Back to Home
sakthisundar-16 icon

ai-infrastructure-agent

by sakthisundar-16

Overview

An intelligent system for managing AWS infrastructure using natural language commands, featuring multi-AI provider support and a web dashboard.

Installation

Run Command
docker run -d --name ai-infrastructure-agent -p 8080:8080 -v $(pwd)/config.yaml:/app/config.yaml:ro -v $(pwd)/states:/app/states -e OPENAI_API_KEY="your-openai-api-key-here" -e AWS_ACCESS_KEY_ID="your-aws-access-key" -e AWS_SECRET_ACCESS_KEY="your-aws-secret-key" -e AWS_DEFAULT_REGION="us-west-2" ghcr.io/versuscontrol/ai-infrastructure-agent

Environment Variables

  • OPENAI_API_KEY
  • GEMINI_API_KEY
  • ANTHROPIC_API_KEY
  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY
  • AWS_DEFAULT_REGION
  • PORT

Security Notes

The default WebSocket (`/ws`) connection explicitly allows all origins (`CheckOrigin: func(r *http.Request) bool { return true }`) and the `/api` routes use `Access-Control-Allow-Origin: *`. This configuration poses a significant security risk if the server is exposed publicly without modifications, as it allows arbitrary websites to interact with the API and potentially trigger infrastructure changes. While noted as 'for development' in a comment, it is the default behavior. API keys (OpenAI, Gemini, Anthropic) are correctly recommended to be stored in environment variables, and AWS credentials are handled via `aws configure` or environment variables. However, the IAM permissions suggested in the documentation are broad (`ec2:*`, `vpc:*`, `iam:PassRole`, `elasticloadbalancing:*`, `autoscaling:*`), necessitating careful review and adherence to the principle of least privilege in production environments. No 'eval' or obvious obfuscation detected.

Similar Servers

Stats

Interest Score30
Security Score6
Cost ClassMedium
Avg Tokens4000
Stars1
Forks1
Last Update2025-12-13

Tags

AWSAI AgentInfrastructure as CodeNatural Language ProcessingDevOps