Aurora by Arvo AI — Open Source Agentic Incident Management
Aurora is an open-source (Apache 2.0) AI-powered agentic incident management and root cause analysis tool for Site Reliability Engineers. Built with Python and Next.js, Aurora uses LangGraph-orchestrated LLM agents to autonomously investigate cloud incidents across AWS, Azure, GCP, OVH, Scaleway, and Kubernetes.
Key Features
- Agentic AI investigation using LangGraph workflows with 30+ tools
- Multi-cloud support: AWS, Azure, GCP, OVH, Scaleway, and Kubernetes
- Webhook-triggered auto-investigation from PagerDuty, Datadog, Grafana, Netdata, Dynatrace, Coroot, ThousandEyes, and BigPanda
- Infrastructure CLI execution in sandboxed Kubernetes pods — runs kubectl, aws, az, and gcloud commands safely
- Infrastructure knowledge graph powered by Memgraph for dependency mapping and blast radius analysis
- Knowledge base with Weaviate vector search over runbooks, past postmortems, and documentation
- Automatic postmortem generation with Confluence export
- Terraform and Infrastructure-as-Code analysis
- LLM provider flexibility: OpenAI, Anthropic, Google, or local models via Ollama for air-gapped deployments
- Self-hosted via Docker Compose or Helm chart with HashiCorp Vault secrets management
Integrations
Aurora integrates with 22+ tools including PagerDuty, Datadog, Grafana, Slack, GitHub, Confluence, Netdata, Dynatrace, Coroot, ThousandEyes, BigPanda, and all major cloud providers.
How Aurora Works
When a monitoring tool fires an alert, Aurora's AI agents autonomously investigate the incident. The agents dynamically select from 30+ tools to query infrastructure, execute CLI commands in sandboxed pods, search the knowledge base for similar past incidents, traverse the infrastructure dependency graph, and synthesize findings into a structured root cause analysis with remediation recommendations.
Open Source
Aurora is fully open source under the Apache 2.0 license. It is free to self-host with no per-seat or per-incident pricing. The source code is available at github.com/Arvo-AI/aurora.
Getting Started
Clone the repository, run make init to configure, then make prod-prebuilt to start Aurora. Kubernetes deployment is available via Helm chart.








