Where am I
Answered by VPS
One camera frame returns a 6-DoF pose in the map of your site at a sub-5 cm median, on glasses, phones, headsets and robots.
Today
For AI agents on glasses, phones and robots
Your agents can already see. MultiSet tells them where they stand, which machine is in front of them, which part to work on and where everything else sits, from the scans and CAD your site already holds.
median VPS accuracy, from one camera frame
object tracking precision, from a scan or CAD
objects checked in one cloud query
beacons installed, since the map comes from your scans
Vision models can name a pump. Knowing which of six identical pumps is in view, and where the wearer stands, takes a map of the site.
Answered by VPS
One camera frame returns a 6-DoF pose in the map of your site at a sub-5 cm median, on glasses, phones, headsets and robots.
Today
Answered by Object Tracking
The machine is recognized from its scan or CAD with millimeter precision, and its pose lands in the same map, so its place says which of six identical units it is.
Today
Answered by Object Tracking, part by part
Each part tracks on its own, even in the technician's hand, with the step, the reading and the work order anchored to it. Your agent brings the instruction from your own procedures.
Today
Answered by the map, as the site's memory
Every tag in your asset register sits where the asset stands, so an agent can route a wearer to any of them. Listing and counting by type and floor is next.
Today and next
A phone photo placed in a theatre scan, simulation view
The app finding a toy truck and locking onto its edges
Labels anchored to each part of the engine
Brewery valves tagged where they stand
Bring your asset register in the coordinates it already uses, from a plant grid, an EPSG code or GeoJSON, and every tag becomes a place in the map. Your agent calls MultiSet like any other tool and gets back a position, the unit in view and the nearest tags.
Route drawn from where you stand. Twenty-one meters to go.
P-102, the second unit from the wall. Its open work order is on screen.
TodaySixty-two tagged on floor 3, twelve of them in bay C.
Next// Illustrative response { "map": "plant-north", "pose": { "position": [12.41, 1.62, -3.08], "rotation": [0, 0.38, 0, 0.92] }, "confidence": 0.91, "object": { "code": "P-102", "name": "Feed pump P-102" }, "nearest": [{ "tag": "V-12", "type": "valve", "distance_m": 3.4, "bearing": "ahead, left" }] }
Illustrative conversation. The route clip is a real recording from the MultiSet app.
A place one device names is a place every other can find.
Glasses, phones, headsets and robots read the same map. A tank the agent names for the wearer is a goal the robot can walk to, on the same coordinates.
Upload the E57, Matterport or 360 capture you already own, or scan a room with the MultiSet app.
Import the asset register in its own coordinates and upload the scans or CAD of the machines and parts that matter.
Call the API or an SDK from your app and hand the result to the model that runs the conversation.
Give your agent a map of one room today, on the free plan.
A map of a real site that an agent can query for position, objects and assets. MultiSet builds it from the scans and CAD a site already holds, then tells the agent where the user stands, which machine and part are in view and where every tagged asset sits.
The device sends a camera frame to MultiSet, which returns a 6-DoF pose in the site map at a sub-5 cm median. The agent then knows the room, the floor and the direction the user faces, with no GPS signal and no beacons installed.
Yes. Object tracking matches the machine from its scan or CAD with millimeter precision, and its place in the map says which unit it is. Parts track the same way from 5 cm upward, including one in the technician's hand.
Import your asset register in its own coordinates and every tag becomes a place in the map. Agents can route a wearer to any tag today. Listing and counting by type and floor through an API comes next.
An MCP server for positions, objects and asset tags is planned. Today agents reach them through the REST API and SDKs, and the MultiSet docs already run as an MCP server that any assistant can read with no key.
Give your agents a spatial memory of your site.
Start with one room on the free plan, or bring us the scan of a plant, the CAD of its equipment and its asset register.