Connect Hugging Face to Your AI Agent

Describe the model task or dataset you are evaluating. AI can compare metadata and inspect sample rows before you choose.

14 tools OAuth

Connect Hugging Face Install OOMOL

Try a Hugging Face Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Hugging Face

Evaluate a dataset split

Read dataset information, sample rows, and column statistics to assess its suitability.

/oo Hugging Face: Inspect dataset [owner/dataset], configuration [config], split [split]. Read its metadata, first rows, and statistics, then explain whether it suits [task]. Note any partial statistics.

Compare models for a task

Find models by task and compare their metadata and access requirements.

/oo Hugging Face: Find Hugging Face models for [pipeline task]. Read details for [selected model IDs] and compare their library, tags, configuration, and gating status.

Start Working with Hugging Face

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Hugging Face

Authorize your Hugging Face account through OAuth.
Connect Hugging Face →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

A Hugging Face account with access to the repositories or inference models you need.

Hugging Face Tools

This connection reads Hub models, datasets, Spaces, repository files, and endpoint listings. Inference operations generate chat responses or text embeddings with available models.

Hub research

Discover models, datasets, and Spaces, inspect repository files, and preview dataset content.

Inference

Generate non-streaming chat responses or embeddings and list inference endpoints for a namespace.

14 tools

Get Current User

Get the current authenticated Hugging Face user profile.

huggingface.get_current_user

List Models

List Hugging Face models using user-friendly search filters.

huggingface.list_models

Get Model Info

Get detailed metadata for a Hugging Face model by modelId.

huggingface.get_model_info

List Datasets

List Hugging Face datasets using user-friendly search filters.

huggingface.list_datasets

Get Dataset Info

Get detailed metadata for a Hugging Face dataset by dataset id.

huggingface.get_dataset_info

Get Dataset First Rows

Preview the first rows of a dataset split from the Hugging Face Dataset Viewer.

huggingface.get_dataset_first_rows

Get Dataset Statistics

Get column statistics for a dataset split from the Hugging Face Dataset Viewer.

huggingface.get_dataset_statistics

List Spaces

List Hugging Face Spaces using user-friendly discovery filters.

huggingface.list_spaces

Get Space Info

Get detailed metadata for a Hugging Face Space by repo id.

huggingface.get_space_info

List Repo Files

List files in a Hugging Face repository tree.

huggingface.list_repo_files

Get Trending

Get trending Hugging Face repositories across models, datasets, and Spaces.

huggingface.get_trending

List Endpoints

List Hugging Face Inference Endpoints for a namespace.

huggingface.list_endpoints

Generate Chat Completion

Generate a chat completion with Hugging Face Inference Providers.

huggingface.generate_chat_completion

Generate Embeddings

Generate text embeddings with Hugging Face inference.

huggingface.generate_embeddings

Frequently Asked Questions

What do I need to preview a dataset?

Provide its full repository ID, configuration name, and split name. Statistics may cover only part of the source.

Does model information include the complete model card?

It includes repository metadata, configuration, and parsed card metadata, rather than the complete card text.

Can I use any model for inference?

Use a model available for the selected inference operation and accessible to your account. Inference access and usage depend on Hugging Face and its providers.