Features
Predictive incident detection using ML
Alert deduplication and noise reduction
Intelligent alert grouping
Custom alert rules engine
On-call scheduling and escalation
Multi-channel notifications (Slack, PagerDuty, Teams, email)
Historical analytics and reports
Integration with monitoring tools (Prometheus, Datadog, Grafana)
API for programmatic access
Role-based access control
Distributed tracing for LLM agents
Capture prompts, retrievals, tool calls, outputs
Human annotations on traces
Create datasets from traces
Run experiments to compare changes
OpenTelemetry-native instrumentation
Self-host locally, Docker, or Kubernetes
Cloud instances with free tier
Vendor agnostic: any model or framework
3M+ monthly downloads, 9k+ GitHub stars
