hcaptcha-challenger
🥂 Gracefully face hCaptcha challenge with multimodal large language model.
What is hcaptcha-challenger?
🥂 Gracefully face hCaptcha challenge with multimodal large language model.
Overview of hcaptcha-challenger
What it is
hCaptcha Challenger is an open-source tool that uses multimodal large language models to solve hCaptcha challenges. It does not rely on Tampermonkey scripts or third-party anti-captcha services. The project implements interfaces to enable AI versus AI solving of captchas.
Key features
- Supports multiple challenge types: image_label_binary, image_label_area_select (point and bounding box), image_label_multiple_choice, and image_drag_drop.
- Pluggable resources include ResNet ONNX classification, YOLOv8 ONNX detection and segmentation, ViT ONNX zero-shot motion, and Spatial Chain-of-Thought.
- Advanced tasks include Rank.Strategy (nested-model-zoo), self-supervised challenge (CLIP-ViT), and Agentic Workflow (AIOps Multimodal Large language model).
- Workflow tasks cover sentinel, collector, dataset version control and annotation, model training/validation (ResNet, YOLOv8), model upload/upgrade, and public dataset archiving.
- Does not use any Tampermonkey script or third-party anti-captcha service.
Use cases
Automating hCaptcha solving for web automation tasks, testing captcha resistance of AI models, and research in multimodal AI vs AI captcha solving.
Getting started
See the repository README for installation and quick-start instructions.
License and pricing
Licensed under GPL-3.0. It is open source and free.
Based on the project's public README and repository metadata.