Open source · AGPLv3 · runs on your own hardware

Don't replace your cameras for AI. Upgrade them.

OpenNVR is the open vision AI platform that turns your existing cameras into AI solutions: plate reading, intrusion alerts, footage search, and the apps you build.

It records and streams like any NVR, runs any AI model you choose, and keeps the footage, the models and the audit trail on hardware you own, air-gapped if you need. New capabilities arrive as software, not as new boxes. It is built for surveillance today; robots, vehicles and drones are where it goes next.

Built on a published offline-first security architecture. Read the paper

git clone https://github.com/open-nvr/open-nvr.git && cd open-nvr && ./start.sh

Pre-built images · runs on a Pi 5, a laptop or a server · no cloud account, no API keys.

No camera? Use your Android phone, your laptop's webcam or a video file.

personperson
North gateLIVE
YardLIVE
truck 0.91
Loading dockREC
personperson
LobbyLIVE
NO SIGNALlast frame 02:14
Perimeter EOFFLINE
carcar
Car parkLIVE

opennvr.inference.*

every detection is an event, on a bus you own

  • ›person · track 3 · stationary · cam1
  • ›N894JV read · cam1
  • ›Under-occupancy in zone 'drawn' · cam1
  • ›L605HZ read · cam1
  • ›car · track 7 · best frame · cam1
  • ›K884RS read · cam1

health

every layer reports — and alarms when it stops

  • Recording5 of 6 · Perimeter E offline
  • Watchingkeeping up · every camera
  • Models15 registered · fingerprints match
  • Apps17 installed · all healthy
  • Storage1.4 TB free · 31 days kept

have an idea?

Something to build on vision or video streams — an app for your cameras, a use case for a camera sensor?

Talk to the team that built the platform. We scope it with you, build it on OpenNVR, and hand you a working solution in the shortest cycle — not a slide deck. An app not accurate enough on your site? We fine-tune its model on your footage, on your hardware.

Talk to us
15
detectors out of the box
YOLO · BLIP · InsightFace · LPR · pose · more
~30
lines of Python per adapter
Apache-2.0 SDK · any model, any licence
17
one-click app-store apps
digest-pinned · manifest-driven UI
100%
offline-first by default
runs with no cloud account and no API keys
  • AGPLv3 core
  • Apache-2.0 SDKs
  • ONVIF · RTSP
  • Published architecture paper
  • Self-hosted forever

Where to start

Why it matters

An AI camera is as smart as the day you bought it.

Cameras with built-in AI lock their intelligence into the chip and the firmware they ship with. In a few years the models are dated, the vendor has moved on to the next range, and the only upgrade is a new camera.

OpenNVR moves the intelligence out of the camera and onto a box you control. Your cameras only need to send video. When a better model or a new capability appears, you install it on the cameras you already own.

  • Upgrade any time. New models and apps arrive as software. Nothing on the wall changes.
  • Switch freely. Swap one model for another, or bring your own, without replacing anything else.
  • You hold the keys. The footage, the AI, the security settings and the audit trail stay in your hands.

For installers and integrators that means selling cameras and installations as you do today, without being tied to one vendor's recorder, and adding AI applications and services on top.

AI cameras and NVRsOpenNVR
AI fixed inside the camera, on the chip it shipped withAI on a box you own: upgrade it, swap it or add to it any time
Records and plays backRecords and plays back — as the foundation, not the product
Features fixed when you buy the boxNew capabilities as apps and models, installed in one click
AI means the vendor's cloud, or a new boxAny AI model, on your hardware, swappable without touching anything else
Firmware from one vendor, patched when they chooseOpen source, patched on your schedule, built in public
An upgrade means replacing hardwareAn upgrade means installing software
Trust the vendorVerify: an audit log, model fingerprints, an evidence pack
A new capability is software, not a new box. A new model is released; it becomes an adapter on your existing OpenNVR box, where its weights are fingerprinted, its permissions declared and the local-only policy applied; an app in the App Catalog is installed and puts it to work; your people get the result as an alert on their phone. Recording runs the whole time, and a new appliance is crossed out.
A new model, an adapter, an app, an alert — on the box you already have. The fall-alert app is an illustration; the other tiles are apps that ship today.
See it in action

A real product, not a demo repo.

Dashboard, live view, search, the app catalogue and vehicle plate reads — all self-hosted, all yours.

OpenNVR screens, one after another: the dashboard, live view, search over recorded footage, the app catalogue, and vehicles with licence-plate reads.
The screens cycle on their own. Every one of them runs on your hardware.
What is different

Not another recorder with AI bolted on.

Most systems sell you detections. OpenNVR is built so that the footage, the models, the decisions and the evidence all stay yours — and so that the system tells you when any part of it is not doing its job.

Apps, not projects

Install a capability in one click

17 apps install from a catalog every deployment opens — plate watchlists, occupancy, guard-scan compliance, a smart doorbell — each with its own page, live dashboard and settings. And every one of them becomes something the assistant can answer about.

What makes it true: An app declares a manifest and the platform renders its UI, issues its credential, and scopes its cameras.

Any model, no lock-in

Your detectors are yours to choose

Object detection, plates, faces, body pose, scene captions, speech — nine ship, and any model from anyone can join them under any licence, including one you fine-tuned and cannot share. Swap one out and nothing that depended on it changes.

