Agent activity
Checking for WebMCP support
Requests are only sent after you confirm them. How this works
Deployment
Where the processing runs changes everything else
In short
Ayonix states that its systems are built to run on-premise, at the edge, or fully air-gapped, in addition to conventional server deployment. That choice determines bandwidth, latency, what happens during an outage, which integrations are possible, and whether the deployment satisfies your data-residency position.
Start here
Which architecture fits your estate?
Four questions usually settle it. This runs in your browser and sends nothing.
Suggested starting point
This is a starting point, not a design. Hardware sizing needs your actual stream profiles and rule set, and comes from Ayonix — no channel-count or throughput figure is published on this site.
All options
Deployment architectures
-
Edge video analytics
Run analytics next to the cameras so video stays on site, alerts survive a WAN outage and only events cross the network.
Read the detail → -
On-premise video analytics
Run analytics on your own servers inside your network, alongside an existing VMS, with full control of data, updates and retention.
Read the detail → -
Air-gapped video analytics
Run analytics with no outbound connectivity for defence, utilities and regulated operational networks, with offline updates and local audit.
Read the detail → -
Hybrid video analytics
Process video locally and aggregate results centrally, combining local alerting resilience with estate-wide reporting and management.
Read the detail → -
Multi-site video analytics
Manage rules, thresholds, updates and health across many sites so measurement is comparable and configuration does not drift.
Read the detail → -
ATLAS AIBOX
What Ayonix publishes about ATLAS BOX and ATLAS AIBOX edge hardware, how it fits an edge analytics architecture, and which specifications require Ayonix confirmation.
Read the detail →
Comparison
Side by side
| Model | Bandwidth | Resilience | Scaling |
|---|---|---|---|
| Edge video analytics | Lowest of any model. Continuous video stays local; only events, small evidence artefacts and aggregate series cross the WAN. A sit… | Highest per-site independence. A WAN outage stops central reporting but not local detection and alerting. Conversely, an edge node… | Scales by adding sites rather than by growing a central cluster. Per-site camera capacity is bounded by the node, so a site that g… |
| On-premise video analytics | Camera-to-server traffic stays on the LAN, which is normally well provisioned. No continuous video crosses the internet. WAN use i… | Depends on the customer’s own server and network resilience. Analytics inherits whatever redundancy the site already operates, whi… | Scales by adding server capacity within the site. Because processing is centralised, adding cameras is usually a capacity question… |
| Air-gapped video analytics | No external bandwidth is used at all. Internal traffic follows the same pattern as on-premise or edge deployment depending on wher… | No external dependency means no external failure mode. Resilience is entirely a function of the internal design, which the operato… | Scales within the boundary by adding capacity. Growth planning must account for the controlled process required to introduce any n… |
| Hybrid video analytics | Low and predictable. Only events and aggregate series cross the WAN, so bandwidth scales with activity rather than with camera cou… | Sites operate independently during a WAN outage and forward buffered events when connectivity returns. A central-layer outage does… | Scales well to large estates because processing grows per site while the central layer handles events and metrics rather than vide… |
| Multi-site video analytics | Only configuration, events, metrics and health traverse the WAN. Bandwidth scales with site count and activity, not with camera co… | Sites run on their last known-good configuration during a disconnection. A central-layer outage prevents configuration changes and… | Designed for estate growth. Adding a site means assigning it to a group and completing its readiness review, rather than designing… |
| ATLAS AIBOX | As for any edge deployment: continuous video stays local and only events and aggregate series cross the WAN.… | Per-site independence, with local alerting continuing through a WAN outage. Specific redundancy options should be confirmed with A… | Scales by adding appliances per site or per camera group. Per-appliance capacity is a sizing question that Ayonix must answer agai… |
Get an architecture review
An architecture review works through site count, connectivity, data residency and outage requirements, and produces the sizing inputs Ayonix needs to specify hardware for your estate.