Generador de plugins llms.txt para Discourse 🤖

Discourse llms.txt Generator

:information_source: Summary Automatically generates llms.txt files that make your forum content discoverable by Large Language Models like ChatGPT, Claude, and other AI systems
:hammer_and_wrench: Repository Link GitHub - kaktaknet/discourse-llms-txt-generator: 🤖 Discourse llms.txt Generator Plugin. Automatically generates llms.txt and llms-full.txt files for your Discourse forum to optimize content discovery by Large Language Models (LLMs) and AI systems.
:open_book: Install Guide How to install plugins in Discourse

Features

This plugin implements the llms.txt standard - a proposed convention for providing LLM-friendly content from websites. Think of it as “robots.txt for AI” that helps your forum content appear in AI-generated responses.

For detailed feature documentation, see README.md

For technical documentation and development, see CONTRIBUTING.md

While this video isn’t specifically about Discourse or its plugins, it does a great job explaining why llms.txt files are important for your forum.

Thousands of sites—including many of the world’s largest and most respected tech companies—have already implemented the llms.txt standard on their own domains. Examples include:

  • :white_check_mark: Amazon AWS — https://docs.aws.amazon.com/llms.txt
  • :white_check_mark: Cloudflare — https://developers.cloudflare.com/llms.txt
  • :white_check_mark: Stripe — https://stripe.com/llms.txt
  • :white_check_mark: Angular — https://angular.dev/llms.txt
  • :white_check_mark: Redis — https://redis.io/llms.txt
  • :white_check_mark: Docker — https://docs.docker.com/llms.txt
  • :white_check_mark: Model Context Protocol — https://modelcontextprotocol.io/llms-full.txt

When industry giants adopt a standard at scale—long before it becomes “official”—it’s a clear signal that llms.txt solves a real and urgent problem. Such companies never roll out sitewide initiatives lightly; they always have a solid strategic reason. The rapid, large-scale embrace of llms.txt across the tech industry shows just how important structured content for AI has become, and that the industry itself is driving this adoption forward—even faster than formal standards bodies.

Key capabilities:

  1. Main Navigation File (/llms.txt)

    • Structured overview of your forum with categories, subcategories, and latest topics
    • Helps AI systems understand your forum organization instantly
    • Automatically updates as your forum grows
  2. Full Content Index (/llms-full.txt)

    • Complete forum index with all topics categorized and ready for AI consumption
    • Configurable filtering by views and topic count
    • Optional post excerpts for faster AI indexing
  3. Dynamic Per-Resource Files

    • Generate llms.txt for any category: /c/category-name/123/llms.txt
    • Generate llms.txt for any topic: /t/topic-slug/456/llms.txt
    • Generate llms.txt for any tag: /tag/tutorial/llms.txt
    • Created on-demand without physical storage
  4. Sitemap Index (/sitemaps.txt)

    • Complete list of all llms.txt URLs for efficient AI crawler discovery
    • Automatically integrates with robots.txt and sitemap.xml
  5. SEO Protection

    • Canonical URLs in HTTP headers (RFC 6596 compliant)
    • Prevents duplicate content penalties from search engines
    • Proper attribution to original forum URLs
  6. Smart Caching

    • Hourly background checks for new content
    • Only regenerates when necessary
    • Fast response times (under 50ms)
  7. Bot Control

    • Block specific AI crawlers while allowing forum access
    • Comma-separated list of user agents to block
    • Automatic robots.txt integration via view connector
  8. Privacy & Security

    • Private categories automatically excluded
    • Guardian permission checks for dynamic files
    • SQL-level security filtering
    • No personal data exposed

Benefits for your forum:

  • Increased Visibility: Your content appears in ChatGPT, Claude, and other AI responses
  • Direct Attribution: AI systems cite and link back to your forum
  • More Traffic: Increased discovery through AI-powered search
  • Better GEO: Generative Engine Optimization for AI systems
  • No Maintenance: Automatic generation and updates

Configuration

After installing the plugin, navigate to Admin → Settings → Plugins → discourse-llms-txt-generator

Step 1: Enable the plugin

Set llms_txt_enabled to true (enabled by default)

Step 2: Configure indexing

Set llms_txt_allow_indexing to true to allow AI crawlers access (enabled by default)

This setting controls whether llms.txt files appear in your robots.txt as allowed or disallowed.

Step 3: Set content filters

Configure these settings based on your forum size:

  • llms_txt_min_views: Minimum topic views to include (default: 50)
  • llms_txt_posts_limit: How many topics to include
    • small: 500 topics (recommended for large forums)
    • medium: 2,500 topics (recommended for most forums)
    • large: 5,000 topics
    • all: All topics (use cautiously on large forums)

Step 4: Optional - Add custom description

Fill in llms_txt_full_description with 2-4 sentences describing your forum’s purpose and community. This helps AI systems provide more accurate information about your forum.

