camoufoxvsskyvern

MPL-2.0 244 3 7,089

1.0 million (month) Mar 01 2024 0.4.11(2025-01-29 09:33:18 ago)

21,046 17 148 AGPL-3.0

Feb 01 2024 250.9 thousand (month) 1.0.29(2026-04-02 14:42:44 ago)

Camoufox is an anti-detect browser built on Firefox, designed specifically for web scraping and browser automation while evading bot detection systems. Unlike Chrome-based anti-detect solutions, Camoufox uses a patched version of Firefox with over 100 modifications to prevent fingerprinting and detection.

Key features include:

Firefox-based stealth Uses Firefox instead of Chrome, which has different fingerprinting characteristics and is less commonly targeted by anti-bot systems. The browser is patched at the C++ level to prevent JavaScript-based fingerprint leaks.
Realistic fingerprints Generates and applies realistic browser fingerprints including screen resolution, WebGL renderer, fonts, and other browser properties that match real user configurations.
Playwright integration Works seamlessly with Playwright for Python, providing the familiar Playwright API while running through the stealth-patched Firefox instance.
Proxy support Built-in proxy support with authentication, including residential proxy rotation.
Geolocation spoofing Can spoof browser geolocation to match proxy IP location for consistent fingerprints.
Human-like behavior Includes utilities for adding human-like mouse movements and typing patterns.

Camoufox is particularly effective against sophisticated anti-bot systems that detect Chrome-based automation tools. By using Firefox as the base, it avoids many Chrome-specific detection vectors while the deep browser patches prevent general fingerprinting techniques.

Skyvern is an AI-powered browser automation tool that uses large language models (LLMs) and computer vision to interact with websites. Instead of relying on DOM selectors, Skyvern takes screenshots of web pages and uses visual understanding to identify and interact with elements, making it highly resilient to website changes.

Key features include:

Vision-based interaction Uses screenshots and computer vision (multimodal LLMs) to understand page layout and identify interactive elements visually, rather than through DOM inspection alone.
No selectors needed Describe tasks in natural language and Skyvern figures out what to click, type, and navigate without CSS selectors or XPath.
Complex workflow automation Can handle multi-step workflows like form filling, navigation through menus, file uploads, and multi-page processes.
Self-correcting When actions fail, Skyvern can analyze the resulting page state and adjust its approach, recovering from errors autonomously.
API-first design Provides a REST API for triggering and managing automation tasks programmatically.
Open source with cloud option Core engine is open source and can be self-hosted. Also available as a managed cloud service.

Skyvern is particularly effective for automating tasks on websites with complex or dynamic UIs where traditional selector-based automation breaks frequently. It achieved 85.85% accuracy on the WebVoyager benchmark.

Highlights

anti-detectstealth

ai-powerednatural-languageanti-detect

Example Use

```python from camoufox.sync_api import Camoufox # Launch stealth Firefox browser with Camoufox(headless=True) as browser: page = browser.new_page() # Navigate - the browser appears as a real Firefox user page.goto("https://example.com") # Use standard Playwright API for interaction page.fill("input[name='search']", "web scraping") page.click("button[type='submit']") # Extract data results = page.query_selector_all(".result") for result in results: title = result.query_selector("h3").text_content() print(title) # With proxy and custom fingerprint from camoufox.sync_api import Camoufox with Camoufox( headless=True, proxy={"server": "http://proxy.example.com:8080"}, geoip=True, # auto-match geolocation to proxy IP ) as browser: page = browser.new_page() page.goto("https://example.com") print(page.content()) ```

```python import requests # Skyvern runs as a service - interact via REST API SKYVERN_API = "http://localhost:8000/api/v1" # Create a task with natural language instructions task = requests.post( f"{SKYVERN_API}/tasks", json={ "url": "https://example.com/contact", "navigation_goal": "Fill out the contact form with test data and submit it", "data_extraction_goal": "Extract the confirmation message after submission", "navigation_payload": { "name": "John Doe", "email": "john@example.com", "message": "Hello, this is a test message", }, }, ).json() task_id = task["task_id"] # Check task status result = requests.get(f"{SKYVERN_API}/tasks/{task_id}").json() print(result["status"]) # "completed" print(result["extracted_information"]) # confirmation message ```