Skip to main content
Aurora uses environment variables for configuration. Copy .env.example to .env and configure the variables below.

Quick Start

For local development:

Core Configuration

string
default:"dev"
Environment mode: dev, staging, or prod

Database

PostgreSQL database configuration (required).
string
default:"aurora"
required
PostgreSQL username
string
required
PostgreSQL password. Auto-generated by make init.
string
default:"aurora_db"
PostgreSQL database name
string
default:"postgres"
PostgreSQL host (Docker service name or hostname)
number
default:"5432"
PostgreSQL port

Redis

Redis is used for Celery task queue and caching.
string
default:"redis://redis:6379/0"
Redis connection URL

Object Storage

S3-compatible object storage configuration. See Storage Configuration for details.
string
default:"aurora-storage"
required
S3 bucket name
string
default:"http://seaweedfs-filer:8333"
S3 endpoint URL. Default uses SeaweedFS (included in docker-compose).For AWS S3, omit this variable. For other providers (Cloudflare R2, MinIO, etc.), set the endpoint URL.
string
default:"admin"
required
S3 access key ID
string
default:"admin"
required
S3 secret access key
string
default:"us-east-1"
S3 region
boolean
default:"false"
Enable SSL/TLS for storage connections
boolean
default:"false"
Verify SSL certificates. Set to true in production for security.
boolean
default:"true"
Enable Redis caching for storage file listings
number
default:"60"
Cache TTL in seconds

URLs & Networking

string
default:"http://localhost:3000"
Frontend URL (for internal use)
string
default:"http://aurora-server:5080"
Backend URL (for internal container-to-container communication)
string
default:"http://localhost:5080"
Backend URL accessible from the browser. Injected at container startup.
string
default:"ws://localhost:5006"
WebSocket URL for chatbot. Injected at container startup.
string
default:"http://chatbot:5007"
Internal chatbot service URL
NEXT_PUBLIC_* variables are injected at container startup, not baked at build time. To change them:
  1. Update .env
  2. Recreate the frontend container: docker compose -f docker-compose.prod-local.yml up -d frontend

Authentication & Security

string
required
Flask session secret key. Auto-generated by make init.
number
default:"5080"
Flask API port
string
required
Auth.js secret key. Auto-generated by make init.
string
required
HashiCorp Vault root token. Auto-generated by make init.See Vault Secrets for details.
string
default:"http://vault:8200"
Vault server address
string
default:"aurora"
Vault KV v2 engine mount point
string
default:"users"
Base path for user secrets in Vault

LLM & AI Services

At least one LLM provider API key is required. See LLM Providers for details.
string
OpenRouter API key (recommended). Get from https://openrouter.ai/keysSupports multiple models from various providers through a single API.
string
OpenAI API key. Get from https://platform.openai.com/api-keys
string
Anthropic API key. Get from https://console.anthropic.com/
string
Google AI (Gemini) API key. Get from https://aistudio.google.com/app/apikey
string
default:"openrouter"
Default LLM provider: openrouter, openai, anthropic, or google
number
default:"240"
Maximum recursion depth for agent workflows
string
default:"http://searxng:8080"
SearxNG internal URL
string
default:"http://localhost:8082"
SearxNG public URL
string
SearxNG secret key. Auto-generated by make init.

AI Features

boolean
default:"false"
Enable cost optimization for root cause analysis
boolean
default:"false"
Disable “thinking” mode for Gemini models

Cloud Provider Integrations

Optional cloud provider credentials for resource discovery and management.

Google Cloud Platform

string
GCP OAuth client ID
string
GCP OAuth client secret

Amazon Web Services

string
AWS access key ID
string
AWS secret access key
string
default:"us-east-1"
AWS default region

Cloud Provider Cache

Applies to all cloud providers (GCP, AWS, Azure).
boolean
default:"true"
Enable caching for cloud provider API responses
number
default:"3600"
Cache TTL in seconds (1 hour)
boolean
default:"false"
Verify CLI identity for cloud provider connections
boolean
default:"false"
Cache cloud provider tokens in Redis

Third-Party Integrations

Optional integrations with external services.

GitHub OAuth

string
GitHub OAuth client ID
string
GitHub OAuth client secret

Slack

boolean
default:"false"
Enable Slack integration
string
Slack OAuth client ID
string
Slack OAuth client secret
string
Slack signing secret

PagerDuty

boolean
default:"false"
Enable PagerDuty OAuth integration
string
PagerDuty OAuth client ID
string
PagerDuty OAuth client secret

Bitbucket

boolean
default:"false"
Enable Bitbucket integration
string
Bitbucket OAuth client ID
string
Bitbucket OAuth client secret

OVH (Multi-Region)

boolean
default:"false"
Enable OVH integration
string
OVH Europe client ID
string
OVH Europe client secret
string
OVH Canada client ID
string
OVH Canada client secret
string
OVH US client ID
string
OVH US client secret

Scaleway

boolean
default:"false"
Enable Scaleway integration

Confluence

boolean
default:"false"
Enable Confluence integration
string
Confluence OAuth client ID
string
Confluence OAuth client secret

Dynatrace

boolean
default:"false"
Enable Dynatrace integration

BigPanda

boolean
default:"false"
Enable BigPanda integration

ThousandEyes

boolean
default:"false"
Enable ThousandEyes integration

Email (SMTP)

string
SMTP server hostname
number
default:"587"
SMTP server port
string
SMTP username
string
SMTP password
string
Email sender address
string
default:"Aurora"
Email sender name

Kubernetes & Pod Isolation

Configuration for running Aurora agents in isolated Kubernetes pods.
boolean
default:"false"
Enable isolated pod execution for terminal and chatbot agents
string
Kubernetes namespace for terminal pods
string
Container image for terminal pods
number
Time-to-live for terminal pods (seconds)
string
Runtime class for terminal pods (e.g., gvisor, kata-containers)
number
Time-to-live for chatbot pods (seconds)
boolean
Schedule pods on untrusted nodes (with appropriate taints/tolerations)
string
Helm chart URL for kubectl agent deployment

Weaviate (Vector Database)

string
default:"weaviate"
Weaviate host (Docker service name or hostname)
number
default:"8080"
Weaviate HTTP port
number
default:"50051"
Weaviate gRPC port

Memgraph (Graph Database)

string
default:"memgraph"
Memgraph host (Docker service name or hostname)
number
default:"7687"
Memgraph Bolt protocol port
string
default:"aurora"
Memgraph username
string
default:"CHANGE_ME"
Memgraph password
number
default:"1"
Resource discovery interval (hours)

Rate Limiting

boolean
default:"false"
Enable API rate limiting
string
Token to bypass rate limits (for testing/admin)
boolean
default:"true"
Include rate limit headers in API responses

Development

string
ngrok tunnel URL for local development (webhooks, OAuth callbacks)

Configuration Examples

Minimal Local Development

Production with AWS S3

Production with Cloudflare R2