AI-first, built in-house

// Chat completion — works with any provider
const response = await zm.ai.chat({
  model: 'gpt-4o',  // or claude-sonnet, gemini-pro, etc.
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Explain quantum computing simply.' }
  ],
  max_tokens: 500
})

// Streaming response
const stream = await zm.ai.chat({
  model: 'claude-sonnet-4-20250514',
  messages: [{ role: 'user', content: 'Write a poem.' }],
  stream: true
})

for await (const chunk of stream) {
  process.stdout.write(chunk.content)
}

// Prompt Arena — compare models side by side
const arena = await zm.ai.arena({
  prompt: 'Summarize this article...',
  models: ['gpt-4o', 'claude-sonnet', 'gemini-pro', 'deepseek-chat']
})

// Ask Zy — the context-aware assistant
const zy = await zm.ai.zy({
  message: 'How do I query users from my database?'
})
// Returns project-specific guidance with actual endpoints