Aurora

Aurora is an open-source AI-powered incident management and root cause analysis tool designed for site reliability engineers. It uses large language model agents to autonomously investigate cloud incidents and identify their causes across multiple cloud platforms including AWS, Azure, GCP, Kubernetes, and others. The tool integrates with popular monitoring and alerting systems like PagerDuty, Datadog, Grafana, and Slack, allowing incidents to trigger investigations automatically. Aurora can execute infrastructure commands in sandboxed environments, search knowledge bases for similar past incidents, and analyze infrastructure dependencies to understand the scope of problems.

Developed by Arvo-AI, Aurora is released under the Apache 2.0 license and is free to self-host with no per-seat or per-incident pricing. The tool is built with Python and Next.js, using LangGraph to orchestrate workflows across numerous integration points. It can be deployed via Docker Compose or Kubernetes Helm charts, and supports flexible large language model providers including OpenAI, Anthropic, Google, or local models via Ollama for offline deployments.