Screenshots From the README of snazzybean/roommind.
About
RoomMind is a Home Assistant integration for room climate control that learns how each room heats and cools. It builds a thermal model per room and uses it for model predictive control, falling back to on/off control while it learns. Radiator valves receive calculated setpoints instead of simple on/off commands, and the model also accounts for solar gain estimated from sun position and weather data. Rooms can follow several schedules, with manual boost, eco or custom temperature overrides, plus a vacation mode with a global setback temperature. Presence detection can lower the temperature when assigned people are away, and climate control pauses when windows or doors are open. It works locally, is set up in the UI, and provides climate, sensor, binary sensor and switch entities.
Automatic summary of the README and code of snazzybean/roommind. Something wrong, or are you the maintainer and want your own text here? Get in touch
Supports
Works locally Talks to your devices on your own network. No vendor cloud in between.
From the Marketplace Installed through the Marketplace, formerly HACS.
Actively maintained Its author released or pushed a change in the last six months.
Provides
- Climate
- Switches
- Sensors
Setting it up
Install it from the Marketplace and restart Home Assistant, then add it under Settings, Devices and services.
Troubleshooting
- DiagnosticsDownloads a diagnostics file to attach to a bug report.
- Repair noticesNotices it can show in Settings, Repairs:Restart required, RoomMind entities to replace
From the README
Intelligent room climate control for Home Assistant - self-learning thermal model, proportional valve control, and a dedicated management panel.
- Self-Learning MPC - Per-room thermal model (Extended Kalman Filter) that learns your home's heating/cooling behavior over time. Automatic fallback to on/off control while learning.
- Proportional Valve Control - TRVs receive calculated setpoints instead of simple on/off, producing smoother temperature curves with less overshoot.
- Solar Gain Awareness - Estimates solar irradiance from sun position and weather data. The model learns each room's solar response and reduces unnecessary heating.
- Multi-Scheduler - Multiple schedule.* entities per room with selector switching via input_boolean or input_number.
- Manual Override - Boost, eco, or custom temperature with configurable duration and instant UI feedback.
- Presence Detection - Link person.*, device_tracker.*, binary_sensor.*, or input_boolean.* entities globally or per room. Eco temperature is used when all assigned persons are away.
- Ignore Presence per Room - Rooms can opt out of presence detection to always follow their schedule.
- Eco When the Room Is Empty - Per room, optional. Occupancy sensors (motion, presence) always help the thermal model learn how much heat people and devices add. With "Eco when the room is empty"…
- Vacation Mode - Global setback temperature with end date for all rooms.
Shows in Vulpo
Quick Toggle card, Climate card, Chart card, Apple Watch, Control Center, Climate Live Activity.Information
- Installs
- 417 sharing analytics
- GitHub stars
- 418
- Connection
- Works locally
- Upkeep
- Updated in the last 6 months
- Version
- v1.8.0,
- Category
- Climate
- Kind
- Marketplace integration
- Needs
- Needs the Marketplace (HACS on 2026.10 and older)
- Domain
roommind- Issues
- Report an issue
