KGent is a smart Kubernetes CLI assistant powered by AI that helps you create, list, and delete Kubernetes resources using natural language. It acts as a bridge between your natural language input and the Kubernetes API.

• Natural Language Interface: Interact with your Kubernetes cluster using everyday language
• Resource Creation: Generate YAML files for Kubernetes resources based on your description
• Resource Management: List and delete resources through conversation
• AI-Powered: Uses large language models to understand requests and generate responses

• Go 1.21.3 or later
• Access to a Kubernetes cluster
• DashScope API token (or other compatible API token)

1. Clone the repository:

   git clone https://github.com/your-username/kgent.git
   cd kgent

2. Build the project:

   go build -o kgent

3. Set up your environment:

   Option 1: Using .env file (recommended)

   Copy the example environment file and edit it with your credentials:

   cp .env.example .env
   # Edit .env with your API keys and configuration

   Option 2: Using environment variables directly

   export DASH_SCOPE_API_KEY=your_api_token_here # required
   export DASH_SCOPE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
   export DASH_SCOPE_MODEL=qwen-turbo

Start a conversation with the Kubernetes assistant:

./kgent chat

You can specify a default namespace for all operations:

./kgent chat --namespace default

• Creating a pod:

  > Create a pod named nginx-pod with nginx image
  

• Listing resources:

  > List all pods in the default namespace
  

• Deleting a resource:

  > Delete the pod named nginx-pod
  

You can configure KGent through either environment variables or a .env file:

This project is licensed under the MIT License - see the LICENSE file for details.