How intelligence meets the physical world

More than connected. Connected to context.

A room is more than a collection of devices. ALYT brings their signals, controls and relationships into one environment for Simone to work with.

Explore the platformFind your hub

Sense.Connect.Understand.

Follow the signals

Computers gained intelligence. Now spaces can too.

AIoT, with a place to think.

AIoT combines artificial intelligence with connected devices. ALYT gives that intelligence a practical foundation: rooms, device capabilities, state, permissions and ways to act in the physical environment.

ALYT turns that idea into a platform: shared device capabilities, persistent rooms and state, local routines and Simone. The connections are the foundation. A useful environment is the point.

Reading the room

A reading is useful. Context makes it better.

An open window, a falling temperature, heating still on. The value lies in how observations relate. ALYT’s environmental intelligence is built around that idea: connect the signals, consider their timing and respect the limits of what they tell you.

Good context starts with compatible sensors, fresh observations and clear permissions.

Inside the reasoning

A clearer picture of activity in the room.

A door opens. A motion sensor reports activity. Considering the room and timing gives those signals more meaning than either reading alone.

Sensor inputs

Motion sensorRecent activity
RoomLocation context
Door contactRecent opening
SimoneLocal AI on Hub AI

What the signals suggest

Activity worth a closer look

The useful question

“What changed, where—and how recently?”

How the signals combine

A presence estimate needs recent evidence. A device joining Wi-Fi does not prove who is in a room, and a quiet sensor does not prove the room is empty.

Occupancy is an estimate. Security actions follow the security system’s own rules.

Inside the reasoning

Know more about the appliances you already own.

A power-monitoring plug and a vibration sensor offer different views of the same appliance. Their sequence matters as much as their latest reading.

Sensor inputs

Power monitorBack near idle
Vibration sensorMovement settled
Recent historyCycle pattern
SimoneLocal AI on Hub AI

What the signals suggest

The cycle may be complete

The useful question

“Has the cycle finished, or is this a pause?”

How the signals combine

A pause can look like the end of a cycle. Useful interpretation compares the recent pattern and keeps uncertainty visible.

Compatible sensors provide clues. Appliance-specific interpretation needs evidence; a low reading is not permission to cut power.

Inside the reasoning

Understand why a room is losing heat.

A window contact, temperature readings and heating state tell a more useful story together. Room relationships make it possible to ask the right question.

Sensor inputs

Window contactOpen
Room temperatureFalling
Heating stateStill active
SimoneLocal AI on Hub AI

What the signals suggest

Heat may be escaping

The useful question

“Is an open window working against the heating?”

How the signals combine

Timing matters: did the room begin cooling after the window opened? A useful suggestion also needs to account for comfort settings and the household’s permissions.

An environmental explanation is a hypothesis. Changes must respect the controls and permissions of the installation.

Resident intelligence · close to the environment

The internet can disappear. Local capability should not.

Hub AI runs Simone’s model locally, alongside the space it serves. Supported local reasoning can avoid the internet connection, remote API and model queue. Every hub runs local routines and sensor-based protection; local devices still need power and working connections.

Built around the space

A space with context of its own.

A persistent model of the environment. Resident intelligence. Governed actions. Connections across brands. Together, these create the foundation for spaces that can become more useful as AI advances—without handing their control to a single external model provider.

Less waiting on the outside world.

For a local task, reasoning can avoid a remote-model round trip and its variable availability. Response time still depends on the task, model and devices.

Sensitive context can stay close.

Supported local processing can keep environmental information in the space. External AI and connected services have separate authorization and data requirements.

Use intelligence where it adds value.

A routine does not need a new AI decision every time a sensor changes. Let defined rules handle familiar actions and use model reasoning when interpretation is useful.

Several ways to stay connected.

Compatible Zigbee and Bluetooth LE devices can talk directly to the hub without your Wi-Fi router. Matter over Thread uses a local mesh; Wi-Fi devices use the home network. Local operation avoids dependence on an internet connection, while each device still needs its own working local path.

Thread uses IPv6, and Wi-Fi/LAN integrations use IP networking. Local AI means no cloud round trip for local model processing; it does not mean every device avoids TCP/IP.

Meet Hub AI

Explore the platform

A clear view of what connects.

Compare models, check compatible devices and explore documented workflows. Developers can extend the platform through supported integrations.

Hub features

Compare the models and their connection options.

Compatible connections

See what connects, and how.

Routines in practice

Read the homeowner guide to saved routines.

Build with ALYT

Explore the public API, SDKs and connector documentation.

Good questions. Straight answers.

Does an ALYT home work without internet?

Local routines and compatible local device controls run on the hub while it and the devices remain powered and connected. Cloud AI on Hub and Hub Music needs internet. Hub AI runs Simone’s model locally, but online content and cloud integrations still need their services.

What is resident intelligence, and where does it run?

Resident intelligence is AI intended to understand and operate within the space it serves. Simone is ALYT’s own intelligence layer; Hub AI runs its custom-trained model locally. The current Hub and Hub Music models use cloud Simone. Local routines and sensor-based protection run on every model.

Is Matter the same thing as AIoT?

No. Matter is a standard for communication between compatible smart-home devices. AIoT describes combining AI with connected things. ALYT supports Matter over Wi-Fi or Thread on all three hub models, alongside Wi-Fi, Bluetooth LE and Zigbee connectivity.

Can ALYT bring different device brands together?

Yes, through supported connectors and shared device capabilities. Compatibility depends on the specific device and connection. Check ALYT’s connector catalogue for supported brands and workflows; a shared radio standard alone does not mean every feature of every device is supported.

Does edge AI mean the home stops using TCP/IP?

Edge AI describes where the model runs: on local hardware. It can operate without an internet connection when its inputs and outputs are local. Zigbee and direct Bluetooth LE connections can bypass a Wi-Fi router; Thread uses IPv6, and Wi-Fi devices still use IP networking. Local connections must remain operational.

Can a private home agent also serve an office or building?

The same combination of AI, connected devices and permissions can apply to other spaces. ALYT offers discussions for dedicated single-customer deployments, including businesses and facilities. Device coverage, local operation and access are agreed for each project. Private model processing refers to Hub AI; connected online services keep their own data requirements.

Local at the core. Open to more intelligence.

Bring your devices together. Give everyday routines a home. Meet ALYT.

Register your home Find your hub