What is Docusaurus?
Docusaurus is Meta's open-source documentation framework built on React. It is widely used by large open-source projects to publish versioned, searchable documentation sites from Markdown and MDX files.
How Kelu works with Docusaurus
Everything you can do once the integration is connected.
Multi-version doc support
Add one source per versioned path and give each a Version label (v1, v2, or latest). With source groups, on the Enterprise plan, each version's widget answers from the correct version of your Docusaurus docs.
Robots.txt and sitemap compliance
The crawler respects your Docusaurus robots.txt and uses the sitemap to discover all pages — including blog posts, API references, and custom pages.
Hybrid search across all versions
Users can ask questions about any version of your docs. Kelu uses vector + full-text hybrid search and RRF fusion to surface the most relevant answer.
How to set it up
- 01
Add your Docusaurus site URL to a Kelu knowledge base. The crawler will discover pages via sitemap.xml and start the first index.
- 02
Add the Kelu widget script to the scripts option in docusaurus.config.js to surface AI chat to all visitors.
- 03
Give each versioned source a Version label. On the Enterprise plan, scope each version's widget to its own source group.
Related integrations
Mintlify
Kelu crawls your Mintlify docs site, keeps it in sync, and answers user questions with citations.
GitBook
Index your GitBook spaces and let users ask questions with full citations back to source pages.
ReadMe
Crawl your ReadMe docs hub and let users ask questions with cited answers from your reference material.
Got questions?
Docusaurus — Frequently Asked Questions
Common questions about connecting Kelu to Docusaurus.
Yes. Add one source per versioned path of your Docusaurus site and give each a Version label (v1, v2, latest). On the Enterprise plan, put each in its own source group and scope each version's widget to it, so users get answers from the correct version.
Add the Kelu script to the scripts option in docusaurus.config.js. Docusaurus adds it to every page, with no swizzling needed.
Yes. Kelu uses your Docusaurus sitemap.xml to discover all pages — including blog posts, API reference pages, and any custom pages. You can exclude specific URL patterns in the source settings if you prefer to limit indexing to the /docs path only.
Kelu re-crawls every 24 hours, and the knowledge base's Scheduled Crawling setting can add an hourly, daily, weekly, or monthly sync. Click Sync Now after a deploy to re-index at once. A sync only re-processes pages that have changed.