AI Navigate

Quine: Realizing LLM Agents as Native POSIX Processes

arXiv cs.AI / 3/20/2026

📰 NewsDeveloper Stack & InfrastructureModels & Research

Key Points

  • Quine introduces a runtime architecture that realizes LLM agents as native POSIX processes rather than at the application layer.
  • The mapping is explicit: identity as PID, interface as standard streams and exit status, state as memory/env/filesystem, and lifecycle as fork/exec/exit, with a single executable that recursively spawns itself.
  • This design leverages OS-level isolation and resource control and enables shell-native composition and context renewal via exec, while acknowledging the limits of processes as a cognitive runtime.
  • The authors point to extensions beyond process semantics (task-relative worlds and revisable time) and provide a public GitHub reference implementation.

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.