What makes it true: Apps ask for a task, never a model by name; any model serving that task is a drop-in.

Sovereign

Nothing leaves the building

Your cameras sit on a network with no way out, your footage stays on your disks, and the AI runs beside it. Reaching a cloud — for storage or for a model — is a decision an administrator makes, not a default a vendor made for you.

What makes it true: Two default-deny gates, checked continuously; cloud routes answer 403 until you allow them.

All 8 differences, and the reasoning behind them

Answers

Frequently asked questions

Everything people ask before they try OpenNVR.

Is OpenNVR free and open source?

Yes. OpenNVR is fully open source under the AGPLv3 licence, and the AI adapter SDK is Apache-2.0. Self-hosting on your own hardware is free, with no account and no cloud subscription. Businesses that resell or embed OpenNVR buy a commercial licence; the pricing page has the terms.

What is an open-source NVR?

An NVR (network video recorder) ingests, records, and serves video from IP cameras. An open-source NVR is one whose code you can read, audit, self-host, and modify — so your footage and analytics stay on hardware you control instead of a vendor's cloud. OpenNVR is an offline-first open-source NVR with an open AI platform on top.

How is OpenNVR different from Frigate, ZoneMinder, or Verkada?

OpenNVR adds a published open AI adapter contract (any model becomes a detector under any licence), an end-to-end audit chain with model-fingerprint drift detection, two default-deny sovereignty gates, a published architecture paper, and a voice agent you can talk to. See the full side-by-side on the OpenNVR vs Frigate, ZoneMinder and Shinobi comparison.

Can OpenNVR run completely offline?

Yes — offline-first is the default. Cameras sit on an isolated network with no route to the internet, recording and AI run locally, and cloud connectivity is off unless you explicitly enable it (and that opt-in is audit-logged).

Can I run my own AI models on my cameras?

Yes. Bring Your Own Model (BYOM): wrap any model — ONNX, PyTorch, a fine-tuned model, or a cloud endpoint — in about thirty lines of Python with the Apache-2.0 SDK, and OpenNVR treats it as a first-class detector. 15 adapters ship out of the box, including an open-vocabulary detector you can query with free text like "red truck".

Can I search my recorded footage in plain language?

Yes. The footage-search example indexes your recorded inference (object labels plus scene captions) and lets you ask "show me every red truck at the dock yesterday" — object classes come from the detector, attributes like colour from the captioner or the open-vocabulary adapter. Fully on your hardware, no cloud, no API keys.

Can I really talk to my cameras?

Yes. The camera-agent example lets you ask a question out loud — "is there a person at the front door?" or "did a red truck come by the dock earlier?" — and a local LLM answers, grounded in a live frame or your recorded-footage index, spoken back to you. Whisper, an Ollama LLM with tool-calling, and Piper, all running on your hardware. No cloud, no API keys.

Who needs the OpenNVR Commercial License?

Businesses doing what the AGPL doesn't allow: selling hardware with OpenNVR pre-installed under their own brand (with proprietary changes or locked firmware), embedding OpenNVR inside proprietary software, or hosting a modified OpenNVR as a closed service. Self-hosting is free forever on any hardware. It's the Qt/Linphone dual-licensing model — see the license matrix.

Can the apps and adapters I build be proprietary?

Yes — deliberately. The app SDK and the AI adapter SDK are Apache-2.0, so anything you build on them ships under any license you choose, including closed source. Only the platform core is AGPL. Building on OpenNVR never requires a lawyer.

Do I have to publish my app or model to the catalog?

No. An app or adapter you run from your own repository and your own image registry works exactly like a catalog one, and both SDKs are Apache-2.0, so it can stay closed. Listing in the catalog is optional: it makes your work one click for every deployment, through a pull request against a public index. Your first app covers both paths.

What is "Powered by OpenNVR"?

The trademark badge. Anyone shipping substantially unmodified OpenNVR under the AGPL may use it for free; commercial licensees are required to display it (unless they purchase the white-label tier). The code license and the trademark are separate on purpose — the code stays genuinely open while the name stays trustworthy.

Where are the API references?

Three, all generated from the code rather than written beside it: the App SDK reference for building apps, the Adapter SDK reference for publishing a model, and the operator API — the same OpenAPI document a running install serves at /docs. Start at the developer corner if you are not sure which you need.

What cameras does OpenNVR work with?

Any camera that speaks ONVIF or RTSP — which covers virtually all modern IP cameras (Hikvision, Dahua, Axis, Reolink, and generic ONVIF/RTSP). No proprietary hardware to buy; reuse the cameras you already own.

Your cameras. Your hardware. Your AI.

Two commands to run it. Build on it for good.

Pull the pre-built images, point it at a camera, and watch detections appear. Then write an adapter, fork an example, and make it solve your problem — the contract is the front door, and it's open.

Free and open forever under AGPLv3 — self-host it, fork it,write an adapter, oropen a PR.

OpenNVR is free software maintained by a small team.Sponsor the work, lend us hardware or give your time →

Deploying for a government, critical-infrastructure, or regulated environment?Talk to us about a pilot or security assessment →