Phoenix (Arize)
Open-source AI observability with embedding and RAG tracing
Verdict
Strongest tool for RAG evaluation — UMAP visualisation of embeddings, retrieval quality scoring, and hallucination detection. Run locally or in Arize Cloud.
Other Observability & Evals
- Arize AIStable
ML and LLM observability platform with drift detection and evaluation
- BraintrustExperimental
End-to-end LLM evaluation and experimentation platform
- HeliconeStable
LLM gateway with logging, caching, and cost analytics
- LangfuseProduction
Open-source LLM engineering platform — traces, evals, prompts
- OpenLLMetryExperimental
OpenTelemetry-based observability for LLMs
- PromptLayerStable
Prompt version control, A/B testing, and analytics platform