Observed arrival · 2026-09-09
BigHugger, the AI index that reads the files
A search and research system covering models, datasets, papers, repositories, packages, MCP servers, skills, and frameworks.
Field notes
The index is assembled from eight source categories and extracts details from files such as model cards, tokenizers, chat templates, and configuration data. The page reports 4.2 million files inventoried, 785,000 structured properties, and 2.2 million evaluation results. Its outputs are designed for downstream execution: Workbooks can contain a notebook, pinned environment, model file, MCP server, and SKILL.md, while the cache mirrors repository weights with pinned revisions and resumable downloads.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue