EdgeMind — Factory Telemetry with Agentic Analysis
Factory MQTT telemetry, stored as time series, analysed every 30 seconds by an LLM running against a five-minute rolling window. Anomalies become natural-language insights.
What it does
A factory broadcasts telemetry over MQTT — temperatures, throughputs, machine states, counts. EdgeMind subscribes to the firehose, writes the numeric data to a time-series store, and runs an agentic analysis loop every thirty seconds against a rolling five-minute window. The output isn’t a dashboard chart; it’s a natural-language summary of what’s happening, with anomalies called out and trend shifts flagged.
The dashboard you see in the demo shows the raw data on one side and the agentic insights on the other. The visitor can watch the two stay in sync.
Why it matters
Time-series tooling solves the storage problem. It does not solve the noticing problem. Most factory operators don’t have time to watch a Grafana board — they need the system to tell them when something interesting happened, in language a human reads in two seconds.
Architecture
- MQTT broker → Node.js subscriber → time-series store (InfluxDB), with a throttled WebSocket stream to the browser.
- Agentic loop (every 30s): query the rolling window, hand it to the LLM with a small prompt, broadcast the resulting analysis over the same WebSocket.
- Frontend is a static HTML/JS dashboard fed by the WebSocket.
Try it now
The live demo ships in V1.1 — for now this page describes the system. The demo page shows the chrome and current status.