# AI Tools & Models Intelligence (`swerve/aitools-intel-scraper`) Actor

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.

- **URL**: https://apify.com/swerve/aitools-intel-scraper.md
- **Developed by:** [Swerve](https://apify.com/swerve) (community)
- **Categories:** AI, Developer tools, Lead generation
- **Stats:** 4 total users, 0 monthly users, 100.0% runs succeeded, 1 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.00 / 1,000 results

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

## AI Tools & Models Intelligence

Aggregate AI tool, model, dataset, and space data from two of the largest open catalogs:

- **[Futurepedia](https://www.futurepedia.io)** — the largest curated directory of AI tools, with 29 categories (chatbots, code assistants, image generation, video, marketing, productivity, AI agents, etc.)
- **[Hugging Face Hub](https://huggingface.co)** — the canonical registry for open-source AI models, datasets, and hosted demos (Spaces)

Pick a source, optionally narrow by category and keyword, and get a normalized dataset across all four endpoints.

### 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:**

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

**All text-generation LLMs sorted by downloads:**

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

**AI chatbots on Futurepedia:**

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

**All AI agent tools across Futurepedia:**

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

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

```json
{
  "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.

# Actor input Schema

## `source` (type: `string`):

Which catalog to pull from. Hugging Face is free and fast. Futurepedia is the largest curated directory of AI tools (uses residential proxy).

## `category` (type: `string`):

Source-specific filter. Leave empty to pull all.

Futurepedia slugs: chatbots, code-assistant, image, video, audio, productivity, ai-agents, marketing, business, writing-generators, design-generators, research-assistant, customer-support, finance, sales, social-media, education-assistant, real-estate, legal, health, art, gaming, lifestyle, translation, avatars, data-analysis, human-resources, religion, fun-tools.

Hugging Face Models examples: text-generation, image-classification, automatic-speech-recognition, text-to-image, image-to-text.

Hugging Face Datasets examples: task\_categories:text-classification, task\_categories:question-answering.

Hugging Face Spaces examples: gradio, streamlit, docker, static.

## `keyword` (type: `string`):

Free-text keyword. Examples: llama, image, chatbot, whisper, gpt. For Hugging Face, sent server-side via ?search=. For Futurepedia, applied client-side against title + tags. All tokens must appear in the title or tags (no description-based false positives).

## `sortBy` (type: `string`):

Hugging Face sort order. Ignored for Futurepedia (uses the site's default ordering per category).

## `maxItems` (type: `integer`):

Optional cap on how many items to return. Leave this blank to scrape ALL matching results (recommended). Big sources like Hugging Face and Futurepedia can return thousands of items, so a blank value may run for a while and cost more per result. Set a number only if you want to limit the run, for example 15 for a quick sample or 500 to bound cost.

## Actor input object example

```json
{
  "source": "huggingface_models",
  "sortBy": "trending"
}
```

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("swerve/aitools-intel-scraper").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("swerve/aitools-intel-scraper").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call swerve/aitools-intel-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,swerve/aitools-intel-scraper"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/9V6PvA6rmHsgDV7GO/builds/9NwaRQytNVho1KPpy/openapi.json