Arvo-AI/aurora

Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Grafana, Slack and More. Apache 2.0.

What it solves

Aurora automates the tedious manual investigation process that on-call engineers face during system incidents. Instead of spending an hour manually checking dashboards, running CLI commands, and searching logs after an alert fires, Aurora autonomously triages the issue and delivers a structured root cause analysis (RCA) before the engineer even begins.

How it works

Aurora uses AI agents powered by LangGraph that can dynamically select from over 30 tools to investigate a tech stack. These agents run commands (like kubectl, aws, az, and gcloud) within sandboxed Kubernetes pods to ensure security. The system integrates with common alerting tools (PagerDuty, Datadog, etc.) to trigger investigations automatically and uses a knowledge graph to trace the blast radius across services. It can also suggest code fixes and generate pull requests for remediation.

Who it’s for

SREs, DevOps engineers, and on-call developers who manage complex multi-cloud or on-premise infrastructure and want to reduce the time spent on incident triage and postmortem documentation.

Highlights

  • Agentic Investigation: Autonomous agents that run infrastructure commands in secure sandboxes.
  • Auto-Generated Postmortems: Creates detailed reports with timelines and impact assessments, exportable to Notion or Confluence.
  • AI Code Fixes: Goes beyond diagnosis to suggest remediation and generate PRs.
  • Infrastructure Knowledge Graph: Visualizes dependencies to understand how a failure affects the entire system.
  • Broad Integration Support: Connects with major cloud providers (AWS, Azure, GCP), monitoring tools, and various LLMs (OpenAI, Anthropic, Ollama for air-gapped use).

Related

  • Project
    Kritt-ai/open-kritt

    An open-source security research platform that orchestrates AI agents to find, validate, and rank vulnerabilities in codebases using focused, parallelized workflows.

  • Project
    Tracer-Cloud/opensre

    An open-source framework for AI SRE agents that automates production incident investigation and root-cause analysis across cloud infrastructure.

  • Project
    ongridio/ongrid

    An AI operations agent that automates root-cause analysis and infrastructure troubleshooting via Slack or Telegram, integrating with observability stacks and system topology.

  • Project
    openocta/openocta

    A desktop-based AIOps agent for Windows and macOS that automates IT operations, alert analysis, and system inspections across full-stack infrastructure using natural language.

  • Dispatch
    Inside OpenAI's In-House Data Agent

    OpenAI has developed a bespoke internal AI data agent that enables employees to perform complex data analysis across 600 petabytes of data using natural language, utilizing a multi-layered context system and a self-learning reasoning loop.