A documented comparison for teams evaluating cloud video as a service. Two facts shape this one before any feature list: Arcules is a Milestone product, and its analytics are largely the ones already running inside your cameras. Both are strengths, and both change what you are actually buying.
Arcules is cloud video as a service hosted in Google Cloud, sold on a subscription with no servers to run, and it keeps your existing cameras through ONVIF support when paired with a gateway. Its analytics come from two places: cloud-side detections like people detection with zones, line crossing and parked vehicle counts, and camera-side analytics passed through from Axis, Bosch, iPro and Hanwha devices. Teams shop for an alternative when the detection set should not depend on which cameras they bought, when they want an action on site after the alert, or when the questions run past security. The five below split on that.
Both platforms run on the cameras a site already owns. They differ on whether the intelligence belongs to the platform or to the cameras, and that decides whether two sites behave the same way.
Every cell is something the vendor publishes, or an explicit not publicly specified.
Swipe the table sideways to see every column.
Arcules's row was read off arcules.com on August 12, 2026, including the Google Cloud hosting, the ONVIF-plus-gateway condition and the per-manufacturer camera-side analytics list. Its Milestone ownership is stated on its own pages. The other five rows come from each vendor's public documentation reviewed in July and August 2026 on the same five columns. Gaps are marked as not publicly specified rather than guessed.
Start by discarding the wrong reason, because Arcules is more open than its category usually is. It supports ONVIF devices when paired with a gateway and says in its own words that this avoids hardware lock-in, so the cameras on the wall stay. It is hosted in Google Cloud rather than on infrastructure you maintain, sold as a subscription, and it inherits the open-platform approach of Milestone, which owns it. For a team that wants cloud video without a server room, that is a coherent package.
The first real reason is where the intelligence comes from. Arcules publishes a genuinely useful cloud-side set: people detection with zones, line crossing by direction, parked vehicle counts, forensic search and smart alerts for loitering or boundary crossing. Beyond that, the deeper analytics are the ones already inside your cameras, listed per manufacturer: Axis Object Analytics and Motion Guard, Bosch people count and occupancy, iPro cross-line and intrusion, Hanwha people and vehicle detection. That is honest engineering and it means your detection catalog is a function of which cameras you happen to own, and it differs from site to site.
The second is scope and what happens next. The published set is security and counting shaped. Nothing on the public pages covers PPE compliance, forklift near-misses, hazard-zone crowding or dock delays, and no speaker, talk down or strobe behaviour appears, so the escalation path ends with a person in a browser. A platform where the same detections run identically on every camera, and where an alert can trigger an action on site, is answering a different question.
Arcules keeps your cameras and your capital. What it cannot do is make two sites with different cameras behave the same way, because the deeper detections come from the cameras themselves.
What each one is, where it is strong, and what to check before you commit.
Spot AI is a software-led video AI platform that turns the IP cameras a business already owns into AI coworkers. An on-site Intelligent Video Recorder keeps full-resolution video in the building and sends only event metadata to the cloud, so search and multi-site management stay cloud-based while footage does not leave the facility.
Eagle Eye Networks is a cloud video management system that connects to virtually any ONVIF-conformant camera and digitises analog feeds through analog-ready Bridges and CMVRs, then layers cloud analytics on top of the estate. Its documentation names ONVIF Profile S and dual codec streaming as the integration path.
Milestone XProtect is an open-platform video management system sold in four editions: Express+, Professional+, Expert and Corporate. Milestone positions it around what it calls the market's widest choice of cameras, sensors and IoT devices, with more than 1,000 third-party applications available to extend it.
Verkada is a cloud-managed platform that sells its own cameras, access control, sensors, alarms and intercoms under one console, and publishes per-device MSRPs, which is unusual in this market. Third-party cameras come in through Command Connector, which Verkada states is an ONVIF Profile S conformant client and can also ingest RTSP feeds.
Rhombus sells cloud-managed cameras, sensors, access control and alarm monitoring as one system, described by the company as a cloud-edge system that operates offline. Third-party cameras come in through the Relay Connector N100, and the company publishes SOC 2, NDAA, GDPR and TAA compliance badges.
Six questions that separate these platforms faster than any feature list.
This is the question Arcules puts on the table. Its deeper analytics are camera-side, listed per manufacturer, so a site with Axis cameras and a site with Bosch cameras get different capabilities. Spot AI runs the same 15+ agents on any ONVIF or RTSP camera. Eagle Eye runs its named analytics in the cloud. Decide whether you want one behaviour everywhere or the best of what each camera can already do.
