A deep dive into what Anthropic, OpenAI, Perplexity and LangChain are actually building. Covering the orchestration loop, tools, memory, context management, and everything else that transforms a stateless LLM into a capable agent.

深入探讨 Anthropic、OpenAI、Perplexity 和 LangChain 实际在构建什么。涵盖 orchestration loop、tools、memory、context management，以及将无状态 LLM 转变为强大 agent 的其他一切。

You've built a chatbot. Maybe you've wired up a ReAct loop with a few tools. It works for demos. Then you try to build something production-grade, and the wheels come off: the model forgets what it did three steps ago, tool calls fail silently, and context windows fill up with garbage.

你已经构建了一个聊天机器人。也许你已经用几个工具设置了一个 ReAct 循环。它适用于演示。然后你尝试构建生产级的东西，车轮就开始脱落：模型忘记了三步前做了什么，工具调用静默失败，上下文窗口充满了垃圾。

The problem isn't your model. It's everything around your model.

问题不在于你的模型，而在于模型周围的一切。

LangChain proved this when they changed only the infrastructure wrapping their LLM (same model, same weights) and jumped from outside the top 30 to rank 5 on TerminalBench 2.0. A separate research project hit a 76.4% pass rate by having an LLM optimize the infrastructure itself, surpassing hand-designed systems.

LangChain 通过仅更改包装其 LLM 的基础设施（相同模型、相同权重）证明了这一点，并从 top 30 之外跃升至 TerminalBench 2.0 的第 5 名。一个独立的研究项目通过让 LLM 优化基础设施本身达到了 76.4% 的通过率，超越了手工设计的系统。

That infrastructure has a name now: the agent harness.

现在，这种基础设施有了一个名字：代理 harness。

What Is the Agent Harness?

什么是 Agent Harness？

The term was formalized in early 2026, but the concept existed long before. The harness is the complete software infrastructure wrapping an LLM: orchestration loop, tools, memory, context management, state persistence, error handling, and guardrails. Anthropic's Claude Code documentation puts it simply: the SDK is "the agent harness that powers Claude Code." OpenAI's Codex team uses the same framing, explicitly equating the terms "agent" and "harness" to refer to the non-model infrastructure that makes the LLM useful.

该术语于2026年初正式化，但该概念早已存在。harness 是围绕 LLM 的完整软件基础设施：orchestration loop、tools、memory、context management、s...