edge-agents

Turn a finished Edge Agents *.workflow.json into a runnable, standalone deployment bundle — the docker-compose package (engine + config + any llama components + any operator-authored custom components) an operator builds and runs on an edge/IoT controller. Drives the fh-workflow CLI's headless deploy, reading the workflow to learn which hardware pins, MQTT brokers, models, and keys it needs, asking the operator to fill or confirm each value, and writing the bundle while keeping secrets as placeholders so nothing sensitive ever lands in the chat. Use this whenever the user wants to deploy, bundle, package, or ship a workflow to a device or controller — e.g. "deploy this flow to my Raspberry Pi", "make a deployment bundle for the edge", "bundle workflow.json so I can run it on the controller", "ship my agent to the device", "put this workflow on the controller" — even when they don't say the word "bundle", and as the natural next step after generating a workflow. Not for building or editing the workflow graph i

Generate a validated Edge Agents workflow JSON (*.workflow.json) from a natural-language description — the node-graph that runs on Edge Agents edge/IoT agents, built from triggers (timer, startup, pin edge, threshold, MQTT, serial), GPIO/serial/MQTT I/O, LLM Agent nodes, and actuators. Builds the graph to match the workflow contract and drives it to zero errors through the fh-workflow CLI's structural + semantic validators. Use this whenever the user describes automation or agent behavior in prose and wants a ready-to-run workflow file — e.g. "build a flow that reads a sensor every 10s and toggles a relay", "make an Edge Agents agent that summarizes incoming MQTT messages", "wire up a workflow where…" — even when they never say the words "workflow JSON". Not for visually editing an existing workflow (that is fh-workflow open) or merely checking one you already have (fh-workflow check-schema / validate).