AI Infrastructure Agent is an intelligent system for managing AWS infrastructure through natural language commands. Powered by advanced AI models (OpenAI GPT, Google Gemini, Anthropic Claude, or AWS Bedrock Nova), it translates infrastructure requests into executable AWS operations while providing safety features like conflict detection and resolution.
git clone https://github.com/VersusControl/ai-infrastructure-agent.git
cd ai-infrastructure-agent
Edit the main configuration file:
# Edit the main configuration
nano config.yaml
Choose your preferred AI provider in the configuration:
agent:
provider: "openai" # Options: openai, gemini, anthropic, bedrock
model: "gpt-4" # Model to use
max_tokens: 4000
temperature: 0.1
dry_run: true # Start with dry-run enabled
auto_resolve_conflicts: false
Depending on your chosen AI provider, you'll need to set specific API keys:
# For OpenAI
export OPENAI_API_KEY="your-openai-api-key"
# For Google Gemini
export GEMINI_API_KEY="your-gemini-api-key"
# For AWS Bedrock Nova - use AWS credentials (no API key needed)
# Configure AWS credentials using: aws configure, environment variables, or IAM roles
# Configure AWS CLI
aws configure
# Or set environment variables
export AWS_ACCESS_KEY_ID="your-access-key"
export AWS_SECRET_ACCESS_KEY="your-secret-key"
export AWS_DEFAULT_REGION="us-west-2"
Basic Docker Run:
docker run -d \
--name ai-infrastructure-agent \
-p 8080:8080 \
-v $(pwd)/config.yaml:/app/config.yaml:ro \
-v $(pwd)/states:/app/states \
-e OPENAI_API_KEY="your-openai-api-key-here" \
-e AWS_ACCESS_KEY_ID="your-aws-access-key" \
-e AWS_SECRET_ACCESS_KEY="your-aws-secret-key" \
-e AWS_DEFAULT_REGION="us-west-2" \
ghcr.io/versuscontrol/ai-infrastructure-agent
Using Docker Compose (Recommended):
Create a docker-compose.yml file:
version: '3.8'
services:
ai-infrastructure-agent:
image: ghcr.io/versuscontrol/ai-infrastructure-agent
container_name: ai-infrastructure-agent
restart: unless-stopped
ports:
- "8080:8080"
volumes:
# Mount configuration file (read-only)
- ./config.yaml:/app/config.yaml:ro
# Mount data directories (persistent)
- ./states:/app/states
environment:
# AI Provider API Keys (choose one)
- OPENAI_API_KEY=${OPENAI_API_KEY}
# - GEMINI_API_KEY=${GEMINI_API_KEY}
# - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
# AWS Configuration
- AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
- AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
- AWS_DEFAULT_REGION=${AWS_DEFAULT_REGION:-us-west-2}
Start the application:
# Start with Docker Compose
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the application
docker-compose down
# Clone the repository
git clone https://github.com/VersusControl/ai-infrastructure-agent.git
cd ai-infrastructure-agent
# Run the installation script
./scripts/install.sh
# Start the Web UI
./scripts/run-web-ui.sh
Open your browser and navigate to:
http://localhost:8080
The agent can handle various infrastructure requests through natural language. Here are some examples:
"Create a t3.micro EC2 instance with Ubuntu 22.04"
"Deploy a load-balanced web application with 2 EC2 instances behind an ALB"
"Create an RDS MySQL database with read replicas in multiple AZs"
"Set up a development environment with VPC, subnets, EC2, and RDS"
When you submit a request like:
"Create an EC2 instance for hosting an Apache Server with a dedicated security group that allows inbound HTTP (port 80) and SSH (port 22) traffic."
The agent will:
# Check AWS credentials
aws sts get-caller-identity
# Verify permissions
aws iam get-user
# Test basic AWS access
aws ec2 describe-regions
# Check API key is set
echo $OPENAI_API_KEY
# Test API connection
curl -H "Authorization: Bearer $OPENAI_API_KEY" \
https://api.openai.com/v1/models
# Check what's using the port
lsof -i :8080
lsof -i :3000
# Kill processes if needed
kill -9 <pid>
# Or change ports in config.yaml
If you encounter "Decision validation failed: decision confidence too low" errors, try increasing max_tokens in your config:
agent:
provider: "gemini"
model: "gemini-2.5-flash-lite"
max_tokens: 10000 # Increase this value
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "ai-infrastructure-agent" '{"command":"npx","args":["-y","ai-infrastructure-agent"]}'See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:
{
"mcpServers": {
"ai-infrastructure-agent": {
"command": "npx",
"args": [
"-y",
"ai-infrastructure-agent"
]
}
}
}To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json2. Add this to your configuration file:
{
"mcpServers": {
"ai-infrastructure-agent": {
"command": "npx",
"args": [
"-y",
"ai-infrastructure-agent"
]
}
}
}3. Restart Claude Desktop for the changes to take effect