Upload traces from AI agents (Claude Code, Codex, Pi) directly to Hugging Face Datasets. The Hub auto-detects trace formats and tags datasets as Traces with a dedicated viewer for browsing sessions, turns, tool calls, and model responses. Upload JSONL files from local session directories as-is. Useful for sharing debugging workflows, benchmarking agent behavior, or building training data from real coding sessions.
Mount HF Buckets as persistent storage volumes directly in Spaces. In Space settings, create or select a bucket, set the mount path and access mode. Also attach a bucket when creating a new Space. Useful for caching model weights, storing user uploads, or sharing files between Spaces under the same organization.
Attach any Storage Bucket, model, or dataset from the Hub as a local filesystem. Allows attaching remote storage 100x bigger than local machine's disk—perfect for agentic storage. Read-write access for Storage Buckets, read-only for models and datasets. Install from GitHub: https://github.com/huggingface/hf-mount
Set Spaces to protected, making them private on Hugging Face while keeping their URL publicly accessible. Useful for deploying production-ready demos or internal tools without exposing model weights, prompts, or proprietary logic. Can be combined with custom domains to host websites on Hugging Face.
AI agents (Cursor, Claude Code) now receive Markdown versions of Hugging Face Papers automatically, saving tokens and improving efficiency. A new hugging-face-paper-pages skill for AI agents enables searching papers by title, author, or semantic similarity, reading content, and discovering linked models, datasets, and Spaces on the Hub.