---
name: Hugging Face Changelog
slug: hugging-face-changelog
type: scrape
source_url: https://huggingface.co/changelog
organization: Hugging Face
organization_slug: hugging-face
total_releases: 5
latest_date: 2026-04-07
last_updated: 2026-04-07
tracking_since: 2026-03-18
canonical: https://releases.sh/hugging-face/hugging-face-changelog
organization_url: https://releases.sh/hugging-face
---

<Summary type="rolling" window-days="90" release-count="5">
The Hub is building out infrastructure for agents as first-class entities, shipping storage and filesystem layers alongside trace capture and direct agent integration. hf-mount graduated remote storage to native filesystem access, letting agents treat Hub buckets as local disks 100x larger than physical hardware. Spaces now mount buckets directly as volumes, and the new Agent Traces viewer auto-detects and organizes debugging sessions from Claude Code and similar tools. The Hub also shipped protected Spaces—keeping model weights private while serving the app publicly—and wired Hugging Face Papers into agent tooling so Claude and Cursor can search and read papers without token bloat.
</Summary>

<Summary type="monthly" period="March 2026" release-count="4">
Storage and access patterns dominated the month. Spaces gained persistent storage through HF Buckets with direct mounting, while hf-mount enabled attaching remote storage 100x larger than local disk as a filesystem—crucial for agentic workloads handling massive model weights. Protected Spaces let developers keep URLs public while hiding implementation details, and AI agents gained native Hugging Face Papers integration with semantic search across papers and linked resources.
</Summary>

<Release date="April 7, 2026" published="2026-04-07T00:00:00.000Z" url="https://huggingface.co/changelog#agent-traces-on-the-hub">
## Agent Traces on the Hub

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.
</Release>

<Release date="March 31, 2026" published="2026-03-31T00:00:00.000Z" url="https://huggingface.co/changelog#storage-buckets-for-spaces">
## Storage Buckets for Spaces

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.
</Release>

<Release date="March 24, 2026" published="2026-03-24T00:00:00.000Z" url="https://huggingface.co/changelog#introducing-hf-mount">
## Introducing hf-mount

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
</Release>

<Release date="March 20, 2026" published="2026-03-20T00:00:00.000Z" url="https://huggingface.co/changelog#protected-spaces-with-public-urls">
## Protected Spaces with Public URLs

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.
</Release>

<Release date="March 18, 2026" published="2026-03-18T00:00:00.000Z" url="https://huggingface.co/changelog#hugging-face-papers-for-ai-agents">
## Hugging Face Papers for AI Agents

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.
</Release>