Our goal is to make it effortless to create a knowledge base for search and chat experiences. With our integrations and intellegent crawlers, we automatically index, chunk, embed, and re-rank all types of different content to get the best search and chat retrieval performance (learn more here).

Onboarding new content

Give us a ping over Slack or send an email to sources@inkeep.com. We personally onboard and vet the quality of all new sources.

Common sources

Below are sources that we support out of the box. Note that this list is not exhaustive, we’re generally able to ingest any web source.


  • Docusaurus
  • Next.js (Nextra and custom)
  • Astro (Starlight and custom)
  • Mintlify
  • Readme
  • GitBook
  • Redocly
  • VitePress / VuePress
  • Sphinx
  • Read the docs
  • Hugo
  • Gatsby
  • Custom


  • Discourse
  • Slack threads
  • Discord threads

Marketing / blogs / landing pages

  • Webflow
  • Framer
  • Next.js
  • Astro
  • Custom

CMS / Blogs

  • Wordpress
  • Sanity
  • Prismic
  • DatoCMS
  • Contentful
  • Strapi
  • Agility CMS
  • Cosmic
  • ButterCMS
  • Storyblok
  • Hygraph
  • Sitecore
  • Custom


  • GitHub (pull requests, issues, readmes, releases)
  • Changelogs
  • GraphQL specifications
  • OpenAPI specifications

Enterprise Sources

We support ingestion of historical support tickets, internal documents, and others sources that contains knowledge about your product. We’ll work with your team to ingest any source in any format and your security team to ensure compliance with your data processing policies.

Help center and support tickets

  • Intercom
  • Zendesk
  • Help Scout
  • Freshdesk

Internal knowledge

  • Notion
  • Google Drive
  • Confluence
  • Files (.docx, .md, .csv, .pdf, etc.)