# QIN2DIM/hcaptcha-challenger

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

Repository: https://github.com/QIN2DIM/hcaptcha-challenger
Canonical: https://ross.abutalabs.com/products/hcaptcha-challenger
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: hcaptcha, hcaptcha-solver, yolo, playwright, clip, agent, gemini, llm, ai-agents, chatgpt, openai, captcha-solver, captcha, captcha-solving
Last push: 2026-08-15T02:53:15+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 64, longevity 100
- inputs: {"age_days": 1660, "days_push": 18, "days_rel": 241, "gap_med": 5, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2482, forks 446 (observed 2026-08-28T04:06:55.288413+00:00)

## What it is
A Python library that solves hCaptcha challenges using multimodal large language models and ONNX vision models (YOLO, CLIP, ResNet) integrated with Playwright browser automation. It implements an 'AI vs AI' approach without third-party anti-captcha services or userscripts.

## Use cases
- solve hcaptcha challenges automatically
- bypass hcaptcha in web scraping with playwright
- classify hcaptcha image challenges with yolo onnx models
- use gemini or gpt-4v to answer captcha image prompts
- automate hcaptcha image drag and drop challenges
- integrate captcha solving into python browser automation

## When to choose
- you need to automate interactions with sites protected by hCaptcha in Python
- you want a self-hosted solver using your own multimodal LLM or ONNX models
- you already use Playwright for browser automation and need captcha handling

## When to avoid
- you need a language other than Python
- you want a hosted captcha-solving API with no ML setup
- solving captchas violates the target site's terms of service or local law

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, agent-framework, web-scraping, llm-inference
- domain: artificial-intelligence, computer-vision, security
- platform: python, cross-platform
- tags: captcha-solver, hcaptcha, playwright, yolo, clip, multimodal-llm, browser-automation, automation

## Member repositories
- QIN2DIM/hcaptcha-challenger (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:55.288413+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:28:07.255399+00:00, confidence not recorded.
  - readme: https://github.com/QIN2DIM/hcaptcha-challenger (fetched 2026-08-28T04:06:55.288413+00:00, sha 649d12ff0732)
  - registry_pypi: https://pypi.org/pypi/hcaptcha-challenger/json (fetched 2026-08-29T10:10:14.565712+00:00, sha 0600077fb032)
- Data as of 2026-08-30T08:39:29.467469+00:00.