Features
Experiment tracking with parameters and gradients
Multimedia logging (images, media)
Real-time alerts via email and critical issues
Model performance monitoring over time
Reproducibility with Git status and uncommitted file tracking
100% compatible with Weights & Biases API
Open source (community-driven)
Self-hosted deployment (Enterprise tier)
Compute Instances (private beta, upcoming)
Inference (private beta, upcoming)
Real-time parameter and gradient visualization
Trace visibility for agent steps (prompts, retrievals, tool calls, outputs)
LLM-as-judge evaluation for relevance, toxicity, quality scoring
Dataset creation from traces for reproducible testing
Experiment management and regression benchmarking
Built-in Prompt IDE for iterative prompt optimization
Self-hosted deployment on local, Docker, Kubernetes
Phoenix Cloud managed hosting option
Vendor-agnostic support for any model/framework
Native OpenTelemetry integration
OpenInference specification for LLM telemetry
Human annotation and automated labeling
Ghost trajectories to simulate alternative agent paths
Eval-as-you-test for early quality feedback
One-click integration with LlamaIndex
