内容来源：https://techcrunch.com/2026/04/15/openai-updates-its-agents-sdk-to-help-enterprises-build-safer-more-capable-agents/

内容总结：

近日，人工智能领域迎来重要进展：以OpenAI和Anthropic为代表的科技企业正加速布局“智能体AI”（Agentic AI）技术，致力于为企业提供构建自动化智能助手的工具。作为该领域的关键举措，OpenAI宣布对其智能体软件开发工具包（Agents SDK）进行重要升级，推出多项新功能，以帮助企业基于其模型开发定制化智能体。

本次升级的核心亮点是新增了“沙盒环境”支持。该功能允许智能体在受控的计算机环境中运行，通过隔离操作空间、限制文件与代码访问权限，在保障系统整体安全的同时执行特定任务。OpenAI产品团队成员卡兰·夏尔马指出，此次升级旨在使SDK兼容各类沙盒服务商，让用户能依托自身基础设施开发“长周期任务智能体”——即能够处理复杂多步骤工作的智能体。

同步推出的“分布式控制框架”进一步强化了开发体验。该框架允许企业在前沿模型上部署和测试智能体，使其能够在受控工作空间内安全使用文件与核准工具。OpenAI表示，新功能将首先在Python版本中上线，TypeScript版本预计后续推出，未来还将持续扩展代码模式、子智能体等能力。

目前，新版SDK已通过API向所有客户开放，按标准计费模式提供服务。这一系列升级标志着智能体AI技术正朝着更安全、更易用的方向演进，有望为企业级应用场景提供更强大的自动化解决方案。

中文翻译：

智能体AI正成为科技行业最新的成功典范，OpenAI与Anthropic等公司竞相为企业打造自动化助手工具。为此，OpenAI近日升级了智能体软件开发工具包（SDK），推出多项新功能，帮助企业基于OpenAI模型构建专属智能体。

新版SDK新增沙盒环境功能，使智能体能在受控计算机环境中运行。这项功能至关重要——由于智能体偶尔会表现出不可预测性，完全无监督的运行方式可能存在风险。通过沙盒集成，智能体可在特定工作区内以隔离模式运作，仅在执行特定操作时访问文件与代码，从而保障系统整体完整性。

OpenAI表示，新版SDK同时为开发者提供了前沿模型的分布式控制框架，使智能体能在工作区内处理文件并使用经核准的工具。（在智能体开发领域，“控制框架”指代智能体除底层模型外的其他组件。分布式控制框架通常可帮助企业部署并测试基于前沿模型的智能体，这些模型被视为当前最先进的通用模型。）

OpenAI产品团队成员卡兰·夏尔马向TechCrunch透露：“本次升级的核心目标，是让现有智能体SDK兼容各类沙盒服务提供商。”他进一步指出，结合新的控制框架功能，用户将能“依托自有基础设施，运用我们的框架构建长期任务型智能体”。这类“长期任务”通常指代更复杂、多步骤的工作流程。

在Disrupt大会遇见您的下一个投资机遇
新一轮融资、关键人才招募、突破性机遇——尽在TechCrunch Disrupt 2026大会。届时将有超万名创业者、投资者与科技领袖齐聚，参与为期三天的250多场实战研讨、高效人脉对接与市场定义型创新展示。立即注册可享最高410美元优惠。

OpenAI透露将持续扩展智能体SDK功能。现阶段新的控制框架与沙盒能力将率先支持Python语言，TypeScript版本预计后续发布。公司表示正在开发更多智能体功能（如代码模式与子智能体），未来将同步适配Python与TypeScript。

新版智能体SDK功能将通过API向所有客户开放，并采用标准计费模式。

英文来源：

Agentic AI is the tech industry’s newest success story, and companies like OpenAI and Anthropic are racing to give enterprises the tools they need to create these automated little helpers. To that end, OpenAI has now updated its agents software development toolkit (SDK), introducing a number of new features designed to help businesses create their own agents that run on the backs of OpenAI’s models.
The SDK’s new capabilities include a sandboxing ability, which allows the agents to operate in controlled computer environments. This is important because running agents in a totally unsupervised fashion can be risky due to their occasionally unpredictable nature.
With the sandbox integration, agents can work in a siloed capacity within a particular workspace, accessing files and code only for particular operations, while otherwise protecting the system’s overall integrity.
Relatedly, the new version of the SDK also provides developers with an in-distribution harness for frontier models that will allow those agents to work with files and approved tools within a workspace, the company said. (In agent development, the “harness” is a term that refers to the other components of an agent besides the model that it’s running on. An in-distribution harness often allows companies to both deploy and test the agents running on frontier models, which are considered to be the most advanced, general-purpose models available.)
“This launch, at its core, is about taking our existing Agents SDK and making it so it’s compatible with all of these sandbox providers,” Karan Sharma, who works on OpenAI’s product team, told TechCrunch.
The hope is that this, paired with the new harness capabilities, will allow users “to go build these long-horizon agents using our harness and with whatever infrastructure they have,” he said.
Such “long-horizon” tasks are generally considered to be more complex and multi-step work.
Meet your next investor or portfolio startup at Disrupt
Your next round. Your next hire. Your next breakout opportunity. Find it at TechCrunch Disrupt 2026, where 10,000+ founders, investors, and tech leaders gather for three days of 250+ tactical sessions, powerful introductions, and market-defining innovation. Register now to save up to $410.
Meet your next investor or portfolio startup at Disrupt
Your next round. Your next hire. Your next breakout opportunity. Find it at TechCrunch Disrupt 2026, where 10,000+ founders, investors, and tech leaders gather for three days of 250+ tactical sessions, powerful introductions, and market-defining innovation. Register now to save up to $410.
OpenAI said it will continue to expand the Agents SDK over time, but initially, the new harness and sandbox capabilities are launching first in Python, with TypeScript support planned for a later release. The company said it’s also working to bring more agent capabilities, like code mode and subagents, to both Python and TypeScript.
The new Agents SDK capabilities are being offered to all customers via the API, and will use standard pricing.