joshuaKnauber/breadcrumb

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications w

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows wit

Trace-native CI/CD for AI agents: grade production traces, cluster failures, freeze them i

Open-source observability for your GenAI or LLM application, based on OpenTelemetry