGPL-3.0). It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by open-nvr/open-nvr, and it first shipped in 2026. The project is developed in the open on GitHub with 71 stars and 811 commits in the last 90 days. Among its 9 catalogued features are camera monitoring, AI detection, and model adapters. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Other projects tracked alongside this one