Agent Computer avatar

Agent Computer

Official

@agentcomputerai

0Followers
|
7Public Repos
|
33Published Skills

Offers specialized web extraction modules for bypassing anti-bot protections and parsing structured data from major e-commerce and research platforms.

Skills Distribution
DomainData Systems...Web-Scraping-Engin.. (40%)Anti-Bot-Evasion (30%)Structured-Data-Pa.. (30%)

Agent Skills by Agent Computer

Showing 33 vetted skills indexed across 1 GitHub repositories.

AgentComputerAIAgentComputerAI
5

proxy

Route Puppeteer web scraping through authenticated residential, datacenter, or mobile proxies.

Official
Advanced
AgentComputerAIAgentComputerAI
5

2captcha

Solve reCAPTCHA, hCaptcha, and image CAPTCHAs for Puppeteer workflows.

Official
Advanced
AgentComputerAIAgentComputerAI
5

agentmail

Create and manage email inboxes for AI agents via HTTP, webhook, and WebSocket integrations.

Official
Advanced
AgentComputerAIAgentComputerAI
5

contributing

Guide contributors through pull request submission and torch skill authoring workflows.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

camoufox

Scrape websites headlessly with a fingerprint-spoofing Firefox fork via Playwright-core.

Official
Advanced
AgentComputerAIAgentComputerAI
5

scrape

Scrape websites to extract structured data while handling anti-bot protections.

Official
Advanced
AgentComputerAIAgentComputerAI
5

reverse-engineer

Reverse-engineer hidden internal APIs and encrypted data from target websites.

Official
Advanced
AgentComputerAIAgentComputerAI
5

ubereats

Scrapes Uber Eats category pages for store listings using curl and cheerio.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

hackernews

Scrapes news.ycombinator.com listing pages into structured JSON story data.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

pypi

Extract PyPI package listings and metadata via RSS feeds and JSON API.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

costco

Extract Costco product listings and metadata via the public catalog search API.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

wikipedia

Scrape Wikipedia articles and extract text, headings, references, and categories.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

airbnb

Recovers user passwords and decrypts them for Windows (via UAC) and Linux (via JVM).

Official
Intermediate
AgentComputerAIAgentComputerAI
5

amazon

Extract Amazon search result data via a live Chrome session.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

homedepot

Scrape HomeDepot search pages via Chrome debugging port and parse product data.

Official
Advanced
AgentComputerAIAgentComputerAI
5

booking

Scrape Booking.com hotel listings and prices via a Chrome debugger connection.

Official
Advanced
AgentComputerAIAgentComputerAI
5

ikea

Scrape IKEA category pages via Chrome debug port and parse product cards with cheerio.

Official
Advanced
AgentComputerAIAgentComputerAI
5

target

Fetch Target.com product listings from the public redsky.target.com API.

Official
Intermediate
AgentComputerAIAgentComputerAI
5

doordash

Scrape DoorDash deals by bypassing Cloudflare and parsing server-rendered HTML.

Official
Advanced
AgentComputerAIAgentComputerAI
5

producthunt

Extracts structured metadata from Product Hunt homepage and leaderboard pages.

Official
Advanced
AgentComputerAIAgentComputerAI
5

yelp

Scrape Yelp search pages via Chrome CDP to extract business listings.

Official
Advanced
AgentComputerAIAgentComputerAI
5

etsy

Scrape Etsy search pages and extract listing data via Chrome debug port.

Official
Advanced
AgentComputerAIAgentComputerAI
5

ebay

Extract structured listing data from eBay search result pages.

Official
Advanced
AgentComputerAIAgentComputerAI
5

walmart

Scrape Walmart product listings via Chrome and parse __NEXT_DATA__ JSON.

Official
Advanced

Frequently Asked Questions About Agent Computer

FAQPage Schema
What specific data extraction tasks are supported?

These modules enable the extraction of structured product listings, metadata, and search results from platforms like Amazon, Walmart, Zillow, and DigiKey. They handle complex tasks such as parsing server-rendered HTML, navigating pagination, and deserializing internal JSON state objects like __NEXT_DATA__ into clean, usable records.

Which technical personas benefit from these modules?

Data engineers, market researchers, and software developers building competitive intelligence platforms or price-tracking services will find these modules effective. They are designed for those requiring reliable, high-frequency data ingestion from websites that employ aggressive anti-bot measures and dynamic content rendering.

What are the primary dependencies for runtime execution?

Execution requires a Node.js environment with Puppeteer or Playwright-core installed to manage headless browser sessions. Additionally, users must configure proxy providers for residential or datacenter IP rotation and integrate CAPTCHA-solving services to maintain connectivity when interacting with protected target domains.