Skip to content
X-Edge AI

Product Overview

Xisom Edge AI Box is an industrial edge appliance and runtime that brings real-time AI inference to your plant floor — no cloud round-trip required. It runs on an NVIDIA Jetson TX2.

X-Edge AI dashboard with live inference metrics and execution-provider status X-Edge AI dashboard with live inference metrics and execution-provider status
The X-Edge AI dashboard — real-time inference at a glance.

Core capabilities

Section titled “Core capabilities”
  • Real-time inference — ONNX models on the Jetson’s GPU through CUDA, with CPU fallback.
  • Streaming ingestion — connect OPC-UA, MQTT, and CSV input sources.
  • Output writeback — send predictions and setpoints to PLCs, brokers, and files.
  • Flows — upload a model, bind it to an input and its outputs in a flow, and enable the flow.
  • Observability — built-in latency, throughput, and execution-provider dashboard.
  • Hardened deployment — air-gapped offline install, non-root containers, RBAC, audit log.

Who it’s for

Section titled “Who it’s for”
  • Plant engineers automating quality inspection and predictive maintenance.
  • System integrators connecting AI models to existing SCADA/MES systems.
  • OT/IT teams needing on-prem inference without exposing data to cloud.

Architecture at a glance

Section titled “Architecture at a glance”
Architecture: input datasources (OPC-UA, MQTT, CSV) → Inference Runtime (ONNX, CUDA/CPU) with Model Manager; the runtime writes to output datasources (PLC, broker, file) which feed MES / Historian, and pushes via Event Bus (SignalR) to the Web Dashboard

Next

Section titled “Next”