Karakuri Agent Core Example

This example demonstrates how to use the karakuri-agent-core library to create and deploy AI agents.

Setup

1. Install dependencies:

npm install

2. Configure environment variables:

cp .env.example .env
# Edit .env with your configuration

3. Run the example:

npm start
# or for development with hot reload
npm run dev

Available Scripts

• npm start - Start the server
• npm run dev - Start with hot reload
• npm run build - Build TypeScript files

Configuration

Edit .env file to configure:

• PORT - Server port (default: 8080)
• KANON_LLM_BASE_URL - LLM API base URL
• KANON_LLM_API_KEY - Your API key
• KANON_LLM_MODEL - Model to use (e.g., gpt-4)
• KANON_USER_NAME - User name for Kanon agent
• KANON_USER_INFO - User information for context

API Endpoints

Once running, the following endpoints are available:

• GET /v1/models - List available agents
• POST /v1/chat/completions - Chat with an agent (OpenAI-compatible)
• GET /health - Health check

Using the API

# List available models
curl http://localhost:8080/v1/models

# Chat with Kanon agent
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kanon-agent",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'