Example:

This forum is dedicated to discussing Python programming, with focus on web development,
data science, and machine learning. Our community includes beginners and experienced
developers sharing practical solutions and best practices.

Step 5: Optional - Block specific bots

If you want to block certain AI crawlers, enter their user agent names in llms_txt_blocked_user_agents as a comma-separated list:

Example: Omgilibot, ChatGPT-User, CCBot

Step 6: Verify installation

Visit your forum at:

  • /llms.txt - Main navigation file
  • /llms-full.txt - Full content index
  • /sitemaps.txt - Complete sitemap

Check your /robots.txt to verify the integration.

Settings

Name Default Description
llms_txt_enabled true Enable or disable the plugin
llms_txt_allow_indexing true Allow AI crawlers to access llms.txt files (affects robots.txt)
llms_txt_blocked_user_agents "" Comma-separated list of bot user agents to block from llms.txt files
llms_txt_intro_text Custom text Introduction text that appears in the main llms.txt file
llms_txt_full_description "" Custom description for llms-full.txt to help AI understand your forum context
llms_txt_min_views 50 Minimum topic views required for inclusion in llms-full.txt
llms_txt_posts_limit medium Topic count limit: small (500), medium (2,500), large (5,000), or all
llms_txt_include_excerpts false Include post excerpts in llms-full.txt (increases file size significantly)
llms_txt_post_excerpt_length 500 Maximum excerpt length in characters (100-5000) if excerpts are enabled
llms_txt_latest_topics_count 50 Number of latest topics to show in main llms.txt file
llms_txt_cache_minutes 60 Cache duration in minutes for the navigation file

Important notes:

  • Enabling llms_txt_include_excerpts with llms_txt_posts_limit set to all may cause extremely large file sizes (potentially 10-100+ MB) and high server load on large forums
  • Private categories are automatically excluded from all llms.txt files
  • Dynamic per-resource files (categories, topics, tags) are not cached and generated on-demand
  • The plugin uses view connectors for robots.txt integration - no need to manually edit robots.txt

Technical Details

Architecture:

  • On-demand generation without pre-generated files
  • Smart caching with hourly background checks
  • Permission-aware using Discourse Guardian
  • SQL-level security filtering for private content
  • Canonical URLs in HTTP headers to prevent SEO penalties

Performance:

  • Navigation file cached for 60 minutes (configurable)
  • Full content file generated on-demand
  • Smart cache only regenerates when new content exists
  • Response time under 50ms for cached content

Compatibility:

  • Discourse 2.7.0+
  • Ruby 2.7+
  • Tested on Discourse 3.6.0.beta3

Standards compliance:

  • llms.txt standard (https://llmstxt.org/)
  • RFC 3986 (URL encoding for international characters)
  • RFC 6596 (Canonical Link headers)

Use Cases

Community Forums:
Your discussions and solutions appear when users ask AI assistants relevant questions, driving qualified traffic back to your forum.

Documentation Sites:
AI systems can reference your documentation and tutorials, providing accurate information with proper attribution.

Support Forums:
Users get direct answers from your knowledge base through AI assistants, with links back to full discussions.

Technical Communities:
Developers discover your forum content through AI-powered coding assistants, increasing community engagement.

Maintenance

The plugin requires minimal maintenance:

  • Cache automatically refreshes every hour
  • Content updates happen automatically on post creation/editing
  • No manual file generation needed
  • Optional rake tasks available: llms_txt:refresh and llms_txt:check

Troubleshooting

Files not accessible:

  • Verify llms_txt_enabled is true
  • Check that llms_txt_allow_indexing is true
  • Confirm plugin is installed in Admin → Plugins

Empty content:

  • Ensure you have public topics with sufficient views (check llms_txt_min_views setting)
  • Verify categories are public (not read-restricted)
  • Check llms_txt_posts_limit setting

robots.txt integration not working:

  • Clear robots.txt cache: Rails.cache.delete('robots_txt')
  • Use rake task: bundle exec rake llms_txt:refresh
  • Restart Discourse: ./launcher restart app

Support

License

MIT License - Free and open-source software

Credits

5 Me gusta

Instalé el plugin hace un par de días. La instalación fue fluida, gracias a la documentación del autor.

Lo que veo ahora. Se generaron muchos archivos txt en mi sitio, por ejemplo https://discuss.rabkesov.ru/llms.txt. Sé que es pronto para esperar que un chatbot de IA (Perplexity) muestre mi contenido como respuesta en el chat.

Así que, para comprobar la capacidad de ser adecuado para LLM, lo subí a Qwen (desafortunadamente no admite el enlace anterior):

¿Podrías analizar la página llms.txt y decirme qué entendiste de lo que leíste? Haz un árbol en forma de mapa mental (Mermaid)

P.D. Si pido traducir todo al inglés, el árbol se rompe.

image
image

Aquí está la estructura de mi sitio (solo la parte pública). ¡Un LLM podría haberla creado a partir de llms.txt! Creo que es solo una pequeña parte de los casos posibles.


