Dreams SDK Integration
Use the Dreams Router with Vercel AI SDK and Daydreams framework
Dreams SDK Integration
Integrate the Dreams Router with Vercel AI SDK and the Daydreams framework for TypeScript/JavaScript applications.
Installation
Install the router SDK alongside the AI SDK:
npm install @daydreamsai/ai-sdk-provider aiUsing with Vercel AI SDK
Quick Start
Set your API key:
DREAMSROUTER_API_KEY=your_api_key_hereGenerate text:
import { generateText } from "ai";
import { dreamsRouter } from "@daydreamsai/ai-sdk-provider";
const { text } = await generateText({
model: dreamsRouter("google-vertex/gemini-2.5-flash"),
prompt: "What is love?",
});Using with Daydreams Framework
Basic Agent Setup
import { dreamsRouter } from "@daydreamsai/ai-sdk-provider";
import { createDreams } from "@daydreamsai/core";
const agent = createDreams({
model: dreamsRouter("google-vertex/gemini-2.5-flash"),
systemPrompt: "You are a helpful AI assistant",
});With x402 Payments
The SDK automatically handles X-Payment header generation for x402-compliant payments:
import { createDreamsRouterAuth } from "@daydreamsai/ai-sdk-provider";
import { privateKeyToAccount } from "viem/accounts";
const { dreamsRouter, user } = await createDreamsRouterAuth(
privateKeyToAccount(process.env.PRIVATE_KEY as `0x${string}`),
{
payments: {
amount: "100000", // $0.10 USDC
network: "base-sepolia",
},
}
);
// The dreamsRouter automatically adds X-Payment header to requests
const agent = createDreams({
model: dreamsRouter("google-vertex/gemini-2.5-flash"),
systemPrompt: "You are a helpful AI assistant",
});Manual X-Payment Header
For direct API calls without the SDK:
import { generateX402Payment } from "@daydreamsai/ai-sdk-provider";
import { privateKeyToAccount } from "viem/accounts";
const account = privateKeyToAccount("0x...your-private-key");
// Generate the payment header
const paymentHeader = await generateX402Payment(account, {
amount: "100000",
network: "base-sepolia",
});
// Include in your request
fetch("https://router.daydreams.systems/v1/chat/completions", {
headers: {
"X-Payment": paymentHeader, // Required for x402 payments
"Content-Type": "application/json",
},
// ... rest of request
});See the Daydreams core documentation for complete agent configuration options.
Streaming
import { streamText } from "ai";
import { dreamsRouter } from "@daydreamsai/ai-sdk-provider";
const { textStream } = await streamText({
model: dreamsRouter("anthropic/claude-3-5-sonnet-20241022"),
prompt: "Write a short story",
});
for await (const chunk of textStream) {
process.stdout.write(chunk);
}Tool Calling
import { generateText } from "ai";
import { dreamsRouter } from "@daydreamsai/ai-sdk-provider";
import { z } from "zod";
const { text, toolCalls } = await generateText({
model: dreamsRouter("openai/gpt-4-turbo"),
prompt: "What's the weather?",
tools: {
getWeather: {
description: "Get weather information",
parameters: z.object({
location: z.string(),
}),
execute: async ({ location }) => {
return `72°F and sunny in ${location}`;
},
},
},
});Structured Output
import { generateObject } from "ai";
import { dreamsRouter } from "@daydreamsai/ai-sdk-provider";
import { z } from "zod";
const { object } = await generateObject({
model: dreamsRouter("google-vertex/gemini-2.5-flash"),
schema: z.object({
name: z.string(),
ingredients: z.array(z.string()),
}),
prompt: "Generate a pasta recipe",
});Complete Example: Paid AI Service
import { createDreamsRouterAuth } from "@daydreamsai/ai-sdk-provider";
import { createDreams, context } from "@daydreamsai/core";
import { privateKeyToAccount } from "viem/accounts";
// Define context for conversation
const assistantContext = context({
type: "assistant",
create: () => ({ conversationHistory: [] }),
});
// Setup payment-enabled router
const { dreamsRouter } = await createDreamsRouterAuth(
privateKeyToAccount(process.env.PRIVATE_KEY as `0x${string}`),
{
payments: {
amount: "100000", // $0.10 per request
network: "base-sepolia",
},
}
);
// Create agent
const agent = createDreams({
model: dreamsRouter("google-vertex/gemini-2.5-flash"),
contexts: [assistantContext],
});
// Handle requests
app.post("/chat", async (req, res) => {
const result = await agent.send({
input: { type: "text", data: req.body.message },
});
res.json(result);
});