Abstract

Specialized, finetuned and RAG-enhanced open-source Large Language Models are key elements in emerging AI agent applications. However, those agent apps also present unique challenges to the traditional cloud computing and SaaS infrastructure, including new requirements for application portability, virtualization, security isolation, costs, data privacy, and ownership.

GRT AI is a decentralized computing infrastructure that enables everyone to create, deploy, scale, and monetize their own AI agents that reflect their styles, values, knowledge, and expertise. A GRT AI node consists of a high-performance and cross-platform application runtime, a finetuned LLM, a knowledge embedding model, a vector database, a prompt manager, an open API server, and a plugin system for calling external tools and functions using LLM outputs. It can be deployed by any knowledge worker as a digital twin and offered as a web API service. A new class of tradeable assets and a marketplace could be created from individualized knowledge bases and components. Similar GRT AI nodes are organized into GRT AI domains, which offer trusted and reliable AI agent services to the public. The GRT AI node and domains are governed by the GRT AI DAO (Decentralized Autonomous Organization). Through Purpose Bound Money smart contracts, the GRT AI network is a decentralized marketplace for AI agent services.