You can use Lightfast agents with any Node.js framework or HTTP server. The fetchRequestHandler provides a framework-agnostic interface that works with Web API Request/Response objects.

Supported Frameworks

Choose your preferred framework for detailed integration guides:

• Node.js HTTP Server - Native Node.js HTTP server with full control
• Express - Popular and flexible web framework with rich middleware ecosystem
• Hono - Ultrafast web framework with excellent Web API compatibility ⭐ Recommended
• Fastify - High-performance framework with schema validation
• NestJS - Progressive framework for building scalable applications

Quick Comparison

Common Setup

All frameworks use the same agent configuration:

import { createAgent } from 'lightfast/agent';
import { createTool } from 'lightfast/tool';
import { RedisMemory } from 'lightfast/memory/adapters/redis';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';

// Create a simple tool
const weatherTool = createTool({
  name: 'get_weather',
  description: 'Get weather for a location',
  parameters: z.object({
    location: z.string().describe('The location to get weather for')
  }),
  execute: async ({ location }) => {
    // Your weather API logic here
    return `Weather in ${location}: Sunny, 72°F`;
  }
});

// Create the agent
const agent = createAgent({
  name: 'weather-assistant',
  model: openai('gpt-4o'),
  system: 'You are a helpful weather assistant.',
  tools: { weather: weatherTool },
  createRuntimeContext: ({ sessionId, resourceId }) => ({
    // Add any runtime context here
    timestamp: Date.now()
  })
});

// Create memory adapter
const memory = new RedisMemory({
  url: process.env.REDIS_URL!,
  token: process.env.REDIS_TOKEN!
});

Getting Started

1. Choose your framework from the list above
2. Follow the specific integration guide for detailed setup instructions
3. Configure your agent and memory using the common setup above
4. Deploy and test your AI-powered API

Each framework guide includes:

• Installation instructions
• Basic and advanced integration examples
• Authentication and middleware setup
• Error handling and logging
• Testing strategies
• Production deployment tips

Why Lightfast Works Everywhere

Lightfast's Web API-first design makes it naturally compatible with any framework that supports standard Request/Response objects. This means:

• ✅ Future-proof - Works with new frameworks as they emerge
• ✅ Edge compatible - Runs on Cloudflare Workers, Vercel Edge, etc.
• ✅ Consistent API - Same integration pattern across all frameworks
• ✅ No vendor lock-in - Easy to migrate between frameworks

Testing Your Integration

You can test any framework integration using curl:

# Test the agent endpoint
curl -X POST http://localhost:8080/agents/my-session \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": "What'\''s the weather like in San Francisco?"
      }
    ]
  }'

Next Steps

• Choose your framework and follow the detailed integration guide
• Explore Agent Development for advanced agent features
• Learn about Memory & State for persistent conversations
• Check out Tool Factories for dynamic tool creation