OFFLINE EDGE AI
Brix Edge / In development
Intelligence that works offline.
The on-device AI stack being built under Maisonate: local inference, site adaptation and fleet sync when connectivity returns. Opening to integrators and hardware partners as it matures.
Cloud AI assumes a connection. Real sites disagree.
The places most worth monitoring are the places the network forgot: paddocks, worksites, coastlines, orbit. Brix Edge is the AI stack we are building under Maisonate so intelligence can live on the asset itself. It will open to partners as it matures.
The stack, in three layers.
The layers Maisonate is being built on, with Brix Watch to follow. Each is meant to start useful, then adapt to site conditions over time.
On-device inference
Models sized for embedded hardware, answering locally without a cloud round trip.
Site adaptation
Designed so each device settles into its own site, its own noise floor and its own normal, without shipping raw data anywhere.
Fleet sync
When a link appears, devices exchange model improvements and telemetry summaries. Raw data stays home.
Built for the people who build.
Developers
A stack that assumes the network is down, because on real sites it usually is. Design notes will be published as the layers land.
Integrators
Ship monitoring and control into places cloud vendors will not quote: farms, heavy industry, marine, remote plant.
Hardware partners
Put a reasoning layer on your sensors and controllers without rebuilding your firmware team.
Follow the build.
Design notes and reference hardware as they are ready, and direct access to the team. Nothing to download yet, and we will not pretend otherwise.
Partnership enquiries: mark@fitbrix.com