GEO outputs from the command line
Generate llms.txt and llms-full.txt for any Node.js project — framework-agnostic, build-time, zero runtime overhead.
For developers who want GEO AI outputs without a framework integration. Works with Express, Fastify, Remix, static site generators, or any custom build pipeline.
Get started
Install and run in seconds
# Install locally (recommended)
npm install --save-dev geo-ai-cli
# Or globally
npm install -g geo-ai-cli# Scaffold geo-ai.config.ts
npx geo-ai init
# Write llms.txt + llms-full.txt to ./public
npx geo-ai generate
# Verify the output
npx geo-ai validateCommands
Four commands, full coverage
geo-ai init
Scaffolds a typed geo-ai.config.ts starter file. Safe to run — exits without overwriting if a config already exists.
geo-ai generate
Reads your config and writes llms.txt and llms-full.txt to ./public (or a custom --out path). Supports --config flag for custom paths.
geo-ai validate
Checks that llms.txt and llms-full.txt are present and have valid content. Works on local files or remote URLs via --url.
geo-ai inspect
Previews your config: site info, crawler rules, resource sections with item counts. Optionally fetches remote llms files.
Configuration
One config file
The CLI reads geo-ai.config.ts from your project root. Config discovery order: .ts → .js → .json. Required fields: siteName, siteUrl, provider.
import type { GeoAIConfig } from 'geo-ai-core';
export default {
siteName: 'My Site',
siteUrl: 'https://example.com',
siteDescription: 'A brief description for AI crawlers.',
crawlers: 'all',
provider: {
Pages: [
{ title: 'Home', url: 'https://example.com/', description: 'Welcome page' },
],
Blog: [
{ title: 'Getting Started', url: 'https://example.com/blog/start', description: 'First steps' },
],
},
} satisfies GeoAIConfig;Why CLI
Framework-agnostic, build-time generation
Any Node.js project
Works with Express, Fastify, Hono, Remix, or any static site generator — not just Next.js.
Build-time output
Generate llms.txt before deployment. Static files are served directly with no runtime overhead.
CI/CD friendly
Exit code 1 on validation failure. Drop geo-ai validate into any pipeline to catch regressions.
Ecosystem
Part of GEO AI
The CLI is powered by geo-ai-core and generates spec-compliant output — the same files the Analyzer checks and the Specification defines.
Documentation
Everything you need is documented
- All four commands with flags
- Config file reference
- Validation exit codes
- Debug mode
- Requirements