精选理由
Harbor专门做长期agent评测，LangChain有博客和视频教你怎么集成，适合做复杂agent测试的人。
Harbor是一个用于运行长期、有状态智能体（agent）评估的框架。LangChain通过博客和视频教程展示了与Harbor的多种集成方式。博客地址为langchain.com/blog/unified-s…，视频教程演示了如何使用Harbor和LangSmith评估deepagents。
原文 · Harrison Chase
3/ Harbor integration Harbor is a framework for running long running, stateful agent evals We inte...
3/ Harbor integration Harbor is a framework for running long running, stateful agent evals We integrate with it in multiple different ways. We wrote a blog on those integrations: langchain.com/blog/unified-s… We then made a video of how to use Harbor and LangSmith to evaluate deepagents: youtu.be/Rh6KWngr8T4 💬 2 🔄 0 ❤️ 0 👀 421 📊 2 ⚡