ONVIF support is conditional on a gateway, which is hardware per site with short-term buffering in it. Verkada's Command Connector is listed from $4,499 for up to 10 channels. Rhombus reaches third-party cameras through its Relay Connector N100. Spot AI's Intelligent Video Recorder is covered by the subscription. Ask each vendor for the appliance count and cost for your exact site list.
Arcules is cloud, hosted in Google Cloud, with buffering in the gateway. Milestone, the same company, offers on premises and hybrid. Eagle Eye stores video on its own data centers. Spot AI keeps full-resolution video in the building and sends only metadata. In regulated environments this is settled by written policy, so start there.
Establish what happens when the alert fires and there is nobody on the other end of it. Eagle Eye documents sirens and talk-down alerts. Verkada gates automated audio to the BZ11 or an Intercom. Spot AI runs talk down, strobes and horns through standard speakers already mounted. Arcules, Milestone and Rhombus publish no deterrence behaviour, so the honest answer is that a human closes the loop.
They are the same company, and that is useful rather than awkward. If the requirement is cloud with no servers, Arcules is the shape. If it is an open platform on your own infrastructure with a very large application ecosystem, that is XProtect. Ask one Milestone partner to quote both against the same site list, then compare the totals rather than the marketing.
If your list includes PPE compliance, forklift near-misses, hazard-zone crowding or dock delays, ask which of those ship pre-trained. Arcules publishes security and counting analytics, and none of the cloud vendors here publishes a safety or operations agent set, so a platform that arrives with them answers a question the others route to a partner product.
Spot AI fits when the same behaviour is wanted on every camera regardless of brand, and the questions span security, safety and operations. It runs on any ONVIF or RTSP camera plus legacy analog through the Intelligent Video Recorder, keeps full-resolution video in the building, ships 15+ pre-trained agents plus Iris for custom detections, and acts through standard speakers already on site.
Arcules stays the right call for a team that wants cloud video as a service, has cameras worth keeping, is content for the deeper analytics to come from those cameras, and would rather pay a subscription than run servers. Being a Milestone product also means the open-platform route stays available later without changing vendor.
A camera-agnostic platform lets you test the AI on your own cameras before any hardware decision, which is the cheapest way to de-risk the choice.
Watch the AI coworkers work on your live feeds, not a demo reel.
Customer-reported outcomes from named Spot AI customers.
Bridge33 Capital standardized video across 25 plus commercial properties on whatever cameras each acquisition already had, and cut footage search from hours to minutes.
Cambridge City cut the time it takes to find footage from two hours to thirty seconds.
Don Franklin Family of Dealerships lifted camera utilization 60% as the system became an analytical tool across departments rather than a security archive.
"With Spot AI, we were able to standardize video surveillance across existing and newly acquired assets, regardless of what cameras were already installed."
The five covered here are Spot AI, Eagle Eye Networks, Milestone, Verkada and Rhombus. Spot AI fits teams wanting identical detections on every camera plus deterrence. Eagle Eye Networks fits mixed and partly analog estates. Milestone is the same company's on-premises and hybrid open platform. Verkada fits a site specified from scratch. Rhombus fits mid-market teams wanting one vendor.
Yes, and its own pages say so, describing the same open-platform approach at the heart of all Milestone products. That matters commercially rather than technically: the cloud service and the on-premises open platform come from one vendor, so a partner can quote both against the same site list and a later change of shape does not mean a change of supplier.
Yes, with one condition worth budgeting for. Arcules supports ONVIF devices when paired with a gateway, and frames this as avoiding hardware lock-in so you keep the cameras you already have. The gateway is per-site hardware that also provides short-term buffering, so ask how many your camera count needs before comparing subscription figures.
Two layers. Cloud-side it publishes people detection with customizable zones, line crossing by direction, parked vehicle counts, forensic search by object, person or motion, and smart alerts such as loitering or virtual boundary crossing. Beyond that it passes through camera-side analytics from Axis, Bosch, iPro and Hanwha devices, so the deeper set depends on which cameras a site has.
It publishes the model but not the figures: a subscription that minimises up-front cost, paying only for what you need as the organisation grows. Of the platforms compared here only Verkada publishes per-device MSRPs. Any comparison has to come from quotes on the same site list, with the gateways itemised separately from the subscription.