LLM Generator

Generate llms.txt files for websites to improve their visibility to large language models

LLM Generator

Project Overview

LLMGenerator is a service that generates llms.txt files for websites to improve their visibility to large language models. The service uses Firecrawl's map + scrape approach with OpenAI enhancement to create high-quality, LLM-optimized content.

What is llms.txt?

llms.txt is a standardized format for making website content more accessible to Large Language Models (LLMs). It provides:

  • llms.txt: A concise index of all pages with AI-enhanced titles and descriptions
  • llms-full.txt: Complete content of all pages for comprehensive access

What is llms.txt?

llms.txt is a standardized format for making website content more accessible to Large Language Models (LLMs). It provides:

  • llms.txt: A concise index of all pages with AI-enhanced titles and descriptions
  • llms-full.txt: Complete content of all pages for comprehensive access

Key Features

  • 🚀 Fast Generation: Direct map + scrape approach with background processing
  • Reliable Background Jobs: Trigger.dev integration for long-running tasks with automatic retries
  • 🤖 AI-Enhanced Content: OpenAI-powered titles and descriptions for paid plans
  • 💰 Cost-Optimized Tiers: 95% cheaper than competitors - Free and paid plans with different generation methods
  • 📊 Comprehensive Analytics: Track generation stats, mapped URLs, and usage
  • 🔄 Real-time Updates: Live progress tracking with dedicated status pages
  • 🛡️ Enterprise Ready: Rate limiting, API keys, and robust error handling
  • 📖 API Documentation: OpenAPI/Swagger 3.0 with interactive documentation
  • 🌐 Background Processing: Trigger.dev handles long-running tasks with retries
  • 🔒 Flexible Pricing: Credit packages (never expire) + subscription plans

Tech Stack

Frontend

  • React 19 with TypeScript
  • Vite for fast builds
  • Tanstack Router & Query
  • Tailwind CSS & shadcn/ui
  • React Hook Form with Zod validation

Backend

  • Hono on Cloudflare Workers
  • Cloudflare D1 (SQLite) with Drizzle ORM
  • Better Auth for authentication
  • Trigger.dev for background jobs
  • tRPC for type-safe APIs

Integrations

  • Firecrawl API for web scraping
  • OpenAI API for content enhancement
  • Stripe for payments
  • Cloudflare KV for session caching
  • Sentry for error tracking

Development & Testing

  • Biome for linting/formatting
  • Bun for package management
  • Wrangler for deployments
  • Vitest with 135 tests
  • OpenAPI/Swagger documentation

Generation Methods

🆓 Simple Generation (1x Credits)

  • ✓ Fast generation (15-30 seconds)
  • ✓ Uses Firecrawl's /llmstxt endpoint
  • ✓ Cost-effective for free tier users
  • ✓ Locked for free plans, optional for paid

⭐ Enhanced Generation (2x Credits)

  • ✓ AI-enhanced titles (3-4 words) and descriptions (9-10 words)
  • ✓ Uses map + scrape + OpenAI integration
  • ✓ Premium quality for paid plans
  • ✓ Default for paid users

Business Model & Revenue

This SaaS platform serves developers, agencies, and businesses who want to improve their website's visibility to large language models. The credit-based pricing system provides flexibility while maintaining healthy margins.

Revenue Streams:

  • Credit packages (pay-as-you-go)
  • Subscription plans (monthly recurring)
  • API access (all paid tiers)
  • Enterprise custom solutions

Competitive Advantages:

  • 95% cheaper than competitors
  • Credits never expire (packages)
  • API-first architecture
  • Real-time background processing

Project Timeline

Start Date: June 2025
Status: 🔨 Work in Progress (v2.0.0)
Type: Personal SaaS Project

Links