One Ethical AI Platform for Every Camera You Already Operate

IREX is a cloud-native video-intelligence platform that installs across the cameras a city or agency already owns, from a single site to an entire country. Every capability ships together, under one contract, one SLA, and one upgrade path.

100,000+
Cameras Proven on a Single Instance
250,000+
Cameras Deployed Globally
<1 s
Video Search across Petabytes of Footage
8
Countries in Production

What It Is

Video Intelligence, Not a Video Recorder

A traditional video management system stores footage so a person can go and look at it afterwards. IREX is built the other way round: cameras and sensors feed a private cloud the customer controls, the platform analyzes the streams in real time, and the operator gets the chance to prevent an incident instead of reconstructing it.

It is an aggregation of microservices on Kubernetes rather than a monolith, which is why every dimension scales independently: cameras, users, retention, and the number of active AI modules. One instance is proven in production at 100,000+ cameras, all running real-time analytics with 30-day instant search, and the architecture scales linearly to a ceiling of 1,000,000 cameras and 100,000 users without re-architecture.

Nothing is feature-gated. The analytics catalog, the ethics framework, and the audit trail come with the platform, and the commercial model is independent of how your cameras connect.

Why It Is Different

What You Get That a VMS Cannot Give You

  • Your existing cameras. Camera-agnostic across ONVIF Profile S and the major brands, with no rip-and-replace.
  • One contract, one SLA. Every analytics capability on one platform and one upgrade path, rather than a stack of integrations.
  • Search that answers in seconds. Proprietary descriptor clustering and indexing over billions of face, figure, and vehicle objects.
  • Accountability in the architecture. A mandatory Case ID and a non-erasable, tamper-evident audit trail, not a setting an administrator can switch off.
  • 100% customer data ownership. IREX neither owns nor accesses customer video, events, logs, watchlists, or floor plans.
  • No single point of failure. Every component hot-swappable, triple-replicated storage, and automatic failover under load.

Explore the Platform

Capabilities

Each capability is part of the same platform and the same permission model, not a separate product to integrate.

FAQ

Do we have to replace our cameras?

No. Reusing the existing fleet is the standard deployment model. IREX supports ONVIF Profile S and the major brands, and adds AI across the cameras you already operate, from one site to a whole country.

Does one camera have to be dedicated to one analytics module?

No. Several analytics modules and detectors run on the same camera at the same time, for example face recognition, object tracking and traffic monitoring on one stream, with no extra hardware and no duplicated video stream. Turning a second module on is done from that camera’s module list, and the platform lists the modules already running and asks for confirmation before the change takes effect. The practical consequence is that coverage becomes a question of which capabilities a camera should carry, not of how many cameras a budget will stretch to.

How is this different from a VMS?

A VMS stores and displays video. IREX analyzes it in real time, indexes it for instant search, routes alerts to the people who can act, and records who did what and why. Traditional Windows-server VMS products are not cloud-native and cannot handle data at this scale, so a like-for-like comparison is not meaningful.

Can it run entirely on our own infrastructure?

Yes, and that is the primary model. The platform installs as a private cloud on hardware you own: on-premises, private cloud, or fully air-gapped with no internet dependency at runtime. An IREX-hosted option exists for smaller deployments.

How large can one deployment get?

A single instance is proven in production at 100,000+ cameras with 30-day instant search. The architecture scales linearly to 1,000,000 cameras, 100,000 users, and a one-year retention period without architectural change. Sizing for a given program is calculated per project.

See It on Your Own Cameras

A demo runs on your footage and your use cases, not on a canned dataset. Tell us the camera environment and the constraints and we will scope it.