为万亿智能体而构建

Over the past few months, something big has started to happen with agents. Near the tail end of last year, we began to reach the point where coding agents were able to complete much longer running tasks, and didn’t require as much hand-holding throughout the development process.

在过去几个月里，智能体领域开始发生一些大事。去年年底，我们开始达到这样的点：编码智能体能够完成更长的运行任务，并且在开发过程中不需要那么多手把手指导。

These agents are no longer chatbots with basic tools. Instead, these agents often have their own sandboxed compute environment, have the ability to write and run code for any problem they run into, interact with APIs and CLIs directly, have their own file systems and long-term memory, and so on. This set of core primitives, general progress on agentic harness best practices, and insane model progress on agentic tool-use and software development, offer a glimpse of agents that can handle any task that can be thrown at them.

这些智能体不再是带有基本工具的聊天机器人。相反，这些智能体通常拥有自己的沙箱计算环境，能够为遇到的任何问题编写和运行代码，直接与 APIs 和 CLIs 交互，拥有自己的文件系统和长期记忆，等等。这一组核心原语、agentic harness 最佳实践的总体进步，以及在 agentic tool-use 和软件开发方面的疯狂模型进步，展示出智能体能够处理扔给它们的任何任务。

And while this architecture was initially defined by a mix of coding agents like Claude Code, Devin, Codex, Factory, Cursor, or Replit, we’ve recently crossed the chasm into all areas of personal experiences and knowledge work now with agents like Claude Cowork, Perplexity Computer, Manus, and of course OpenClaw, which took things far further into the future, with an agent that runs 24/7 in its own persistent environment.

虽然这种架构最初由像 Claude Code、Devin、Codex、Factory、Cursor 或 Replit 这样的编码智能体定义，但我们最近已跨越鸿沟，进入个人体验和知识工作的所有领域，现在有像 Claude Cowork、Perplexity Computer、Manus 以及当然是 OpenClaw 这样的智能体，后者将事情推向更远的未来，一个在自己的持久环境中 24/7 运行的智能体。

Because of rapidly advancing capabilities, agents will be brought into nearly all areas of work. Agents will be deployed to review every contract that gets written, handle the front lines of most customer support cases, audit every company’s financials, comb through every piece of medical research for drug discovery, generate nearly all code t...