Skip to main content
TA

Xet storage protocol docs for deduplicated model data

Documentation for the Xet content-addressed storage protocol and its reference implementations. It is aimed at developers building clients or tools that upload and download data from Hugging Face Hub using Xet.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 31 July 2026.

See pricing ↓

Visit Transformers Agents

Is this your tool? Claim this listing to manage your content and analytics.

Recent activity

What's happened with Transformers Agents lately

  • Score change
    Rubric upgrade v3_0 → v3.1: score 3/32 → 8/3638/36(+5)

    Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.

    See the news that prompted this

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about Transformers Agents

Get answers based on Transformers Agents's actual documentation

Try asking:

About

What It Is

Xet is a storage protocol and client implementation layer from Hugging Face for content-addressed data. The documentation describes how Xet handles chunking, hashing, deduplication, file reconstruction, authentication, and CAS APIs for upload and download.

What to Know

This is not a general AI agent product. Based on the crawled content, it is infrastructure for storage interoperability and deduplication, not a tool that autonomously completes tasks for you. Its value is in enabling consistent upload/download behavior and efficient storage across clients.

Key Features
Content-defined chunking for storage efficiency
Chunk-level and global deduplication
Xorb and shard binary formats
Upload and download CAS APIs
Authentication and authorization via Hugging Face tokens
Use Cases
Building a custom client that can upload files to Hugging Face Hub using Xet
Implementing a download tool that reconstructs files from Xet storage
Integrating Xet support into an SDK or automation pipeline
Agenticness: Guided Assistant

Executes tasks you assign, one step at a time, within narrow domains.

High evidence
Last evaluated: Jul 31, 2026

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Pricing not publicly available: No pricing details were found in the crawled content.
Details
AddedMarch 31, 2026
RefreshedAugust 20, 2026
Agenticness
Quick Facts
DeploymentHybrid (cloud + self-hosted)
AutonomyCopilot (human-in-loop)
Model supportMulti-model
Open sourceYes
Team supportSmall team
Pricing modelSubscription
Interfaceapi, cli, browser
Free daily brief

When Transformers Agents changes its pricing, we catch it the next morning

We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.

I use AI for: