Server-Side Code Execution Tools for AI Agents, Compared
这条英文动态主要涉及智能体工作流、模型能力与工程、文化创意。原文要点：OpenAI, Anthropic, Google, and OpenRouter each run model-generated code in a hosted sandbox during an API request. This article compares what each sandbox runs, how each one isolates commands, what persists between requests, what it costs, and when a sandbox platform you operate yourself is the better choice.
推荐理由：来自OpenRouter Announcements的《Server-Side Code Execution Tools for AI Agents, ComparedA server-side code execution tool runs the model's commands in the provider's sandbox during your API request, so you don't provision or secure a container. OpenAI, Anthropic, and Google run code for their own models. Our openrouter:shell tool runs commands for any model on the Responses and Messages APIs, and our openrouter:bash tool does the same on the Messages API. This article compares the four on runtime, isolation, persistence, and cost, shows a complete request against our sandbox with the output it ret