LangSmith

LLM observability and testing platform for debugging AI applications

About LangSmith

LangSmith is an observability and evaluation platform built by LangChain for tracing, testing, and monitoring LLM applications. It works with any LLM framework, not just LangChain, and supports distributed tracing, custom LLM-as-judge evaluations, and regression testing. Deployment options include managed cloud, bring-your-own-cloud, and self-hosted configurations.