Features
Auto-builds a cross-tool knowledge graph of your stack
Root-cause analysis in under 9 minutes from alert firing
Proactive suggestions to tighten retry budgets, auto-scale, etc.
Automated runbooks and remediation workflows
Smart model switching to optimize credit usage
Blast radius tracing from a single alert across connected entities
Continuous learning from every investigation, deploy, and alert
Integrates with cloud providers (AWS, GCP, Azure)
Integrates with code repos (GitHub, GitLab) and CI/CD pipelines
Ingests runbooks, wikis, ADRs, and on-call docs as knowledge sources
Alert correlation and noise reduction via the knowledge graph
Unlimited users per organization on all paid plans
Custom MCP servers for specialized integrations
Email and Slack notification for credit usage (80% threshold)
14-day free trial with full Teams capabilities
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