Salida de texto sin Mermaid
¿Podrías analizar la página llms.txt y decirme qué entendiste de lo que leíste?

Sí. Basado en el contenido de llms.txt, esto es lo que entendí:

El archivo describe “discuss | Комната ломки”, que se traduce aproximadamente como “Foro de Discusión | La Sala de Desarme” — un espacio metafóricamente destinado a desmantelar ilusiones en TI, no personas. Su lema y enfoque sugieren un entorno reflexivo, crítico y comunitario donde los profesionales de TI pueden examinar suposiciones, compartir experiencias y colaborar en desafíos prácticos.

Temas Centrales y Propósito:

  • Reflexión crítica sobre prácticas de TI, trayectorias profesionales, dinámicas organizacionales y crecimiento personal.
  • Énfasis en herramientas y metodologías que simplifican el trabajo: documentación (Markdown/GitLab/Docsify), visualización (Mermaid/Drawio), mecanismos de retroalimentación y redacción colaborativa — particularmente dentro de una plataforma corporativa basada en Discourse.
  • Una mezcla de temas técnicos, filosóficos y personales, a menudo interconectados: p. ej., “Por qué elegimos tareas fáciles”, “Costo de la tranquilidad”, “Procrastinación y evitación de decisiones”.

Estructura:

El sitio está organizado en categorías temáticas, que incluyen:

  • AI: Discusiones sobre modelos (p. ej., Gemma, LM Studio), implementación (Runpod, calculadoras de GPU) y herramientas.
  • Discourse: Temas técnicos del backend (configuración del sitio, tareas rake, métodos de autenticación, parámetros ocultos).
  • Основная (Principal): Reflexiones centrales sobre la cultura laboral, el liderazgo, los estándares de documentación y la responsabilidad.
  • Блог (Blog): Narrativas personales (p. ej., cambios de carrera, reubicación a Samara, incidentes en el lugar de trabajo).
  • Школа (Escuela): Recursos para estudiantes, incluida la ética (consentimiento paterno para usuarios mayores de 14 años) y la alfabetización digital (parámetros UTM).
  • Анонимная (Anónima): Espacio seguro para ideas sensibles.
  • Книги (Libros), Мысль дня (Pensamiento del Día), etc. — que apoyan la reflexión intelectual y diaria.

Señales Técnicas y Culturales Notables:

  • Audiencia multilingüe e internacional: p. ej., guías de autenticación paralelas en ruso/inglés.
  • Preocupación por la autenticación inclusiva: p. ej., preservar el inicio de sesión con Google/GitHub para usuarios no rusos, al tiempo que se admiten proveedores nacionales (VK, Mail.ru, OK).
  • Fuerte interés en la automatización, estandarización y DevOps: GitLab CI/CD, manejo de artefactos, integración de Runpod, implementación basada en SSH.
  • Tema recurrente de desilusión profesional, especialmente entre ingenieros sénior trasladados a roles de soporte, y estrategias para afrontarlo o planificar salidas.

En resumen, llms.txt describe una plataforma comunitaria madura y cuidadosamente diseñada que combina profundidad técnica con introspección psicológica y organizacional, dirigida a profesionales de TI experimentados que navegan por la complejidad, el agotamiento y la búsqueda de sentido en su trabajo.

Avísame si deseas un mapa visual, agrupación temática o sugerencias para los próximos pasos (p. ej., mejorar la capacidad de descubrimiento, la participación o la incorporación).


En cuanto a mí, es un gran plugin para usar en SEO, etc.

Algunos puntos a explorar:

  1. ¿Cómo manejar el contenido que no está en inglés? ¿Le importa al LLM el idioma EN del texto en llms.txt?
  2. Encontrar la prueba de que el archivo raíz final llms.txt nunca contiene páginas privadas (llms.txt se crea para cada página del sitio en este momento).
  3. Comprobar los permisos en /admin/site_settings/category/security?filter=crawler para que los bots de IA necesarios no estén bloqueados :slight_smile:
  4. Reflexiones sobre la mezcla ocasional de la estructura del sitio con los recuerdos que el LLM ha guardado previamente (esto no es culpa del plugin, sino una característica del chatbot, ver el ejemplo a continuación).

Sobre el punto #4. La primera vez, Qwen decidió que:

  • Planeaba dejar mi trabajo
  • Tenía problemas en mi relación :slight_smile:
    ¡y añadió estos puntos a la descripción del sitio!

Qwen puede mezclar recuerdos con la solicitud actual de analizar el mapa del sitio, proporcionado como llms.txt. Ten cuidado :slight_smile:

1 me gusta