Build Spaces with AI agents

UpdateJul 16, 2026VerifiedAdded Sep 22, 2026

The new Space creation page has an option to build with an AI agent: copy the generated command into your agent to build and iterate on a Space for a model, paper, or local folder.

AI agents

Read Hugging Face's release notes

https://huggingface.co/changelog/spaces-with-agents

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Hugging Face Hub releases

Hugging Face HubJul 14, 2026

Fine-grained access token presets

Fine-grained tokens can be created from presets (Read-Only, Inference, Write, CI/CD, Full Access), and preset URLs link straight to a pre-configured token.

UpdateSource

Hugging Face HubJul 21, 2026

Egress metrics for users and organizations

Users see egress usage in the dashboard and organizations get a per-user egress breakdown. It currently covers only traffic routed through the Hugging Face CDN.

UpdateBIObservabilitySource

Hugging Face HubJul 22, 2026

Hugging Face MCP Server adds hf_fs tool

The Hugging Face MCP Server's new hf_fs tool provides a single interface to repositories, storage, documentation, papers and more, with search, in just over 1,000 tokens.

UpdateMCPSource

Hugging Face HubJul 22, 2026

Sandboxes for the Hugging Face MCP Server

Sandboxes give an assistant secure execution environments attached to buckets and repositories for dataset analysis, model training, and Space creation.

UpdateMCPSource

Hugging Face HubJun 30, 2026

Filter Models page by hardware

A Hardware filter on the Models page shows models that fit a specific GPU, CPU, or Apple Silicon chip, set from Hardware settings and shareable via URL.

UpdateSource

Hugging Face HubAug 3, 2026

Filter HF Jobs by label

Jobs can be filtered by label, with most-used labels shown as chips with job counts and a free-form key=value input, on user and organization jobs pages.

UpdateSource

Hugging Face HubJun 26, 2026

Send Hub feedback from the user menu

Users can share feedback on the Hub, including bug reports and feature suggestions, directly with the Hugging Face team from the user menu.

UpdateSource

Hugging Face HubAug 12, 2026

Granular feature access per resource group

Feature access can be controlled per resource group instead of only by organization role, for example leaving Jobs open, restricting Inference Endpoints to admins, and limiting blog publishing.

UpdateObservabilitySource

Also shipped on Jul 16, 2026

Snowflake SnowflakeJul 16, 2026

DCM Projects: New capabilities (Preview)

DCM Projects now supports the following capabilities in preview: For more information, see Supported object types in DCM Projects and Deploy and manage DCM Projects .

PreviewSource

Snowflake SnowflakeJul 16, 2026

VOLATILE scalar UDFs are supported with dynamic table incremental refresh (General availability)

VOLATILE scalar user-defined functions (UDFs) are now supported with dynamic table incremental refresh in INCREMENTAL, AUTO, and ADAPTIVE refresh modes. This applies to scalar UDFs written in Python, Java, Scala, JavaScript, and SQL. For incremental refresh, VOLATILE UDFs are supported only in the SELECT clause.

GASQLSource

Databricks Unity CatalogJul 16, 2026

Scala and Java UDFs in Unity Catalog are now generally available

Register Scala and Java user-defined functions (UDFs) in Unity Catalog and reuse them across notebooks, jobs, and SQL warehouses with Unity Catalog governance. Reuse existing JVM logic and get better performance than Python UDFs on all compute, including serverless. See Scala and Java user-defined functions (UDFs) in Unity Catalog .

GASQLGovernanceNotebooksSource

Databricks Agent Bricks and Mosaic AIJul 16, 2026

MLflow trace storage in Unity Catalog is now generally available

MLflow trace storage in Unity Catalog tables is now generally available. Databricks recommends storing traces in Unity Catalog for new and production workloads: storage is unlimited, traces are stored in OpenTelemetry (OTel) format, access is governed through Unity Catalog schema and table permissions, and you can query traces with SQL, Genie, AI/BI...

GASQLGovernanceSecuritySource

Databricks Databricks Data Intelligence PlatformJul 16, 2026

Agentic code converter is in Beta

The agentic code converter is in Beta . Use it to convert legacy SQL dialects, such as T-SQL, Snowflake, Redshift, Oracle, BigQuery, and Teradata, to ANSI SQL in migration projects in your workspace.

BetaAI agentsSQLBISource

Databricks Agent Bricks and Mosaic AIJul 16, 2026

Google Gemini 3 Pro is retired

Google Gemini 3 Pro is retired. Gemini 3.1 Pro is the recommended replacement. See Deprecated and retired models for migration guidance.

DeprecationLLMsSource