# Noviterm AI - **Website:** - **Primary alias:** `noviterm.com` ## Description Noviterm AI develops predictive climate control software that helps commercial buildings reduce heating and cooling costs and lower carbon emissions without replacing existing HVAC equipment. Its system connects to boilers, chillers, valves, and fans through common protocols including BACnet, Modbus, and KNX. Using a physics-informed Neural ODE digital twin, weather and solar forecasts, electricity tariffs, and occupancy patterns, it predicts building conditions up to 12 hours ahead and adjusts HVAC schedules every 15 minutes to maintain comfort efficiently. The system runs on an on-premises edge gateway, keeping computation and building data local while allowing operation without an internet connection. Noviterm AI says it can begin working on day one without historical building data, and reports potential energy and CO₂ reductions of up to 30%. Its services also include real-time savings dashboards, emissions tracking, and automated measurement and verification reports aligned with IPMVP standards. Noviterm AI supports building operators seeking energy efficiency improvements, with a free consultation to estimate potential savings based on a building’s type, size, and HVAC system. ## Industries - 🖥 Computers Electronics and Technology - 🖥 Artificial Intelligence and Machine Learning _(under Computers Electronics and Technology)_ - 🏭 Heavy Industry and Engineering ## Links - [linkedin](https://linkedin.com/company/noviterm-ai) ## Logos & icons - logo _(primary)_ — PNG — [download](https://cdn.brandfetch.io/idWO5btdyL/w/776/h/176/theme/light/logo.png?c=1bxid64Mup7aczewSAYMX&t=1791377279077) - icon _(primary)_ — JPEG — [download](https://cdn.brandfetch.io/idWO5btdyL/w/100/h/100/theme/dark/icon.jpeg?c=1bxid64Mup7aczewSAYMX&t=1791377279209) ## Colors | Name | Hex | Theme | | --- | --- | --- | | Navy Blue | #020381 | accent | ## Fonts - var(--font-display) — asset _(custom)_ - var(--font-body) — asset _(custom)_ --- _Source: _ _See [/llms.txt](/llms.txt) for a full list of agent-readable pages, and [/auth.md](/auth.md) for how agents authenticate._