Changelog

You can now duplicate any Dataset directly on the Hugging Face Hub, making it easier to experiment, modify, or extend existing datasets.

Thanks to Xet deduplication technology, duplication is nearly instant, allowing you to create your own copy and start iterating right away.

Profile statuses are here—pick “Open to Work” “Open to Collab” “Hiring 💼” and more! The label shows right on your avatar, so everyone knows what you’re up to in one look. 🤩

Featured Spaces (Spaces of the Week) are now marked with a 🔥 icon, making them easier to identify at a glance. This update helps you quickly find standout projects curated by the Hugging Face team.

Our official app is now listed on the Okta Integration Network (OIN) and available to all Okta users. Organizations get a trusted, pre-validated integration that makes SSO setup easier and onboarding faster. The app currently supports SAML, with OIDC, SCIM, and JIT provisioning coming soon.

Hugging Face Docs now expose llms.txt & llms-full.txt, making them easier for AI agents to read & process. Every page also includes buttons to view the Markdown source or chat about the content with various chatbots, including HuggingChat. When AI agents such as Cursor or Claude Code fetch a Hugging Face Docs page, Markdown versions of pages are served automatically, saving tokens and improving efficiency.