提问 HN：如何将 Agent 框架与代码库分离？
1 分•作者: FrankRay78•2 个月前
我对如何将 Agent 的框架和代码分离（最好是分离的仓库）的任何方法或想法都感兴趣。
规范驱动开发对我来说进展顺利，同时还有大量的 Agent 和技能等。
然而，我发现 .Claude/memory/*、docs/*、.specify/*、钩子和扩展、上下文管理工具等，管理起来的开销有时与代码库本身一样大。
而且，它们都混在一起，在同一个仓库里。这肯定是一种反模式。
有更好的方法来做到这一点吗（目前还没有）？或者这会是 AI 发展的下一个前沿领域？
查看原文
I’m interested in any approaches or ideas for how to keep agent harness and code separate, like ideally separate repos.<p>Spec driven development is going really well for me, along with a swarm of agents and skills etc.<p>However, I’m seeing .Claude/memory/<i>, docs/</i>, .specify/*, hooks and extensions, context management tools etc becoming as much an overhead to manage as the codebase itself sometimes.<p>Also, it’s all mixed in together, in the same repo. Surely this is an anti-pattern.<p>Are there better ways to do this (yet)? Or is this the next AI frontier to evolve?