We built traceAI, an open-source tool for tracing LLM calls in production

Hey everyone We have been building traceAI, an open-source observability tool for LLM apps in production. It captures every call, inputs, outputs, latency, costs, and errors with minimal setup. Works with any LLM backend. Repo: GitHub - future-agi/traceAI: Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks · GitHub Would love feedback from folks here. What does your current monitoring setup look like for production LLM apps?