编码代理的组件：工具、内存与仓库上下文如何提升 LLM 实践
原标题：Components of A Coding Agent
AI 摘要
本文由 Ahead of AI 发布，作者 Sebastian Raschka 探讨了编码代理（coding agents）的设计与组件，强调代理系统（如 Claude Code、Codex CLI）通过工具使用、内存和仓库上下文管理，使 LLM 在实际编码任务中表现更佳。文章区分了 LLM、推理模型、代理和代理框架（harness）的概念，并指出编码框架（coding harness）是提升模型性能的关键因素，甚至可能使开源模型与专有模型表现相当。
正文节选
Components of A Coding Agent How coding agents use tools, memory, and repo context to make LLMs work better in practice In this article, I want to cover the overall design of coding agents and agent harnesses: what they are, how they work, and how the different pieces fit together in practice. Readers of my Build a Large Language Model (From Scratch) and Build a Large Reasoning Model (From Scratch) books often ask about agents, so I thought it would be useful to write a reference I can point to.