Overview
Claude Agent SDK is a framework for calling Claude Code from your own code. It abstracts away the underlying process management and calls to the model API.What Laminar captures
- The entire structure of the Claude Agent SDK function calls, including
connect,query, andreceive_messages. - LLM prompts and responses sent to the model.
- Tool calls and their results.
- Latencies, token counts, and token costs.
Getting started
- TypeScript / JavaScript
- Python
View the traces in Laminar
Go to the Laminar dashboard, and you will see the traces for the Claude Agent SDK. Example trace:
Multi-agent visualization
When multiple Claude agents collaborate in a single run, Laminar renders each agent as a distinct branch in the trace so you can follow handoffs and parallel work. Example multi-agent trace:
