Open Source AI Models Tracker avatar

Open Source AI Models Tracker

Pricing

from $0.01 / 1,000 results

Go to Apify Store
Open Source AI Models Tracker

Open Source AI Models Tracker

Track the latest open-source AI models from popular repositories like Hugging Face and GitHub. Collect model names, organizations, descriptions, tags, licenses, popularity metrics, URLs, and timestamps. Export structured results to JSON, CSV, Excel, or XML for analysis and automation.

Pricing

from $0.01 / 1,000 results

Rating

0.0

(0)

Developer

Biddut Hossain

Biddut Hossain

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

2 days ago

Last modified

Share

Track the latest open-source AI models from popular repositories such as Hugging Face and GitHub. This Apify actor collects structured metadata about AI models and exports the results for analysis, monitoring, and automation.

Features

  • Track open-source AI models from multiple sources
  • Collect model names and organizations
  • Extract descriptions and tags
  • Capture license information
  • Record popularity metrics when available
  • Export results to the Apify dataset
  • Download data as JSON, CSV, Excel, XML, or HTML
  • Easy integration with Apify schedules and webhooks

Input

Example input:

{
"sources": [
"https://huggingface.co/models",
"https://github.com/trending"
],
"maxItems": 50
}

Input Parameters

ParameterTypeDescription
sourcesArrayList of source URLs to monitor
maxItemsIntegerMaximum number of models to collect

Output

Each dataset item contains fields similar to:

{
"modelName": "Example Model",
"organization": "Example Organization",
"description": "Example description",
"tags": [
"llm",
"text-generation"
],
"downloads": 125000,
"likes": 3200,
"license": "apache-2.0",
"source": "Hugging Face",
"url": "https://huggingface.co/example/model",
"scrapedAt": "2026-07-16T00:00:00Z"
}

Project Structure

.actor/
src/
main.py
tracker.py
requirements.txt
README.md

Workflow

  1. Read actor input
  2. Load source URLs
  3. Download each page
  4. Detect the source platform
  5. Extract model information
  6. Normalize the data
  7. Save results to the Apify dataset

Use Cases

  • Monitor newly released AI models
  • Research open-source LLMs
  • Build AI model databases
  • Compare model popularity
  • Track licensing information
  • Feed AI dashboards
  • Automation with Apify webhooks
  • Market and technology research

Requirements

  • Python
  • Apify SDK
  • httpx
  • BeautifulSoup4
  • lxml

Notes

  • Public pages only are scraped.
  • Available metadata depends on the source website.
  • Websites may change their HTML structure over time, requiring parser updates.

License

MIT License