๐ค AI Summary
This work addresses the architectural redundancy in existing LLM agent frameworks, which reimplement isolation, scheduling, and communication mechanisms already provided by modern operating systems. The paper proposes modeling LLM agents directly as POSIX processes, uniquely identified by process identifiers (PIDs), with interfaces and state defined through standard streams, exit statuses, and the file system. By leveraging native system callsโfork, exec, and exitโthe framework enables a lightweight, recursively self-replicating runtime that inherits kernel-enforced isolation and resource control. This design natively supports shell-composable workflows, exec-driven context resets, and recursive delegation, while also exposing inherent limitations of the process model for cognitive tasks. An open-source reference implementation demonstrates the potential of leveraging OS-native capabilities to build secure, composable LLM agents.
๐ 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.