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.shPre-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
truck 0.91
personperson
NO SIGNALlast frame 02:14
carcaropennvr.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.
- 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
Run it at home
A doorbell that knows the family and a porch that knows the parcel is gone, on a Pi 5 or an old laptop. Free to self-host.
Deploy it for a business
Keep the cameras on the wall. Add plate reading, intrusion, occupancy and footage search as apps, on a box you own.
Build on it
Build vision AI apps without building the camera stack. Recording, tracking, events and alerts are done, and your app stays yours under any licence.
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 NVRs | OpenNVR |
|---|---|
| AI fixed inside the camera, on the chip it shipped with | AI on a box you own: upgrade it, swap it or add to it any time |
| Records and plays back | Records and plays back — as the foundation, not the product |
| Features fixed when you buy the box | New capabilities as apps and models, installed in one click |
| AI means the vendor's cloud, or a new box | Any AI model, on your hardware, swappable without touching anything else |
| Firmware from one vendor, patched when they choose | Open source, patched on your schedule, built in public |
| An upgrade means replacing hardware | An upgrade means installing software |
| Trust the vendor | Verify: an audit log, model fingerprints, an evidence pack |
A real product, not a demo repo.
Dashboard, live view, search, the app catalogue and vehicle plate reads — all self-hosted, all yours.
Type what you saw. Get the moment.
A question in plain words becomes filters you can edit, and the answer is every visit that matches, across all your cameras. The search runs on your own box.
4 visits · 2 cameras
personNorth gate08:12
personNorth gate08:13
personLobby09:40
personLobby09:41
1 visit · 1 camera
truckLoading dock14:26
2 visits · 1 camera
carCar park18:04
carCar park18:31
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.
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 →