精选理由
想给长时间运行的有状态智能体做评测？用harbor吧，已经是行业标准，LangChain全家桶都深度集成了，省心。
harbor是一个用于评估长时间运行、有状态智能体的框架。它正在成为行业标准，支撑着terminal bench 2等基准测试。LangChain已将harbor深度集成到LangSmith、Sandboxes和Deep Agents中。这有助于开发者更高效地评测智能体性能。
原文 · Harrison Chase
harbor is a great framework for running evals for long running, stateful agents its becoming indust...
harbor is a great framework for running evals for long running, stateful agents its becoming industry standard, powering benchmarks like terminal bench 2 we've integrated deeply with harbor: across LangSmith, Sandboxes, and Deep Agents LangChain @LangChain x.com/i/article/2069… 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 1 👀 413 📊 1 ⚡