Aurora AI Agent

<div align="center"> <img src=".github/assets/aurora-banner.gif" alt="Aurora — The open-source AI agent that investigates your incidents for you" width="100%" />

<a href="https://github.com/Arvo-AI/aurora/stargazers"><img src="https://img.shields.io/github/stars/Arvo-AI/aurora?style=for-the-badge&logo=github&color=181717" alt="Stars" /></a>  <a href="https://github.com/Arvo-AI/aurora/releases/latest"><img src="https://img.shields.io/github/v/release/Arvo-AI/aurora?style=for-the-badge&label=version&color=2ea44f" alt="Version" /></a>  <a href="https://github.com/Arvo-AI/aurora/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache_2.0-blue?style=for-the-badge" alt="License" /></a>  <a href="https://discord.com/invite/ccbN4FwHxM"><img src="https://img.shields.io/badge/Discord-Join_us-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord" /></a>  <a href="https://cal.com/arvo-ai"><img src="https://img.shields.io/badge/Book_a_Demo-FF6B4A?style=for-the-badge&logo=googlecalendar&logoColor=white" alt="Book a Demo" /></a>  <a href="https://aurora-ai.net"><img src="https://img.shields.io/badge/Try_it_Live-aurora--ai.net-8B5CF6?style=for-the-badge&logo=rocket&logoColor=white" alt="Try Aurora Live" /></a>

<br />

<a href="https://aurora-ai.net">Try Aurora Live</a>  •  <a href="#quick-start">Quick Start</a>  •  <a href="https://arvo-ai.github.io/aurora/">Documentation</a>  •  <a href="#integrations">Integrations</a>  •  <a href="https://www.aurorasre.ai">Website</a>  •  <a href="CHANGELOG.md">Changelog</a>

</div>

---

What's New

• Artifacts — Persistent agent-maintained documents in Monitor, continuously updated as investigations progress
• Actions — Automated post-RCA workflows (generate postmortems, open fix PRs, notify Slack) triggered on investigation completion
• AWS Bedrock Support — Use Claude, Titan, and other Bedrock models via IAM auth
• Fly.io Connector — Investigate incidents on Fly.io infrastructure
• CloudBees Enterprise — Operations Center + Feature Management connector
• Kubeconfig Upload — Connect on-prem Kubernetes clusters without a cloud provider
• CloudWatch Alarm Webhooks — Ingest AWS CloudWatch alarms directly as incidents
• Extensibility Hooks — Gate LLM calls, enforce seat limits, and customize behavior with lifecycle hooks

See the full CHANGELOG for all releases.

---

Why Aurora?

When an alert fires at 3 AM, your on-call engineer spends 30-60 minutes doing the same thing every time: checking dashboards, running kubectl commands, reading logs, correlating deployments, and searching Slack history.

Aurora does all of that autonomously. It receives the alert, spins up AI agents that investigate across your entire stack, and delivers a structured RCA by the time you open your laptop.

Without Aurora	With Aurora
Engineer paged, context-switches	Alert auto-triaged in background
30-60 min manual investigation	AI agents investigate in parallel
Knowledge siloed in individuals	Investigation reasoning captured
Postmortem written days later	Postmortem auto-generated
Same failure, different engineer	Knowledge base grows over time

<div align="center"> <a href="https://www.loom.com/share/8082df350ea64a928f7fadbf811c5138"> <img src=".github/assets/aurora-demo.gif" alt="Aurora Demo — AI agent investigating a cloud incident" width="100%" /> </a>

_{Click to watch the full demo}

</div>

How well does it work?

We test it in the open. Aurora Lab breaks a Kubernetes cluster in 19 known ways, sends Aurora only the alert, and grades the investigation against the injected root cause. Every run is published, including the ones Aurora gets wrong.

• Benchmark: Aurora and HolmesGPT on the same 19 faults, with the losses. K8sGPT takes no alert and scans the namespace, so its runs are reported separately, not scored against the other two
• Runbooks: one per lab fault (OOMKilled, ImagePullBackOff, Service with no endpoints, and more), built from the real runs

---

Features

<table> <tr> <td width="50%" valign="top">

Agentic Investigation

AI agents dynamically select from 30+ tools. They run kubectl, aws, az, and gcloud in sandboxed Kubernetes pods, query logs, check deployments, and correlate data — all autonomously.

</td> <td width="50%"> <img src=".github/assets/ai-investigation.png" alt="AI agent investigating" width="100%" /> </td> </tr> <tr> <td width="50%" valign="top">

AI Code Fixes

Aurora doesn't just find root cause — it suggests fixes and can generate pull requests with the remediation.

</td> <td width="50%"> <img src=".github/assets/pr-suggestion.png" alt="PR suggestion" width="100%" /> </td> </tr> <tr> <td width="50%" valign="top">

Incident Dashboard

Ingest alerts from PagerDuty, Datadog, Grafana, New Relic, OpsGenie, incident.io and more. Every alert auto-triggers a background investigation.

</td> <td width="50%"> <img src=".github/assets/incidents-dashboard.png" alt="Incidents dashboard" width="100%" /> </td> </tr> <tr> <td width="50%" valign="top">

Auto-Generated Postmortems

Detailed reports with timeline, root cause, impact assessment, and remediation steps. Export directly to Confluence, Notion, or SharePoint.

</td> <td width="50%"> <img src=".github/assets/postmortem-report.png" alt="Postmortem report" width="100%" /> </td> </tr> <tr> <td width="50%" valign="top">

Infrastructure Knowledge Graph

Visualize your entire infrastructure as a dependency graph. When an incident occurs, Aurora traces blast radius across services and providers.

