GBR SYSTEM DEMONSTRATION

On a small device, with no external server

Meet GBR SYSTEM, built on its own architecture, on a real device. It answers from its own memory and remembers new knowledge taught through conversation.

[First Look] GBR SYSTEM Demo: Memory-Centric Sovereign AI with an Independent Architecture

Filmed on one NVIDIA Jetson Orin Nano Super with the network disconnected.

In this demo, questions and motion commands are typed on a keyboard. Active tracking and speech recognition are in development.

Length
14 min 53 sec
Published
November 1, 2026

Demo checklist

Answers grounded in memory

GBR reads knowledge stored on the device without calling an external server. Sources accompany its answers.

Teach it, and the very next answer uses it

A user teaches a new fact and confirms that GBR should remember it. GBR uses that memory in the next answer without restarting or retraining.

Retract a memory from use in answers

A retracted memory is no longer used in answers. The record of its retraction remains.

Control a camera and motor with natural language

It understands the words it was taught and controls the camera and motor. Answering questions and moving hardware happen on the same device.

Reasoning from memory

The latter part of the video presents the Sudoku results of the GBR reasoning engine. Explore the published results and materials on the research page and GitHub.

An independent architecture connecting memory and reasoning

GBR SYSTEM is made of GBR DBMS, which stores and finds memories, and GBR AI, which handles everything from perception to generation. Memory and reasoning connect within one system.

Bring GBR to your device

Let's explore applications for robots and embedded devices together. Tell us about the knowledge and device requirements you need.

agent@zigulabs.com