$npx skillfedfor your agent

recognizer

🦉Gracefully face reCAPTCHA challenge with ultralytics YOLOv8-seg, CLIPs VIT-B/16 and CLIP-Seg/RD64. Implemented in playwright or an easy-to-use API.

With conditionsPyPI Software DevelopmentReleased Apr 2024111.8K downloads / moGNU General Public License v3.0Pure Python

Decision gist · record as of 2026-08-14

pure-Python wheel — recognizer-1.4-py3-none-any.whl
v1.4 · released 2024-04-10 · Python >=3.8 · 6 runtime deps: opencv-python, imageio, ultralytics, transformers, numpy, playwright

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

Before you install

  • Requires Python >=3.8.
  • For consistent reCAPTCHA solving, documentation recommends using an undetected browser engine like Botright; standard Playwright is easily detected by reCAPTCHA.
  • Low friction installation with a pure-Python wheel.

License · maintenance · safety

GNU General Public License v3.0 (permissive) — 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.

last release 2024-04-10 (856 days) · last repo commit 2026-03-29 · 252 stars

0 known vulnerabilities (OSV.dev, 2026-08-14) · 111,844 downloads/mo, #12,395 on PyPI

Verify before relying

from recognizer import Detector

detector = Detector()
task_type = "bicycle"
images = "recaptcha_image.png"
response, coordinates = detector.detect(task_type, images, area_captcha=False)
  • 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
Same gist for agents: .md · .json

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 on it.

With conditions

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

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.

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

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)

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

LicenseGNU General Public License v3.0 permissive
Python supportSupports the current Python release >=3.8
Install frictionLow. Pure-Python wheel
Runtime dependencies
6 packages
opencv-pythonimageioultralyticstransformersnumpyplaywright
MaintenanceActively maintained 856 days since the last release
Last repo commit
First released
Downloads111,844 / month, #12,395 on PyPI 30-day window, as of 2026-08-14
Known vulnerabilitiesNone known OSV.dev, checked 2026-08-14
Classifiers
License :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Topic :: Internet :: WWW/HTTP :: BrowsersTopic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules

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

Tags

Capabilities
recaptcha solvercaptcha recognition aiplaywright recaptcha automationyolov8 image detectionbrowser captcha bypassautomated captcha solvingrecaptcha v2 solver
Topics
captcha-solvingbrowser-automationcomputer-vision
PyPI keywords
botrightplaywrightbrowserautomationfingerprintsfingerprintingdatasetdatarecaptchacaptcha

Let your AI agent find packages like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.

wish › “recaptcha solver”

  • recognizerSolves reCAPTCHA challenges using AI-based image recognition, with…
  • 2captcha-pythonA Python client for the 2Captcha API that automates captcha solving…
  • anticaptchaofficialSolves CAPTCHAs and related challenges (image text, reCAPTCHA v2/v3,…

Give your agent the search over MCP, or paste the wish link into any chat.

More Software Development packages

typing-extensions Worth it
PyPI · Software Development · released Jul 2026

Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.

PSF-2.0pure Python · 3.9+
1.9Bdownloads / mo
numpy Worth it
PyPI · Software Development · released Aug 2026

NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.

BSD-3-Clause AND 0BSD AND MIT AND Zlib AND CC0-1.0compiled wheel · 3.12+
1.1Bdownloads / mo
fastapi Worth it
PyPI · Software Development · released Jul 2026

FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.

MITpure Python · 3.10+
568.6Mdownloads / mo
annotated-doc With conditions
PyPI · Software Development · released Jul 2026

Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.

MITpure Python · 3.9+
456.2Mdownloads / mo
typer Worth it
PyPI · Software Development · released Aug 2026

Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.

Install it if you are building CLIs in Python.

MITpure Python · 3.10+
369.3Mdownloads / mo
distlib With conditions
PyPI · Software Development · released Jun 2026

Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.

permissive licensepure Python
323.3Mdownloads / mo

See also tf-playwright-stealth · anticaptchaofficial · playwright · capsolver · 2captcha-python · django-simple-captcha · django-recaptcha · patchright · playwright-stealth · rebrowser-playwright

Further reading