Skip to main content

AI-Friendly Documentation

Endive documentation is designed to be easily consumed by LLMs, AI agents, and developer tools. All machine-readable files are auto-generated at build time from the same source as the human-facing site, using the llms.txt specification.

Available Endpoints​

EndpointDescription
/llms.txtLightweight index of all docs and blog posts with one-line descriptions
/llms-full.txtFull documentation content concatenated into a single file
/sitemap.xmlStandard sitemap for crawler discovery
/robots.txtPermits all crawlers including AI agents

Every documentation page also has a raw Markdown version available by appending .md to its path. For example:

Usage Examples​

Feed Endive docs to an LLM in one shot​

Fetch llms-full.txt and include it in your prompt context:

curl -s https://endive.run/llms-full.txt | wc -c
# ~86 KB — fits easily in any modern LLM context window

Let an AI agent discover relevant pages​

An agent can fetch llms.txt first to find the right page, then fetch only that page's Markdown:

# 1. Fetch the index
curl -s https://endive.run/llms.txt

# 2. Fetch a specific page as clean Markdown
curl -s https://endive.run/docs/core/host-functions.md

Configure AI coding tools​

Many AI-powered development tools support llms.txt natively. Point them to https://endive.run/llms.txt to give them access to the full Endive documentation.

What Gets Included​

  • All documentation pages covering installation, core concepts, compilation, WASI, security, and more
  • All published blog posts
  • Content is cleaned: front matter and test harness comments are stripped, leaving only the documentation text

These files are regenerated on every site build, so they always reflect the latest documentation.