From Everything-is-a-File to Files-Are-All-You-Need: How Unix Philosophy Informs the Design of Agentic AI Systems

TL;DR

This paper examines how the Unix philosophy of 'everything is a file' influences the design of modern agentic AI systems, promoting unified, composable interfaces for better maintainability and robustness.

Contribution

It draws a connection between Unix abstractions and current AI system design, proposing that file-like models improve agentic system development.

Findings

File-like abstractions enable resource unification.

Code-based specifications improve system composability.

Adopting these models enhances system robustness.

Abstract

A core abstraction in early Unix systems was the principle that 'everything is a file', enabling heterogeneous devices and kernel resources to be manipulated via uniform read/write interfaces. This paper explores how an analogous unification is emerging in contemporary agentic AI. We trace the evolution from Unix to DevOps, Infrastructure-as-Code, and finally autonomous software agents, highlighting how file-like abstractions and code-based specifications collapse diverse resources into consistent, composable interfaces. The resulting perspective suggests that adopting file- and code-centric interaction models may enable agentic systems that are more maintainable, auditable, and operationally robust.