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.

翻译：当前的LLM智能体框架通常将隔离、调度和通信机制实现在应用层，尽管这些机制已由成熟的操作系统提供。本文未引入另一套应用层编排器，而是提出Quine——一套运行时架构与参考实现，将LLM智能体实现为原生POSIX进程。其映射关系明确：身份标识由PID承载，接口通过标准流和退出状态定义，状态体现于内存、环境变量及文件系统，生命周期遵循fork/exec/exit模型。该模型通过单可执行文件递归生成自身新实例的方式实现。通过将智能体抽象锚定于操作系统进程模型，Quine直接从内核继承隔离性、组合能力与资源控制，同时自然支持递归委派、通过exec实现上下文更新以及基于Shell的原生组合。该设计亦揭示了POSIX进程模型的边界：进程为执行提供稳健基座，但并非完整的认知运行时模型。具体而言，分析指出需要超越进程语义的两项扩展方向：面向任务的相对世界（task-relative worlds）与可修正的时间（revisable time）。Quine的参考实现已在GitHub公开。