Menu

Blog

nucore-ai-programs

It’s Alive!

, , , , , , ,

It’s alive. And you need to see this in the upcoming OpenADR Webinar:

📅 Date: Thursday, January 29th 8AM US Pacific Time

🔗 Register now: [ link ].

We’re not talking vaporware or slideware. We’re talking a live, working demo of something that’s never been done before, and it’s going to change how demand flexibility and smart homes work forever.

The Problem Everyone’s Been Ignoring

Matter gave us interoperability. Home Assistant gave us open-source control. But they all still force developers and manufacturers into predefined device types. Light. Switch. Thermostat. Lock.

Your innovative new device that’s part heater, part dehumidifier, part air purifier? Good luck finding which category to shoehorn it into. And forget about creating a “Peak Event Optimizer” service that coordinates across devices, that’s not even a “device type.”

Enter NucoreAI: The First Truly Typeless Open-Source Smart Home Platform

🔹 No device types exist. Period. A Zigbee light bulb, a demand response service, and a robot assistant manager all use the exact same pattern: they describe their capabilities naturally, and the platform understands them.

🔹 No standards battles. Use whatever protocol you want (Zigbee, Z-Wave, WiFi, BACnet, OpenADR). Your plugin abstracts it. The platform doesn’t care.

🔹 Everything describes itself at runtime. Not by conforming to a specification. Not by implementing predefined “clusters.” Devices tell the platform what they can do in natural language: Properties, Commands, Constraints, and AI reads it. All of it.

🔹 AI interprets. Platform executes. You talk naturally: “Set all cool temps to 72 on weekdays when I’m home in the summer months.” AI creates the execution plan. The platform validates it against device constraints. Then, and only then, it executes. You get intelligence without losing control.

Why This Is Different

Home Assistant? Amazing, but still built on device types. Matter? Industry standard, but requires certification for predefined categories. NuCoreAI? Genuinely typeless. A service plugin is indistinguishable from a device plugin. The platform orchestrates across ALL of them: no special cases, no exceptions.

See It Live

I’ll be demonstrating eisyAI at the OpenADR webinar with real demand response scenarios. Real devices. Real natural language. Real orchestration across devices AND services. Something that literally doesn’t exist anywhere else.

This isn’t a proof of concept. It’s working. It’s alive. Come see it.

  • Command/control/monitoring of one or many devices using English as if you are talking to a human
  • Creation of complex conditional logic programs right in front of your eyes
  • Real capabilities, real devices, real scenarios
  • Live Q&A

📅 Date: Thursday, January 29th 8AM US Pacific Time

🔗 Register now: [ link ].

Open source. MIT licensed. Built by a non-profit foundation. No vendor lock-in. Ever.

The smart home industry has been fighting standards battles for 20 years. We just ended the war.

standards

Do We Really Need Standards for Demand Flexibility?

No, we don’t!

Why? Because when devices describe themselves, their capabilities, and properties, you can fine-tune an LLM to understand what you mean without you having to spell it out. 

Examples:

“What’s the cabin temp?”
→ Cabin Temperature for Batmobile is 72°F
(It knows you mean your Tesla’s cabin. Because you have one!)

Make it multi-device:

“How much charge do I have, how many miles can I drive, and what’s the price?”
→ State of Charge: 44.72%
→ Range: 111.2 miles
→ Utility Price (oadr3): $0.0864

Not just energy:

“Is it paired? And what’s playing?”
→ PulseSound: Paired (Bluetooth speaker)
→ YouTube Player: Classical

Stack properties and commands:

“Turn on both Hues, then set left Hue to red in 3 seconds and right Hue to blue in 4.”

Even automation & optimization:

“If price < $0.75 and range > 150 miles, set charge limit to 90% and start charging. But only on weekdays.”

Add a plugin platform for any device or service, and standards become irrelevant. Plugins describe themselves in English, and it just works because the platform understands what you mean!

That’s NuCore.ai: an MIT-licensed (FREE) fine-tuned LLM and natural-language platform for Smart Buildings. Run it locally at the edge (with llama.cpp) or in the cloud.

The age of standards is ending.

The age of understanding has begun. Come play with it today!

Smart,Home,With,Blue/light,Green,Glassmorphism,Our,Vision,Who,We

Is It Paired?

The short answer is Yes! Because it knows you’re talking about your Bluetooth speaker.

So why exactly do we still need mappings, ontologies, and standards just to adjust thermostat set points, charge a car, optimize DERs (Distributed Energy Resources), or even pair Bluetooth speakers or play music?

The short answer is: we don’t.

With NuCore.ai, a fine-tuned LLM and platform for Smart Buildings, MIT licensed and able to run locally at the edge or in the cloud, none of that is needed.

Things describe themselves in plain English at runtime. You speak to it as you would a person, and the model understands what you mean.

  • “What’s the cabin temp?”
    → Cabin Temperature for Batmobile is 72°F (it knows you’re asking about your Tesla’s cabin temp, because you have one!)

  • “How much charge do I have and how many miles can I drive and what’s the price?”
    → State of Charge for Batmobile is 44.72%
    → Estimated Range for Batmobile is 111.2 miles
    → Price for Utility Signals (oadr3) is: 0.0864$

  • “Turn on both Hues and then set left Hue to red in 3 seconds; set right Hue to blue in 4 seconds.”

  • “If price < $0.75 and miles I can drive is more than 150, set charge limit to 90% and start charging. But only on weekdays.”

The age of standards is ending.

The age of understanding has begun, and you are invited to play with everything right now!

Indoor,Photo,Of,Dramatic,Image,Of,An,Artistic,Looking,Computer

From OPEn to NuCoreAI

It’s hard to believe it’s only been seven months since we introduced OPEn. It started as a bold idea: a plugin framework that uses AI to understands smart home and IoT devices, interpret their properties and commands at runtime, and generate intelligent execution plans for optimization. In essence, eliminating the need for rigid standardization across device and grid protocols.

By February 2025, we had a fully functional demo running on cutting-edge tech: Claude 3.5 Sonnet, RAG with Pinecone, and a healthy dose of optimism. The results were stunning, the interest was immense, and we were flying high … until we realized we were spending over $100/month on AI services for just one demo! At roughly 10 queries a day over two months, reality set in: the business model simply wasn’t sustainable.

And that’s when the real adventure began: the birth of NuCoreAI and our deep dive into the fascinating world of local AI. Suddenly, our days were filled with fine-tuning, parameter counts, LoRA/PEFT, Alpaca-style datasets, vector databases, context window gymnastics, Hugging Face, Unsloth, Colab sessions, temperature tweaking, GPUs vs. NPUs, and yes, prompt engineering (on loop).

Somewhere in that whirlwind, we had more than a few LOL moments, especially when testing prompts that explicitly told LLMs not to make things up. Naturally, they responded with absolute confidence, and zero regard for accuracy:

Me: What is nodeshit?
LLM: Nodeshit is a command that allows you to interact with IoX nodes directly from the IoX shell.

Me: What is crap?
LLM: In the context of IoX, ‘crap’ refers to a device that is not working properly or at all. It can also describe a device causing issues or conflicts with the IoX system.

So where are we now? At a pretty exciting milestone: we’re seeing up to 80% accuracy using LLaMA 3 8B, with reranking as a first step. Next up: exploring model and technique optimizations, such as caching, and defining minimum hardware requirements for maximized accuracy and speed.

Want to dive in? Check out our GitHub for the code, models, and all the AI goodies we’ve cooked up so far.