2026-02-03, 14:50–15:40, B.1.036
SysInspect began life as an ADAS integrity observer in automotive systems. Over time, it morphed into a full-blown configuration & anomaly monitoring framework. Now it’s pushing into the embedded & IoT domain, where the usual CM tools usually don’t dare to. In this talk I’ll show how SysInspect handles anomaly detection, integrity in very constrained devices, and scales seamlessly up to full clusters.
Everyone solved configuration management on big servers. But embedded devices and IoT are still a mess — no SSH, flaky networks, tiny memory, and thousands of quirky devices that existing tools simply ignore.
SysInspect started as an ADAS integrity observer and grew into a configuration and anomaly platform built for exactly these forgotten environments. It works without heavy (that much) agents, tracks state, detects drift and inspects runtime behavior. Telemetry modules stream structured JSON logs or OTLP traces even over poor links.
It scales from a few-megabyte sensor board to large clusters and integrates with existing observability stacks. Typical use cases:
- Validate system state before OTA rollouts.
- Detect anomalies in the field in real time.
- Provide continuous visibility across distributed fleets.
- Feed inspection results directly into whatever uses OTel standard: Loki, Elasticsearch, Vector, Grafana etc.
This talk shows how SysInspect builds a live model of each device, explains anomalies in context, and adapts its configuration logic across wildly different environments — plus what’s new since last year and where the project is heading.
P.S. Of course it uses WASM. Your system doesn’t? 😏
Bo Maryniuk is a UNIX veteran who’s been poking at systems since the SunOS 3.x days. He works as a Principal Engineer in the Automotive world, focused on data analysis, telemetry, and making sure complex software behaves correctly in real cars — including, quite possibly, the one you’re driving.