Introducing the Agents API

隆重推出 Agents API

Build and run cloud agents with the Codex harness, fully managed by OpenAI.

使用 Codex 架构构建并运行云端智能体（Agents），并由 OpenAI 进行全面托管。

As we’ve scaled Codex and ChatGPT for Work to millions of people around the world, we’ve learned what it takes to make long-running agents work well in practice. Useful agents need a powerful harness that manages context, uses tools efficiently, and coordinates subagents. They also need infrastructure that keeps them running reliably for days, with environments where they can work with files, run code, and save intermediate results.

随着我们将 Codex 和 ChatGPT for Work 推广至全球数百万用户，我们深刻理解了如何让长时间运行的智能体在实际应用中表现出色。实用的智能体需要强大的架构来管理上下文、高效使用工具并协调子智能体。它们还需要能够维持数天可靠运行的基础设施，以及可以处理文件、运行代码并保存中间结果的运行环境。

Today, we’re introducing the Agents API in public beta, bringing that same harness and infrastructure that powers Codex to developers through a simple, flexible API.

今天，我们正式推出 Agents API 公测版，通过简单且灵活的 API，将驱动 Codex 的核心架构与基础设施提供给广大开发者。

What our customers are saying about Agents API

客户对 Agents API 的评价

“With the Agents API, our evaluation score went from 0.71 to 0.85. The subagent support in the API is great and drastically sped up our workflow. Previously it was pretty cumbersome to observe and orchestrate subagents in our old setup but the new APIs gave us a 4x latency reduction. We spent a long time trying to optimize for this and the subagent flows were a huge out-of-the-box lift.” — Jack Weissenberger, CTO, Ciridae

“通过使用 Agents API，我们的评估分数从 0.71 提升到了 0.85。API 中的子智能体支持非常出色，极大地加快了我们的工作流程。在旧系统中，观察和编排子智能体非常繁琐，而新的 API 使我们的延迟降低了 4 倍。我们曾花费大量时间进行优化，而子智能体流程带来的开箱即用效果提升巨大。” — Jack Weissenberger，Ciridae 首席技术官

“Transforming real-world businesses means deploying AI into workflows of every shape. Agents API supplies the harness; the environment, context, and UX stay ours. With our AI platform Nexus we now stand up agents in hours across industries, from residential services to architecture.” — Rasmus Wissmann, CTO, Long Lake

“重塑现实世界的业务意味着将 AI 部署到各种形态的工作流中。Agents API 提供了核心架构，而环境、上下文和用户体验则由我们掌控。借助我们的 AI 平台 Nexus，我们现在可以在数小时内跨行业部署智能体，涵盖从住宅服务到建筑设计的各个领域。” — Rasmus Wissmann，Long Lake 首席技术官

Build cloud agents with a single API call

通过单次 API 调用构建云端智能体

With the Agents API, you can create a production-ready agent in a single API call by specifying the task, model, tools, and environment:

借助 Agents API，您只需通过一次 API 调用，指定任务、模型、工具和环境，即可创建一个生产就绪的智能体：

(Code snippet omitted for brevity)

OpenAI hosts and maintains the harness. You choose the agent’s compute environment: in an OpenAI-managed sandbox, on your own infrastructure, or with one of our sandbox partners. The Agents API gives you a strong foundation for building agents on top of our optimized agent harness and infrastructure, so you can focus on the tools, knowledge, and workflows that make your agent unique.

OpenAI 负责托管和维护该架构。您可以选择智能体的计算环境：在 OpenAI 管理的沙箱中、在您自己的基础设施上，或通过我们的沙箱合作伙伴运行。Agents API 为您在 OpenAI 优化的智能体架构和基础设施之上构建智能体提供了坚实基础，让您可以专注于打造使您的智能体独一无二的工具、知识库和工作流。

Choose your agent environment

选择您的智能体环境

Different workloads need different compute, storage, and deployment options. The Agents API lets you choose a sandbox that fits your application.

不同的工作负载需要不同的计算、存储和部署选项。Agents API 让您可以选择最适合您应用的沙箱。

We’re partnering with ecosystem providers, including Blaxel, Cloudflare, Daytona, DigitalOcean, E2B, Modal, Oracle, Runloop, and Vercel, to provide first-class integrations for a range of needs:

我们正在与包括 Blaxel、Cloudflare、Daytona、DigitalOcean、E2B、Modal、Oracle、Runloop 和 Vercel 在内的生态系统提供商合作，为各种需求提供一流的集成方案：

Fully managed environments or deployments within your VPC. 完全托管的环境或在您的 VPC 内进行部署。
Specific file and secret storage mechanisms. 特定的文件和密钥存储机制。
Different CPU, GPU, and memory configurations, with performance, cold-start, and cost profiles to match your company’s workflow. 不同的 CPU、GPU 和内存配置，并提供匹配您公司工作流的性能、冷启动和成本方案。