Ecosystem overview for everything related to agent-evaluation.
PandaProbe is an open-source agent engineering platform by Chirpz AI, enabling teams to collaboratively trace, evaluate, monitor, and debug AI agents. It features asynchronous trace ingestion, automated LLM-as-a-judge evaluation, and a comprehensive dashboard for workflow analysis. Supporting both self-hosting and managed cloud versions, it provides professional observability and performance metrics for the entire AI agent development lifecycle.