LLM Integration — Wired, Not Chatted
Run a local LLM with Ollama in your home automation — summarize sensor data, write alerts, and act on the results offline on your own hardware.
One swarm, every screen — install the control app, or stand up a server.
$ curl -fsSL https://cms.krill.systems/distro/server/install_krill.sh | sudo bash$ curl -fsSL https://cms.krill.systems/distro/desktop/install_krill_desktop.sh | sudo bashRun a krill server on a Raspberry Pi, a laptop, or a rack box. Open the app on any device on your network. Wire sensors, schedulers, calculations, GPIO and dashboards into a live swarm — no cloud, no accounts, no rented brain. The architecture pros use for SCADA, scaled down to fit on a workbench.
Servers discover each other on your LAN and pair into a swarm. Your data, your hardware, your network — never anyone else's cloud.
Data points, cron timers, calculations, GPIO, alerts, dashboards — composable nodes wired into directed graphs. Inspired by industrial SCADA.
Aquaponics, vivariums, breweries, greenhouses, workshops. Drop a server on a Pi, plug in sensors, build the system you actually wanted.
Typed nodes, explicit observer model, deterministic graph evaluation. The same patterns that run factories — without the seat-license bill.
Four minutes. Three nodes. One mental model that scales from a single thermostat to a building's worth of sensors.
Run a local LLM with Ollama in your home automation — summarize sensor data, write alerts, and act on the results offline on your own hardware.
A simple example of using relays and solenoids with water sensors to automate keeping my aquarium topped off with water.
Read I2C and GPIO sensors on a Raspberry Pi with CircuitPython for home automation and data logging.
Controlling Zigbee devices over MQTT
Install Krill Server in Kiosk Mode for Touchscreens
Design custom process-control dashboards and HMI screens from your own SVG drawings, with live sensor and device data.
Create lists of tasks for anything you want to track.
Journal your project progress with notes and photos.
Build live dashboards by overlaying real-time sensor readings and device status on your own SVG diagrams.
Communicate with hardware devices via USB and serial ports for sensor data and device control.