Technical Research & Engineering

GLOBAL INTENT COMPANY

Interactive technical environment for machine learning, scientific instrumentation, computational systems, experiments, and project evidence.

Developed independently by founder and researcher Cory Tortorici. Source code, controlled experiments, null results, architectural iterations, and public research logs are made inspectable across all project nodes.

Source Repositories
Laboratory Chronology

LATEST FROM THE LAB

Recent empirical findings, architectural iterations, and null results surfaced directly from active research logs.

Active laboratory research log entries with timestamped records are available in the full research log.

Interactive Spatial Knowledge Graph

EXPLORE THE RESEARCH

Navigate the connected network of research projects, architectural pipelines, and domain clusters in real-time 3D.

Focused on Kernos OS • Orbiting sub-nodes active
Domains:
SPATIAL FOCUS:Kernos OS•Systems Research
GitHub
Systems ResearchKind: engineeringCognitive Microkernel & Autonomous OS Substrate[KERNOS-COGNITIVE-MICROKERNEL]

A dual-layer autonomous operating system treating AI agents as first-class kernel citizens rather than user-space applications. Combines a high-speed Go 1.23+ microkernel backend featuring high-dimensional decaying/reinforcing vector graph memory and self-healing task DAGs with a React 19 / TypeScript desktop windowing environment.

Engineering Objective:Build an operating system substrate where cognitive agents operate as isolated kernel-level citizens coordinated by a self-healing microkernel, synaptic vector graph memory, and peer-to-peer event routing.

Structural Overview

Kernos OS is architected in two complementary tiers: a high-performance Go microkernel server managing system processes, self-healing task DAGs, and high-dimensional vector memory graphs, communicating with a modular React 19 / Vite desktop shell providing visual multi-agent workspaces, terminal pipelines, and hardware monitors.

Canonical Source Artifact

GitHub Repository
Primary Source CodePublic
GI-Company /kernos-os

Canonical public source repository: Go cognitive microkernel and React 19 autonomous operating system.

Canonical GI-Company Source

Design Invariants & Principles

[1]Agents as Kernel Citizens: Cognitive agents are managed as kernel-level processes with explicit scheduling and memory limits rather than unconstrained user applications.
[2]Self-Healing Graph Execution: When execution steps fail, the task engine dynamically races alternative recovery branches across Directed Acyclic Graphs.
[3]Synaptic Memory Dynamics: High-dimensional vector graphs decay inactive memories and reinforce frequently traversed associations.

System Components

Go Microkernel Core

High-speed event coordinator and scheduler managing isolated agent sandboxes, system Undo, and capability policies (server/main.go).

Self-Healing Task DAG Engine

Directed acyclic graph task execution engine that mutates and races parallel recovery branches upon tool or command failure (server/task_engine.go).

Synaptic Vector Graph Memory

High-dimensional memory graph replacing rigid directory hierarchies with synaptic reinforcement and decay dynamics (server/vector_engine.go).

P2P Communication Gateway

Peer-to-peer communication layer for distributed node discovery and cognitive payload exchange (server/p2p_gateway.go).

Desktop Windowing Environment

React 19 desktop window manager with BIOS setup, cinematic boot, terminal, cartographer visualizer, and multi-agent workspace (apps/ and components/).

Technology Stack

Go 1.23+ (Microkernel & Daemons)React 19 & TypeScriptViteVector Graph MemoryDirected Acyclic Graphs (DAG)P2P Gateway NetworkingTailwind CSS

Technical Decisions

Dual-tier decoupled architecture: High-performance Go microkernel backend paired with React 19 frontend desktop environment.
Deterministic recovery routing via parallel branch racing instead of linear single-threaded retries.
Canonical public source code tracked at GI-Company/kernos-os.
Technical Research Explorer | Global Intent Company