recognizer

What it is and what it does

reCognizer is an AI-powered reCAPTCHA solver that uses YOLOv8 segmentation and CLIP vision models to recognize captcha images and generate solutions. It accepts images in multiple formats—file paths, bytes, or lists—and returns both recognized responses and coordinate data. The package integrates with Playwright for both synchronous and asynchronous browser automation, allowing you to embed captcha solving directly into web scraping or testing workflows.

The package is designed for developers who need to automate interactions with reCAPTCHA-protected sites. It depends on opencv-python for image processing, ultralytics for YOLOv8 models, transformers for CLIP, and playwright for browser control. The documentation explicitly notes that standard Playwright is easily detected by reCAPTCHA and recommends pairing this package with an undetected browser engine for consistent results.

Use it for:

• Automate testing of web applications protected by reCAPTCHA without manual intervention
• Build web scrapers that can bypass reCAPTCHA v2 checkbox challenges on target sites
• Integrate captcha solving into Playwright-based browser automation workflows for data collection
• Recognize and classify objects within captcha image grids as part of a larger automation pipeline
• Develop security research or penetration testing tools that need to handle reCAPTCHA barriers

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Solves reCAPTCHA challenges using AI-based image recognition, with support for direct API calls and integration with Playwright for browser automation.

Yes, if you need reCAPTCHA automation and accept the GPL v3 license obligations. The package is actively maintained, has low install friction, and integrates cleanly with Playwright. However, success depends heavily on using an undetected browser engine (not included); standard Playwright will likely fail. Verify that the package supports your specific reCAPTCHA version and that your use case complies with reCAPTCHA's terms of service.

Install

recognizer on PyPI

pip install recognizer

uv add recognizer

poetry add recognizer

Installing recognizer

Before you install

Low friction installation with a pure-Python wheel. Actively maintained as of 2026-03-29 with 252 repository stars. Requires six runtime dependencies including computer vision (opencv-python, ultralytics) and browser automation (playwright) libraries, which may add setup complexity.

License in practice

Licensed under GNU General Public License v3.0 (permissive treatment). Commercial use is allowed, but you must make source code, license, and copyright available to users. No liability or warranty is provided by the package.

Quickstart

from recognizer import Detector

detector = Detector()
task_type = "bicycle"
images = "recaptcha_image.png"
response, coordinates = detector.detect(task_type, images, area_captcha=False)

Requires Python >=3.8. For consistent reCAPTCHA solving, documentation recommends using an undetected browser engine like Botright; standard Playwright is easily detected by reCAPTCHA.

Verify before relying

• Actual success rate and reliability of captcha solving across different reCAPTCHA versions and configurations
• Whether the package works with reCAPTCHA v3 or only v2 checkbox/image challenges
• Performance characteristics and latency for typical captcha solving tasks
• Whether IP reputation and browser fingerprinting significantly impact solve success beyond the documented Botright recommendation

Package facts

Evidence: recognizer-1.4-py3-none-any.whl

Keywords: botright, playwright, browser, automation, fingerprints, fingerprinting, dataset, data, recaptcha, captcha

Tags

More Software Development packages

Further reading