Introducing Langshark a local-first companion observability tool for self-hosted Langgraph deployments

As part of my foray into working with Langchain/Langgraph, I struggled initially with understanding the feature rich runtime environment. And not having a good understanding of the runtime artifacts hampered the effectiveness of my debug sessions. It motivated me to create Langshark, a stand alone local-first TUI, for observing and learning the Langchain runtime.

It requires a langgraph dev server or a self-hosted Langgraph api server (i.e. Agent Server) be running locally. Having a convenient way to copy and paste contents of the runtime results and agent server log entries into a Claude chat helped keep my agent development moving forward.

Your welcome to give it try.

Very cool - will give this a try for sure.