Pricing

from $0.01 / actor start

Hyper Reader

High-fidelity web extraction for AI agents. Clean Markdown optimized for Claude, GPT-4 & Gemini. 3-level stealth, Vision screenshots, Deep Read link following. Standby Mode for 1-second responses.

Pricing

from $0.01 / actor start

Rating

0.0

(0)

Developer

Jason Pellerin

Actor stats

Bookmarked

Total users

Monthly active users

2 months ago

Last modified

Categories

Agents

Developer tools

Target URL

url

Optional

The web page URL to extract content from.

Type:string

Multiple URLs

urls

Optional

Extract from multiple URLs at once (one per line). Takes precedence over single URL.

Type:string[]

Agent Optimization

agentPreset

Optional

Optimize output format for your target AI agent.

Type:string

Default:Claude

Options:

ClaudeGPT-4GeminiSearchGPTRaw

Output Format

outputFormat

Optional

The format of the extracted content.

Type:string

Default:markdown

Options:

markdownjsonhtml_cleaned

Stealth Level

stealthLevel

Optional

Anti-bot protection level. 1=Basic, 2=Standard, 3=Elite (heavy protection).

Type:integer

Minimum:1

Maximum:3

Default:2

Capture Screenshot for Vision

useVision

Optional

Capture a 1280x720 screenshot for Vision model analysis.

Type:boolean

Default:false

Deep Read Depth

deepReadDepth

Optional

Follow internal links to gather more context. 0 = single page only.

Type:integer

Minimum:0

Maximum:3

Default:0

Deep Read Max Pages

deepReadMaxPages

Optional

Maximum number of pages to extract when using Deep Read.

Type:integer

Minimum:1

Maximum:50

Default:10

Wait for Selector

waitForSelector

Optional

CSS selector to wait for before extracting (for JS-heavy pages).

Type:string

Wait Timeout (ms)

waitForTimeout

Optional

Maximum time to wait for page load.

Type:integer

Minimum:1000

Maximum:60000

Default:30000

Exclude Selectors

excludeSelectors

Optional

CSS selectors to remove before extraction (comma-separated).

Type:string

Include Metadata

includeMetadata

Optional

Include title, author, date, and other metadata in output.

Type:boolean

Default:true

Preserve Links

includeLinks

Optional

Keep hyperlinks in Markdown output.

Type:boolean

Default:true

Include Image URLs

includeImages

Optional

Include image URLs in Markdown output.

Type:boolean

Default:false

Max Content Length

maxContentLength

Optional

Truncate content if it exceeds this character count. 0 = no limit.

Type:integer

Minimum:0

Default:0

Proxy Configuration

proxyConfiguration

Optional

Configure proxy for requests. Leave empty to use Apify's automatic proxy.

Type:object

Default:

{
  "useApifyProxy": true,
  "apifyProxyGroups": [
    "RESIDENTIAL"
  ]
}

Crawl4ai To Markdown Pro2

juryless_rainbow/crawl4ai-to-markdown-pro2

A high-performance web-to-markdown crawler for AI agents, optimized for LLM data extraction using Crawl4AI. Features stealth browsing and high-fidelity content extraction.

aaron jungs

Reader Mode

maged120/reader-mode

Maged

Deep Research Agent (Brave + Gemini 3.1/GPT-5.1/Opus4.6)

visita/deep-research-agent

🦁 Autonomous research assistant. Uses Brave Search + AI (Gemini 3.1/GPT-5.1/Opus4.6) to search, scrape, and synthesize the web into professional, fully cited reports. 📄 Features instant HTML/Markdown export and massive context windows. Perfect for market intelligence, academic research, & briefs.

Visita Intelligence

Crawl4ai

kael_odin/crawl4ai

Extract page content (markdown/HTML/text), metadata, and link stats. Uses crawl4ai.

Kael Odin

Web Scraper For Llms

abotapi/web-scraper-for-llms

Stealth web scraping engine built for LLMs. Converts any web page to clean markdown or HTML

AbotAPI

Stealth Scraper

shvmgrx/stealth-scraper

Shivam Goraksha

The Perfect Prompt Generator

anointment/the-perfect-prompt-generator

Stop getting average results from AI. Input a simple idea, and this Elite Actor engineers a "Mega-Prompt" optimized for GPT-4, Claude 3, and Gemini. Includes persona, constraints, and structural logic.

Anointment

AI Web Crawler

hounderd/ai-web-crawler

Crawl websites and extract clean, LLM-ready markdown content with stealth browser rendering, anti-bot hardening, smart content filtering, and structured metadata extraction. Built for RAG pipelines, AI agents, and data workflows.

Hounderd

Best Web Scraper API

crawlkit/crawlkit-scrape-api

Scrape any website and get clean markdown, HTML, metadata and links. Powered by CrawlKit.sh - supports stealth mode for anti-bot protection.

Crawlkit

📱 Social MCP — AI Content & Media Search

nexgendata/social-content-mcp-server

MCP server for AI agents to search Dev.to, Steam, podcasts & Eventbrite. Connect Claude, GPT or any AI to social platforms. 4 tools for content intelligence.