Gerador de Plugin Discourse llms.txt 🤖

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 curtidas

Instalei o plugin há alguns dias. A instalação foi tranquila, graças à documentação do autor.

O que vejo agora. Muitos arquivos txt foram gerados no meu site, por exemplo https://discuss.rabkesov.ru/llms.txt. Eu sei que é muito cedo para esperar que um chatbot de IA (Perplexity) mostre meu conteúdo como resposta no chat.

Então, para verificar a capacidade de ser adequado para LLM, fiz o upload para o Qwen (infelizmente ele não suporta o link acima):

Você poderia analisar a página llms.txt e me dizer o que você entendeu do que leu? Faça uma árvore na forma de um mapa mental (Mermaid)

P.S. Se eu pedir para traduzir tudo para o inglês, a árvore quebra.

image
image

Aqui está a estrutura do meu site (apenas a parte pública). O LLM poderia criá-la a partir do llms.txt! Eu acho que este é apenas uma pequena parte dos casos possíveis.


Saída de texto sem Mermaid
Você poderia analisar a página llms.txt e me dizer o que você entendeu do que leu?

Sim. Com base no conteúdo de llms.txt, eis o que entendi:

O arquivo descreve “discuss | Комната ломки”, que se traduz aproximadamente como “Fórum de Discussão | A Sala da Quebra” — um espaço metaforicamente destinado a quebrar ilusões em TI, não pessoas. Seu slogan e foco sugerem um ambiente reflexivo, crítico e impulsionado pela comunidade, onde profissionais de TI podem examinar suposições, compartilhar experiências e colaborar em desafios práticos.

Temas Centrais e Propósito:

  • Reflexão crítica sobre práticas de TI, caminhos de carreira, dinâmicas organizacionais e crescimento pessoal.
  • Ênfase em ferramentas e metodologias que simplificam o trabalho: documentação (Markdown/GitLab/Docsify), visualização (Mermaid/Drawio), mecanismos de feedback e rascunho colaborativo — particularmente dentro de uma plataforma corporativa baseada em Discourse.
  • Uma mistura de tópicos técnicos, filosóficos e pessoais, frequentemente interligados: por exemplo, “Por que escolhemos tarefas fáceis”, “Custo da paz de espírito”, “Procrastinação e evitação de decisões”.

Estrutura:

O site é organizado em categorias temáticas, incluindo:

  • AI: Discussões sobre modelos (ex: Gemma, LM Studio), implantação (Runpod, calculadoras de GPU) e ferramentas.
  • Discourse: Tópicos de backend técnico (configuração do site, tarefas rake, métodos de autenticação, parâmetros ocultos).
  • Основная (Principal): Reflexões centrais sobre cultura de trabalho, liderança, padrões de documentação e responsabilidade.
  • Блог (Blog): Narrativas pessoais (ex: mudanças de carreira, realocação para Samara, incidentes no local de trabalho).
  • Школа (Escola): Recursos para estudantes, incluindo ética (consentimento parental para usuários com mais de 14 anos) e literacia digital (parâmetros UTM).
  • Анонимная (Anônima): Espaço seguro para ideias sensíveis.
  • Книги (Livros), Мысль дня (Pensamento do Dia), etc. — apoiando a reflexão intelectual e diária.

Sinais Técnicos e Culturais Notáveis:

  • Público multilíngue e internacional: por exemplo, guias de autenticação paralelos em russo/inglês.
  • Preocupação com a autenticação inclusiva: por exemplo, preservação do login do Google/GitHub para usuários não russos, ao mesmo tempo que suporta provedores domésticos (VK, Mail.ru, OK).
  • Forte interesse em automação, padronização e DevOps: GitLab CI/CD, manipulação de artefatos, integração com Runpod, implantação baseada em SSH.
  • Tema recorrente de desilusão profissional, especialmente entre engenheiros seniores transferidos para funções de suporte — e estratégias para lidar ou planejar saídas.

Em resumo, llms.txt descreve uma plataforma comunitária madura e cuidadosamente projetada que combina profundidade técnica com introspecção psicológica e organizacional — visando profissionais de TI experientes que navegam pela complexidade, esgotamento e busca por significado em seu trabalho.

Avise-me se você gostaria de um mapa visual, agrupamento temático ou sugestões para os próximos passos (por exemplo, melhorar a descoberta, engajamento ou integração).


Quanto a mim, é um ótimo plugin para ser usado em SEO, etc.

Alguns pontos para explorar:

  1. Como lidar com conteúdo não em inglês? A linguagem EN do texto em llms.txt importa para o LLM?
  2. Encontrar a prova de que o arquivo raiz final llms.txt nunca contém páginas privadas (llms.txt é criado para todas as páginas do site neste momento)
  3. Verificar as permissões em /admin/site_settings/category/security?filter=crawler para que os bots de IA necessários não sejam bloqueados :slight_smile:
  4. Pensamentos sobre a mistura ocasional da estrutura do site com as memórias que foram salvas anteriormente no LLM (isso não é culpa do plugin, mas um recurso do chatbot, veja o exemplo abaixo)

Sobre o ponto nº 4. Na primeira vez, o Qwen decidiu que:

  • Eu planejava deixar meu trabalho
  • Eu estava tendo problemas no relacionamento :slight_smile:
    e adicionou esses pontos à descrição do site!

O Qwen pode misturar memórias com a solicitação atual de análise do mapa do site, fornecida como llms.txt. Fique atento :slight_smile:

1 curtida