</td> <td width="50%"> <img src=".github/assets/infrastructure-graph.png" alt="Infrastructure graph" width="100%" /> </td> </tr> </table>

More capabilities: Knowledge Base RAG • Multi-Cloud (AWS, Azure, GCP, OVH, Scaleway, Cloudflare) • Any LLM (OpenAI, Anthropic, Gemini, Vertex AI, OpenRouter, Ollama) • Terraform/IaC Analysis • MCP Server (Cursor, Claude Desktop, Windsurf) • Org-level Command Policies • SigmaHQ Guardrails • NeMo Input Rail

---

Quick Start

Get Aurora running locally in under 5 minutes:

git clone https://github.com/arvo-ai/aurora.git && cd aurora

make init                # Generate secure secrets
nano .env                # Add your LLM API key (OpenRouter, OpenAI, etc.)
make prod-prebuilt       # Pull prebuilt images and start

Open http://localhost:3000. The first user to register becomes admin.

[!TIP] Aurora works without any cloud provider accounts. The LLM API key is the only external requirement. Connectors are optional.

<details> <summary><strong>Vault setup (required after first start)</strong></summary> <br />

# Get the auto-generated root token
docker logs vault-init 2>&1 | grep "Root Token:"

# Add it to .env
echo "VAULT_TOKEN=hvs.your-token-here" >> .env

# Restart to connect services to Vault
make down && make prod-prebuilt

</details> <details> <summary><strong>Pin a specific version</strong></summary> <br />

make prod-prebuilt VERSION=v1.2.3

</details> <details> <summary><strong>Build from source</strong></summary> <br />

make prod-local

</details>

---

Deploy

Method	Best for
make prod-prebuilt	Local evaluation, single-node
Helm chart	Production Kubernetes (GKE, EKS, AKS)
Air-tight bundle	Air-gapped / restricted networks

Kubernetes (Helm)

helm repo add aurora https://raw.githubusercontent.com/Arvo-AI/aurora/gh-pages
helm repo update
helm show values aurora/aurora-oss > my-values.yaml
# Edit my-values.yaml, then:
helm install aurora-oss aurora/aurora-oss -n aurora --create-namespace -f my-values.yaml

Also available via OCI: oci://ghcr.io/arvo-ai/charts/aurora-oss

---

Integrations

<div align="center">

LLMs: OpenAI • Anthropic • Google Gemini • Vertex AI • AWS Bedrock • OpenRouter • Ollama (air-gapped)

</div>

---

Architecture

aurora/
├── server/      # Python API (Flask), Celery workers, LangGraph agents
├── client/      # Next.js frontend
├── deploy/      # Helm chart, Docker Compose, deployment scripts
├── config/      # Default configuration
├── scripts/     # CLI utilities
└── website/     # Documentation (Docusaurus)

Layer	Stack
AI Orchestration	LangGraph, 30+ tool definitions
Backend	Python, Flask, Celery
Frontend	Next.js, TypeScript
Graph DB	Memgraph
Secrets	HashiCorp Vault, AWS Secrets Manager
Storage	PostgreSQL, Redis, S3-compatible

---

Security

• Sandboxed execution — Agent commands run in isolated Kubernetes pods with NetworkPolicy, not on your control plane
• RBAC — Three roles (Admin, Editor, Viewer) enforced at API and UI layers via Casbin
• Closed registration — First user is admin; all others are invited
• SigmaHQ guardrails — 37 threat detection signatures on agent command execution
• NeMo input rail — Prompt injection detection on every turn
• No telemetry — Zero data sent to Arvo AI. Fully self-hosted.

---

Data Privacy

Aurora is 100% self-hosted. Your incident data never leaves your infrastructure.

• All data on your infrastructure (Docker or Kubernetes)
• No telemetry or tracking to Arvo AI
• Secrets encrypted at rest in Vault or AWS Secrets Manager
• LLM calls go directly from your infra to your chosen provider
• Use Ollama for fully air-gapped operation

---

Community

<div align="center">

<a href="https://discord.com/invite/ccbN4FwHxM"><img src="https://img.shields.io/badge/Discord-Join_the_community-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord" /></a>   <a href="https://cal.com/arvo-ai"><img src="https://img.shields.io/badge/Book_a_Demo-FF6B4A?style=for-the-badge&logo=googlecalendar&logoColor=white" alt="Book a Demo" /></a>

</div> <br />

• GitHub Issues — Bug reports and feature requests
• GitHub Discussions — Ideas and Q&A
• Documentation — Full deployment and configuration guides
• Blog — SRE best practices, incident management guides
• Aurora Lab — Reproducible Kubernetes failure scenarios and every graded Aurora run
• lastwords: Open-source Kubernetes DaemonSet that snapshots a container's memory before an OOM kill and saves the logs and core dumps of crashes. Works on its own, without Aurora.
• Contributing — We welcome PRs! Read the guide first.

---

License

Apache License 2.0 — free forever, no per-seat or per-incident pricing.

---

<div align="center"> <br /> <strong>If Aurora helps your team, <a href="https://github.com/Arvo-AI/aurora">star us on GitHub</a></strong> <br /><br /> <a href="https://github.com/Arvo-AI/aurora/stargazers"><img src="https://img.shields.io/github/stars/Arvo-AI/aurora?style=for-the-badge&logo=github&color=181717" alt="Stars" /></a> <br /><br /> </div>