Weavz
Hugging Face

Hugging Face

Run inference on 100,000+ open ML models for NLP, vision, and audio tasks

API KeyAI
8 tools
Use withChatGPTClaudeClaude CodeCursorCodexMCP clientsSetup guide

Tools

Name
document_question_answering

Answer questions from document images using Hugging Face models

language_translation

Translate text between languages using Hugging Face translation models

text_classification

Classify text into categories using Hugging Face models

text_summarization

Generate summaries of long text using Hugging Face models

chat_completion

Generate assistant replies using chat-style LLMs

create_image

Generate images from text prompts using Hugging Face diffusion models

object_detection

Detect and locate objects in images with bounding boxes

image_classification

Classify images with pre-trained or custom categories

Quick Start

TypeScript
import { WeavzClient } from '@weavz-io/sdk'

const weavz = new WeavzClient({ apiKey: 'wvz_...' })

const result = await weavz.actions.execute('hugging-face', 'document_question_answering', {
  workspaceId: '550e8400-e29b-41d4-a716-446655440000',
  integrationAlias: 'hugging-face',
  input: { /* ... */ },
})

Related Integrations

Works well with

Frequently Asked Questions

How do I connect Hugging Face to my app?

Use Weavz Hosted Connect for API Key authentication. Install the SDK, create a connection through the connect portal or API, then execute tools programmatically.

What tools does Hugging Face support?

Hugging Face supports 8 tools including Document Question Answering, Language Translation, Text Classification, Text Summarization, Chat Completion, and more.

Can I use Hugging Face with AI agents?

Yes. Add Hugging Face to an MCP server in Tool Mode or Code Mode. Code Mode provides 3 meta-tools with on-demand API discovery so agents can compose stateful workflows without loading every action schema up front.

How do I connect Hugging Face to ChatGPT or Claude?

Open the Weavz connector setup, sign in, choose a workspace, and add Hugging Face as an approved app. ChatGPT, Claude, and other remote MCP clients can then call the scoped Hugging Face tools exposed by that workspace.

Does Hugging Face work with Claude Code, Cursor, Codex, and local agents?

Yes. Remote and local MCP clients can connect to a Weavz MCP endpoint for the workspace. Local coding agents can also use the Weavz CLI to inspect apps, discover actions, run approved Hugging Face work, and execute Code Mode workflows from a terminal.

What can I ask an AI agent to do with Hugging Face?

Hugging Face exposes 8 tools, including Document Question Answering, Language Translation, Text Classification, Text Summarization, Chat Completion, and more. Use Weavz to keep credentials scoped, require approval for sensitive work, and audit what the agent did.

Can Hugging Face be used in stateful agent workflows?

Yes. Agents can combine Hugging Face tools with Filesystem, State KV, Human Gates, input partials, and other workspace integrations while keeping execution scoped to the selected workspace or end user.

What authentication does Hugging Face use?

Hugging Face uses API Key. Weavz stores credentials securely and uses them for authorized action execution.

How much does the Hugging Face integration cost?

The Hugging Face integration is included on all Weavz plans including the free tier with 20,000 actions per month. No credit card required.

Connect Hugging Face in minutes

Get 20,000 free action executions every month. No credit card required.