Quine: Realizing LLM Agents as Native POSIX Processes

TL;DR

Quine proposes a novel architecture for LLM agents as native POSIX processes, leveraging OS features for isolation, resource control, and composition, with a publicly available implementation.

Contribution

It introduces a process-based runtime architecture for LLM agents, moving away from application-layer implementations to OS-native processes.

Findings

Quine enables LLM agents to run as native POSIX processes.

The architecture inherits OS-level isolation and resource management.

A reference implementation is available on GitHub.

Abstract

Current LLM agent frameworks often implement isolation, scheduling, and communication at the application layer, even though these mechanisms are already provided by mature operating systems. Instead of introducing another application-layer orchestrator, this paper presents Quine, a runtime architecture and reference implementation that realizes LLM agents as native POSIX processes. The mapping is explicit: identity is PID, interface is standard streams and exit status, state is memory, environment variables, and filesystem, and lifecycle is fork/exec/exit. A single executable implements this model by recursively spawning fresh instances of itself. By grounding the agent abstraction in the OS process model, Quine inherits isolation, composition, and resource control directly from the kernel, while naturally supporting recursive delegation, context renewal via exec, and shell-native composition. The design also exposes where the POSIX process model stops: processes provide a robust substrate for execution, but not a complete runtime model for cognition. In particular, the analysis points toward two immediate extensions beyond process semantics: task-relative worlds and revisable time. A reference implementation of Quine is publicly available on GitHub.