# GcrawlAI

> Open-source web scraping and crawling API that converts websites into clean, LLM-ready Markdown or structured JSON.

GcrawlAI is a web scraping API from Gramosoft Private Limited that turns web pages into LLM-ready Markdown, HTML, screenshots, SEO metadata, or image lists. It is aimed at AI agents, RAG pipelines, and data teams, and it offers a hosted cloud API alongside an MIT-licensed engine on GitHub.

## What It Is

GcrawlAI is an API-first web data extraction service. A developer sends a URL to an endpoint and receives cleaned content in selectable formats. The vendor says JavaScript rendering, anti-bot stealth, and proxies are included in every request. The product exposes scrape, crawl, map, batch, screenshot, and search endpoints, plus an offline bundle generator and zero-code extractors for sites such as Amazon, Walmart, Flipkart, Google Search, and the Apple App Store.

## How the Workflow Runs

The scrape endpoint accepts a URL with options for residential geo-targeting, auto-scroll for lazy-loaded content, a timeout, and per-format settings for Markdown, HTML, SEO tags, and images. Crawl follows a domain's subpages, map lists a site's URLs, and batch scrapes multiple URLs in parallel. Search runs a text query against the web, and Smart Answer lets users ask questions about a page using an LLM. The Offline Bundle feature packages a page's HTML, CSS, JS, images, and fonts into a ZIP archive.

## Anti-Bot Handling and Billing Model

The vendor describes a three-tier stealth pipeline that escalates automatically from a fast fingerprint-safe engine, to full browser cloaking, to hardened stealth with residential proxy rotation for protections such as Cloudflare Turnstile, DataDome, and PerimeterX. GcrawlAI states it uses request-based billing with no credit multipliers and does not count failed requests.

## Use Cases and Integrations

GcrawlAI lists use cases including crawling documentation into Markdown for RAG, price and market monitoring with geotargeting, lead enrichment, and research agents that chain search into scrape. It states integration with Claude, GPT, and Gemini agents via REST API, SDKs, and an MCP server, and with LangChain and LlamaIndex. Official Python and Node.js SDKs are mentioned, and the engine can be self-hosted.

## Features
- Scrape, crawl, map, batch, screenshot and search endpoints
- Clean Markdown, HTML, SEO metadata and image extraction
- JavaScript rendering included in every request
- Three-tier automatic anti-bot stealth with residential proxies
- Country-level geotargeting
- Zero-code extractors for structured JSON from popular sites
- Offline Bundle ZIP generator
- Smart Answer for questions about a webpage
- Open-source MIT-licensed engine with self-hosting
- MCP server for AI agents
- Python and Node.js SDKs
- Request-based billing with no credit multipliers

## Integrations
LangChain, LlamaIndex, MCP, Claude, GPT, Gemini, pgvector, GdoczAI, GsearchAI

## Platforms
IOS, WEB, API, DEVELOPER_SDK

## Pricing
Open Source, Free tier available

## Version
v1.0

## Links
- Website: https://gcrawlai.com/
- Documentation: https://gcrawlai.com/docs
- Repository: https://github.com/GramosoftAI/GcrawlAI
- EveryDev.ai: https://www.everydev.ai/tools/gcrawlai