Shivnath Tathe 开发了 "opensmith"，这是一款本地优先的工具，旨在追踪和调试 LLM 管道，而无需将数据发送到云端。这款 LangSmith 等服务的替代品允许开发者直接在本地机器上监控函数调用、延迟、令牌使用量、成本和错误。该工具获得了显著关注，首日下载量超过 600 次，表明开发者在 LLM 应用开发中对注重隐私的离线可观测性解决方案有强烈需求。 AI
影响 满足了开发者在 LLM 应用中对注重隐私的本地可观测性的需求，有可能加速敏感用例的开发。
排序理由 该集群描述了一个用于 LLM 开发的新软件工具的发布。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
<p>Last month I spent $200 on OpenAI tokens debugging a RAG pipeline. I had no idea which step was eating my budget. LangSmith would have helped — but I didn't want to send my prompts to a cloud service just to debug locally.</p> <p>So I built opensmith.</p> <h2> What is opensmit…
<p>I didn't expect this.</p> <p>I published <strong>opensmith</strong> yesterday — a local-first LLM pipeline tracer <br /> built as an alternative to LangSmith.</p> <p>No cloud. No API key. No account. No data leaving your machine.</p> <p>Just <code>pip install opensmith</code> …