agent-builder-vercel-sdk

Files (2)

• SKILL.md
• metadata.json

SKILL.md (first lines)

# Vercel AI SDK Agent Builder

## Purpose
Create streaming AI chat interfaces with minimal code using Vercel AI SDK and OpenRouter provider.

## When to Use
- Building Next.js frontend with chat UI
- Need streaming responses with SSE
- Want type-safe tool calling in TypeScript
- Switching between multiple AI providers
- Building agentic loops with stopWhen/prepareStep

## Quick Start

### Installation
```bash
npm install ai @openrouter/ai-sdk-provider zod
```

### Environment Variables
```env
OPENROUTER_API_KEY=sk-or-v1-...
NEXT_PUBLIC_SITE_URL=http://localhost:3000
```

## Backend Setup (Route Handler)

### Basic Chat Endpoint
```typescript
// app/api/chat/route.ts
import { OpenRouter } from '@openrouter/ai-sdk-provider'
import { streamText } from 'ai'

const openrouter = new OpenRouter({
  apiKey: process.env.OPENROUTER_API_KEY
})

export async function POST(req: Request) {
  const { messages } = await req.json()

  const result = streamText({
    model: openrouter('openai/gpt-4o'),
    system: 'You are a helpful assistant',
    messages,
  })

  return result.toDataStreamResponse()
}
```

### With Tool Calling
```typescript
import { z } from 'zod'
import { tool } from 'ai'

const tools = {
  generateImage: tool({
    description: 'Generate images using AI',
    parameters: z.object({
      prompt: z.string().describe('Image description'),
      numImages: z.number().min(1).max(10).default(1)
    }),
    execute: async ({ prompt, numImages }) => {
      // Your implementation
      const images = await generateImages(prompt, numImages)
      return { images }
    }
  })
}

export async function POST(req: Request) {
  const { messages } = await req.json()

  const result = streamText({
    model: openrouter('openai/gpt-4o'),
    system: 'You are a helpful assistant',
    messages,
    tools,
    maxSteps: 5 // Enable agentic loop
  })

  return result.toDataStreamResponse()
}
```

## Frontend Integration

### Using useChat Hook
```typescript
'use client'

import { useChat } from 'ai/react'

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit, isLoading } = useChat()

  return (
    <div className="flex flex-col h-screen">
      {/* Messages */}
      <div className="flex-1 overflow-y-auto p-4">
        {messages.map(m => (
          <div key={m.id} className={m.role === 'user' ? 'text-right' : 'text-left'}>
            <div className="inline-block p-3 rounded-lg">
              {m.content}
            </div>
          </div>
        ))}
      </div>

      {/* Input */}
      <form onSubmit={handleSubmit} className="p-4 border-t">
        <input
          value={input}
          onChange={handleInputChange}
          placeholder="Type a message..."
          disabled={isLoading}
          className="w-full px-4 py-2 border rounded"
        />
      </form>

From diegosouzapw/awesome-omni-skill, MIT.

More from diegosouzapw/awesome-omni-skill