Vendor-locked telemetry
Every BMS speaks a different dialect. No single view of the fleet.
Battery intelligence
Right packs.
Right station.
Before the rush.
Rootd turns BMS telemetry into per-station forecasts so riders spend less time queuing and more time earning.
Any BMS vendorTenant-isolatedNo hardware
Charged packsDemand
0dry-station events
Packs pre-positioned ahead of both peaks.
The problem
Swap networks are flying blind.
Reactive restocking
Stations run dry at peak hours. Riders queue or ride on.
Invisible battery health
Lenders underwrite packs they can't see degrade.
Rootd is cloud intelligence on your existing network: forecasts, scheduling, and loan signals from a vendor-neutral digital twin.
Rootd is not hardware, a fleet operator, or a swap app replacement.
Platform
One twin. Three decisions.
01 · OPERATORS
Station forecasting
Know what each station needs before peak hour.
- Per-station demand forecasts
- Pre-position packs to smooth peaks
- Fewer dry stations, less overstock
FORECAST · KAWANGWAREon track
TODAY · RESTOCK PLAN4 stations
- Kawangware Hubevening peak+14by 16:00
- Ngara Junctionmorning peak+8by 06:30
- Industrial Areaoverstocked−6rebalance
- Westlands Mallwithin bandholdstable
02 · RIDERS
Rider scheduling
Swap windows that protect earning time.
- Suggested window from live station load
- Less travel, less queue time
- Surfaced through your app
GET /v1/rider/{id}/view200 OK
SUGGESTED SWAP WINDOW
13:20-13:50
Kawangware Hub · 600m away
est. wait 3 min
0%earning time retained
−11minvs. unplanned swap
recommendation only · operator app decides surfacing
03 · FINANCIERS
Loan visibility
SoH-backed residual value, not guesswork.
- SoH trend per pack and cohort
- Confidence bands, not single figures
- Early drift detection
SoH · COHORT 12±1.2%
90.4%mean SoH
residual
bandfrom SoH curve
bandfrom SoH curve
The platform
Any BMS in. One twin out.
Every vendor's telemetry normalized into a single digital twin: connectivity, SoH, and estimated SoC.
NORMALIZATION
Vendor A · CANraw BMS frames
Vendor B · MQTTraw BMS frames
Vendor C · RESTraw BMS frames
VENDOR-NEUTRAL TWIN
SoHconnectivityest. SoCcycles
LIVE TWIN · NORTHWIND
onlinestaleoffline
PackConnectivityState of healthEst. SoCLast reading
SoC is estimated from SoH + latest reading, never stored as a peer field. Offline packs hold last-known twin state.
How it works
Raw frames to decisions in four steps.
01
Ingest
Pull telemetry from any BMS: CAN, MQTT, or REST.
02
Normalize
One vendor-neutral digital twin.
03
Forecast
Station inventory, swap windows, residual value.
04
Decide
Operators, riders, and financiers act on the same signal.
Security
Multi-tenant from the first query.
Tenant-scopedAudited readsStale-state modeled
Tenant isolation
Every query is tenant-scoped. One operator's data never reaches another's.
Observability
Ingestion, freshness, and twin state monitored end-to-end.
Data integrity
Connectivity loss modeled as stale or offline, never silently dropped.
FAQ
Scope, plainly.
No. Rootd reads telemetry your BMS already produces and builds a digital twin from it.
No. Rootd exposes read APIs. Your app stays in place and chooses what to surface.
A BMS feed: CAN, MQTT, or REST. Rootd normalizes whatever each vendor emits.
Every query is tenant-scoped. One operator's twin is never reachable from another's.
No. Rootd is software only, the intelligence layer above networks you run.
See your stations forecasted live.
We'll run Rootd on your network's telemetry: one station, real data.