phoenix-observability

SKILL.md

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.

A trace represents a complete execution flow, while spans are individual operations within that trace.

| PHOENIXPORT | HTTP server port | 6006 | | PHOENIXHOST | Server bind address | 127.0.0.1 | | PHOENIXGRPCPORT | gRPC/OTLP port | 4317 | | PHOENIXSQLDATABASEURL | Database connection | SQLite temp | | PHOENIXWORKINGDIR | Data storage directory | OS temp | | PHOENIXENABLEAUTH | Enable authentication | false |

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights. Source: orchestra-research/ai-research-skills.

View raw