LocalSky
LocalSky
Hyperlocal weather on your hardware. Smart irrigation when you want it. No cloud, no subscription, no account.
Two products, one container
Self-hosted weather dashboarding for your station, plus an optional irrigation engine for when you have sprinklers. Each is useful on its own. Both run from a single Docker image.
Weather dashboard
Live observations from your Tempest or Ecowitt over the LAN. Multi-source forecast merge with per-field provenance so you know where every value came from. Built-in NEXRAD + RainViewer + lightning radar.
No Weather Underground account. No Tempest cloud subscription. No rate limits.
Weather sources →Smart irrigation, optional
FAO-56 Penman-Monteith reference ET, 12-species grass catalog, 7-class USDA soil catalog, 17-rule skip ladder. Drive OpenSprinkler directly, ESPHome, or your existing Home Assistant service calls.
Same engine the meteorologists publish, the math you can audit, free forever.
Irrigation engine →Quick start
Demo mode boots with simulated weather + four irrigation zones so you can explore the UI before connecting anything.
http://localhost:8090. For a real install, drop LOCALSKY_DEMO, mount a config volume, and the first-run wizard at /setup walks you through location, weather sources, controllers, and zones.
For the weather
Your station data, plus the public forecast, plus radar, in one fast self-hosted dashboard.
Live observations
Tempest UDP rapid-wind compass, rain gauge, lightning strike rings, pressure, solar irradiance, UV index. Direct from your station over the LAN.
Multi-source forecast
Open-Meteo, NWS, Tempest. Per-field provenance shows which source provided each value. Hourly, daily, 7-day strip.
Radar + lightning
RainViewer precipitation playback, IEM NEXRAD reflectivity, satellite IR, Tempest lightning rings. Layer toggles, legend, timeline scrub.
For the irrigation
Optional. Adds a peer-reviewed agronomic engine that turns weather into watering decisions, in plain language, with the math you can audit.
Native FAO-56 ET
Penman-Monteith reference ET₀ with ASCE-EWRI 2005 + Hargreaves-Samani fallbacks. Hemisphere-aware Kc curves, 12 grass species, 7 USDA soil textures.
Multi-controller HAL
OpenSprinkler direct, Home Assistant service call, ESPHome native (community), Rachio (planned), DryRun for demo and tests.
17-rule skip ladder
Rain now, rain next 4 hours, probability-weighted 3-day and 7-day rollups, freeze, soil saturation, soil frost, heat advisory. Tunable per deployment.
Local-first, on purpose
Everything runs from a single Docker container on your own hardware. Open source, Apache-2.0, free forever.
Your data stays home
No account, no telemetry, no upstream upload. Open-Meteo is the only optional outbound call and it can be swapped for NWS.
Optional LLM advisor
Ollama auto-detect, llama.cpp, or any OpenAI-compatible endpoint (LM Studio, vLLM, private gateway). Runs locally if you want it. Off by default.
Installable PWA
iOS, Android, desktop. VAPID-signed push notifications. First-run wizard walks the empty state to a working install without touching YAML.
Manual control + per-zone math
If you wire up irrigation: every decision the engine makes is visible. Override any threshold from the settings UI; run any zone for any duration from the dashboard.
Configure once, audit forever
An eight-step first-run wizard takes you from empty container to running install. Every threshold and math input is exposed for tuning later; every irrigation event is logged forever.
