Pricing

from $1.00 / 1,000 results

AI Tools & Models Intelligence

Aggregate AI tool and model data from Futurepedia (29 tool categories) and Hugging Face Hub (models, datasets, spaces). Used by AI investors tracking new launches, founders sizing markets, recruiters sourcing AI talent, and SaaS competitive-intelligence teams benchmarking AI product features.

Pricing

from $1.00 / 1,000 results

Rating

0.0

(0)

Developer

Swerve

Actor stats

Bookmarked

Total users

Monthly active users

2 days ago

Last modified

Use cases

AI investors tracking new tool launches and which models are climbing the popularity rankings
Founders sizing a market ("how many code assistants are out there? how many have over 10K likes?")
Recruiters sourcing AI talent mining authors / orgs of top-trending models
Competitive-intelligence teams benchmarking AI product features against an industry-wide list
AI directory builders seeding their own catalog with a clean baseline
Data scientists finding the most popular datasets for a given task

Sources

Source	What it returns	Filters
`futurepedia`	AI tools across 29 categories	`category` (slug), `keyword` (client-side title filter)
`huggingface_models`	LLMs, vision, audio, multimodal models	`category` (e.g. `text-generation`), `keyword` (server-side), `sortBy`
`huggingface_datasets`	Training / evaluation datasets	`category` (e.g. `task_categories:text-classification`), `keyword`, `sortBy`
`huggingface_spaces`	Hosted Gradio / Streamlit demos	`category` (e.g. `gradio`), `keyword`, `sortBy`

Output fields

Field	Type	Description
`source`	string	One of: `futurepedia`, `huggingface_models`, `huggingface_datasets`, `huggingface_spaces`
`id`	string	Unique ID at the source
`name`	string	Display name
`url`	string	Direct URL on the source
`description`	string \| null	Short description (Futurepedia only)
`categories`	string[]	Human-readable categories
`tags`	string[]	Source-specific tags
`popularity`	integer \| null	Favs / likes
`downloads`	integer \| null	All-time downloads (HF models + datasets)
`author`	string \| null	Author / organization (HF only)
`libraryName`	string \| null	Library (HF models: transformers, diffusers, etc.)
`pipelineTag`	string \| null	Primary task (HF models)
`sdk`	string \| null	Spaces SDK (HF spaces)
`imageUrl`	string \| null	Thumbnail (Futurepedia)
`createdAt`	string \| null	ISO timestamp (HF only)
`scrapedAt`	string	ISO timestamp of the scrape

Examples

Top 100 trending models on Hugging Face:

{
  "source": "huggingface_models",
  "sortBy": "trending",
  "maxItems": 100
}

All text-generation LLMs sorted by downloads:

{
  "source": "huggingface_models",
  "category": "text-generation",
  "sortBy": "downloads",
  "maxItems": 500
}

AI chatbots on Futurepedia:

{
  "source": "futurepedia",
  "category": "chatbots",
  "maxItems": 50
}

All AI agent tools across Futurepedia:

{
  "source": "futurepedia",
  "category": "ai-agents",
  "maxItems": 100
}

Hugging Face Spaces built on Gradio, searching for "image":

{
  "source": "huggingface_spaces",
  "category": "gradio",
  "keyword": "image",
  "maxItems": 50
}

Notes

The keyword filter is title-first: every token must appear in the name, ID, categories, or tags. This avoids description-matching false positives.
Futurepedia category slugs include: productivity, chatbots, image, code-assistant, video, audio, writing-generators, design-generators, marketing, business, research-assistant, ai-agents, avatars, data-analysis, social-media, education-assistant, sales, customer-support, finance, legal, health, translation, art, gaming, real-estate, lifestyle, human-resources, religion, fun-tools.
Hugging Face uses cursor-based pagination via the Link header — pages up to the maxItems cap are fetched automatically.
No login or API key required.

Pricing

Pay per result. See the Pricing tab. Failed runs cost nothing.

Hugging Face Scraper — AI Models, Datasets, Spaces & Papers

logiover/huggingface-hub-intelligence-scraper

Export every AI model, dataset, space and daily paper from the Hugging Face Hub. Filter by task, library (transformers, diffusers, GGUF), language, license, author. Sort by downloads, likes, trending. Sibling files + README. Public HF API, no token. For AI builders, ML research, RAG and VC AI intel.

Logiover

LLM Web Scraper

incredible_moment/llm-scraper

Turn any website into structured JSON using AI. Supports OpenAI GPT-4 and Anthropic Claude. Built in Rust to minimize compute costs while waiting for LLM responses. Extract data without selectors.

Daniel Rosen

Meta Ad Scraper

hello.datawizards/Facebook-Ad-Scraper

Meta Ad Scraper is an Apify Actor that extracts detailed ad data from the Meta (Facebook) Ad Library, including titles, creatives, CTAs, and advertiser info. Ideal for marketing analytics, ad intelligence, and competitor research with full proxy support and clean JSON output.

datawizards

AI Model Governance MCP Server

ryanclinton/ai-model-governance-mcp

Enterprise AI compliance and governance intelligence for AI agents via the Model Context Protocol.

Ryan Clinton

MCP: YouTube Intel - AI Agents Transcript Metadata

seibs.co/mcp-youtube-intelligence

Model Context Protocol wrapper around youtube-intelligence. Exposes 5 AI-agent tools: fetch_transcript, fetch_metadata, bulk_transcripts, search_channel, find_sponsored_segments. Built for Claude, LangChain, LlamaIndex, Lindy. Pay per tool call + pass-through.

Seibs.co

AI Content Detector

muhammetakkurtt/ai-content-detector

The AI Content Detector instantly analyzes how much of your text or file was written by AI. Verify content authenticity, boost your SEO, and maintain academic integrity. Secure your texts with fast, reliable results.

Muhammet Akkurt

5.0

(1)

CarMax Intelligence Scraper

lokki/carmax-intelligence-scraper

Scrape CarMax inventory and enrich vehicles with deal scoring, price/mileage intelligence, transfer friction, feature signals, and risk flags.

Ian Dikhtiar

Airbnb Scraper

scrapio/airbnb-scraper

This actor extracts Airbnb property data to help real estate investors and analysts evaluate short-term rental markets. Get details on nightly rates, occupancy signals, and listing density fast.

Scrapio

TrustMRR Scraper - Verified Revenue & AI Investment Analysis

buseta/trustmrr-scraper

Scrape verified startup revenue data from TrustMRR. Get MRR, growth rates, founder info, and marketplace listings. AI investment analysis scores each startup for acquisition potential. Filter by category, MRR range, and growth. Perfect for micro-PE, indie hackers, and startup investors.

buseta

LinkedIn Top Content & Top Voices Scraper

logiover/linkedin-top-content-scraper

Scrapes LinkedIn's public Top Content directory to extract curated high-engagement posts and Top Voice influencers across 40+ categories. Get post text, author profiles, follower counts, reaction metrics, and Top Voice badges. No login, no cookies, no account ban risk. $2 per 1,000 posts.

Logiover

AI News Scraper

buseta/ai-news-scraper

Most Comprehensive AI News Scraper - scrape news about AI from all over the internet. Get full news contents, summaries, images, and more. Last Update: Mar 22, 2026

buseta