Features
eBPF-based auto-instrumentation for logs, metrics, traces, profiling, K8s events, deployment context
Autonomous AI issue detection and root cause analysis (RCA)
AI-powered alert investigation with full RCA and evidence
Deployment verification: pre- vs post-deployment telemetry comparison
Unified query language across all signals (MetoroQL)
Custom dashboards with widgets and variables
Continuous CPU/memory profiling per process with flame graphs
Kubernetes resource viewer and event history
Cost monitoring for workload allocation and waste
Uptime monitoring with HTTP/TCP health checks and status pages
Cron job monitoring for missed or failed runs
PromQL dashboard queries (alpha)
Integration with OpenTelemetry and Prometheus for external data
Git SHA to workload mapping for deployment context
Automated remediation workflows and fix PRs
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