ghostfetch

name	ghostfetch
description	Stealthy web fetching for AI agents. Bypasses blocks on X.com and other sites to return clean Markdown.
homepage	https://github.com/iArsalanshah/GhostFetch
metadata	{"openclaw":{"emoji":"👻","requires":{"bins":["python3"]}}}

GhostFetch

GhostFetch is a stealthy headless browser service designed specifically for AI agents. It bypasses anti-bot protections (like those on X/Twitter) and returns clean, LLM-friendly Markdown.

Installation

GhostFetch is already in your workspace at the repo root. To use it as a skill, ensure the Python environment is set up from the repo directory:

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
playwright install chromium

Usage

You can use GhostFetch in two ways:

1. Direct CLI (Recommended for quick fetches)

Use the scraper module directly to get Markdown from a URL.

python3 -m src.core.scraper "https://x.com/user/status/123"

2. API Mode (Background service)

Start the FastAPI server to handle concurrent jobs and webhooks.

# Start server
python3 main.py

# Fetch via API
curl -X POST "http://localhost:8000/fetch" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://x.com/user/status/123"}'

Stealth Features

• Ghost Protocol: Advanced proxy rotation and hardware fingerprinting.
• X.com Optimized: Specific logic to wait for dynamic tweet content.
• LLM Ready: Automatic HTML-to-Markdown conversion.

---

Created by Syed Arsalan Shah (@iArsalanshah)