Comprehensive architecture overview of the NOMOS framework
NOMOS is a sophisticated multi-step agent framework that combines the intelligence of Large Language Models with the reliability and predictability of state machines. This document provides comprehensive architecture diagrams that illustrate the system’s design and component interactions.
The following diagram shows the high-level architecture of NOMOS, including its core components and their relationships:
This diagram illustrates how agents are created, sessions are managed, and how the system handles user interactions:
This diagram shows how flows organize steps and manage context transitions:
This diagram illustrates how the LLM makes decisions and executes tools within the step-based architecture:
This diagram shows the API layer and how different clients interact with the system:
This diagram illustrates how NOMOS manages different types of memory and context across sessions and flows:
This diagram shows how NOMOS integrates and manages different types of tools:
This final diagram shows the development workflow and deployment options for NOMOS agents:
The NOMOS architecture is designed around several key principles:
This architecture enables NOMOS to bridge the gap between rapid prototyping and production-ready AI agent deployment while maintaining the testability and reliability expected in enterprise software systems.