# llms.txt - AI-Friendly Documentation URL: https://research-memex.org/docs/introduction/llms Description: A machine-readable summary of Research Memex documentation following the llms.txt standard for AI consumption *A site built for AI partnership should be legible to the partners themselves.* llms.txt is an emerging standard for making documentation easy for large language models to consume. Think of it as a `robots.txt` for AI: one file providing a structured overview of an entire project. ## Three ways AI can access this site [#three-ways-ai-can-access-this-site] | Method | URL | What it provides | | ----------------- | -------------------------------- | ------------------------------------------------------------------------------- | | **llms.txt** | [/llms.txt](/llms.txt) | Generated orientation index with links to public docs pages and the full corpus | | **llms-full.txt** | [/llms-full.txt](/llms-full.txt) | Complete site content in one file (auto-generated, always current) | | **.md suffix** | Any page + `.md` | Markdown version of individual pages for token-efficient loading | Start with `llms.txt` for orientation, use `llms-full.txt` for comprehensive context, and use a `.md` suffix when you need only one page. ## Why llms.txt? [#why-llmstxt] AI tools can load the entire documentation structure in one request Hierarchical organization helps AI understand relationships between topics Every page, concept, and resource listed in one place Following emerging best practices for AI-readable documentation ## How it works [#how-it-works] When you ask an AI assistant about Research Memex: ```text 1. AI fetches research-memex.org/llms.txt 2. Reads the generated site summary and public documentation links 3. Parses the structured documentation map 4. Identifies relevant sections for your query 5. Fetches specific pages via .md suffix or llms-full.txt 6. Provides contextualized answers in the right voice ``` Try it yourself: ask an AI assistant, "Fetch the llms.txt from research-memex.org and tell me about [interpretive orchestration](/docs/introduction/core-principles#1-interpretive-orchestration)." ## What's included [#whats-included] The generated `llms.txt` contains: * Site title and description * Canonical link to the full generated corpus * Public docs pages grouped as readable links * Public documentation pages with descriptions * Hierarchical structure (Introduction → Implementation → Case Studies → Toolkit → Advanced) * Direct links to each section * Essential tools and research platforms * Claude Code plugins and MCP servers in the Toolkit * AI-readable page links for focused loading * Generated links to pages that carry the detailed answers * No separate hand-written FAQ layer * No stale manual navigation map * Contact information * Repository links ## Use cases [#use-cases] ### For AI assistants [#for-ai-assistants] ```bash Claude Code # AI can directly fetch and parse curl https://research-memex.org/llms.txt ``` ```bash Antigravity CLI # Quick project understanding "Analyze the Research Memex based on its llms.txt" ``` ```bash Cherry Studio # Direct markdown fetch "Fetch research-memex.org/llms-full.txt and explain cognitive blueprints" ``` ### For developers [#for-developers] Useful when working with an AI assistant while coding: ``` "Using research-memex.org/llms.txt, show me the Zotero MCP setup steps" ``` Reference it in your own documentation: ```markdown This project uses the Research Memex approach. See: research-memex.org/llms.txt ``` Study it as an example: ``` "Compare research-memex.org/llms.txt structure to other documentation approaches" ``` ## View the files [#view-the-files] Generated index for orientation Complete site content (auto-generated) Example: Core Principles as .md Access directly: ```text https://research-memex.org/llms.txt https://research-memex.org/llms-full.txt https://research-memex.org/docs/introduction/core-principles.md ``` ## The standard [#the-standard] The llms.txt format is an emerging community standard for AI-readable documentation. Learn more: Official llms.txt specification and examples * Plain text format (Markdown) * Hierarchical structure * Complete navigation * Concepts upfront * Links to full content ## For the meta-curious [#for-the-meta-curious] This creates a beautiful loop: 1. We write docs about research with AI 2. We make those docs AI-readable (llms.txt + llms-full.txt + per-page `.md`) 3. Students learn the approach through dialogue with AI 4. The approach becomes embedded through practice 5. Students understand both the framework and how AI accesses knowledge ## Next steps [#next-steps] AI-to-AI communication guidelines