webqa agent

WebQA Agent is an autonomous web browser agent designed to audit performance, functionality, and user experience (UX) for any web product. This tool is particularly useful for QA professionals and developers who need to ensure the quality and reliability of their web applications. Below is a comprehensive overview of its features, installation process, and usage guidelines.

Core Features

Overview

WebQA Agent is an autonomous web agent that conducts comprehensive testing of web products, covering various aspects such as functionality, performance, and user experience.

Feature Highlights

• AI-Powered Testing: WebQA Agent autonomously performs website testing, including page crawling, test case generation, and execution, achieving end-to-end functional test automation.
• Multi-Dimensional Test: The agent covers core testing scenarios, including functionality, performance, user experience, and security. It evaluates page load speed, design details, and links to ensure comprehensive system quality assurance.
• Precise Diagnostics: The agent performs deep testing in real browser environments and provides actionable optimization recommendations.
• Visual Reports: WebQA Agent generates detailed HTML test reports with a multi-dimensional visual presentation of results for easy analysis and tracking.

Installation & Configuration

One-Click Docker Setup

Before starting, ensure Docker is installed. If not, refer to the official installation guide. Follow these steps:

1. Download the configuration template:

mkdir -p config && curl -fsSL https://raw.githubusercontent.com/MigoXLab/webqa-agent/main/config/config.yaml.example -o config/config.yaml

2. Edit the configuration file to set target URL, API key, and other parameters.
3. One-click start:

curl -fsSL https://raw.githubusercontent.com/MigoXLab/webqa-agent/main/start.sh | bash

Source Installation

1. Clone the repository:

git clone https://github.com/MigoXLab/webqa-agent.gitcd webqa-agent

2. Install Python >= 3.10 and run the following commands:

pip install -r requirements.txtplaywright install

3. For performance testing, install Lighthouse (requires Node.js >= 18.0.0):

npm install

4. For security testing, install Nuclei:

# MacOSbrew install nuclei# For other systems, download the appropriate version from the link above# Update templates and verify installationnuclei -ut -v # Update Nuclei templatesnuclei -version # Verify successful installation

5. After configuringconfig/config.yaml, run:

python webqa-agent.py

Usage

Test Configuration

WebQA Agent uses YAML configuration for test parameters. Below is an example configuration:

target:url: https://example.com/ # Website URL to testdescription: example descriptiontest_config: # Test configurationfunction_test: # Functional testingenabled: Truetype: ai # default or aibusiness_objectives: example business objectives # Recommended to include test scope, e.g., test search functionalityux_test: # User experience testingenabled: Trueperformance_test: # Performance testingenabled: Falsesecurity_test: # Security testingenabled: Falsellm_config: # Vision model configuration, currently supports OpenAI SDK compatible format onlymodel: gpt-4.1 # Recommendedapi_key: your_api_keybase_url: https://api.example.com/v1browser_config:viewport: {"width": 1280, "height": 720}headless: False # Automatically overridden to True in Docker environmentlanguage: zh-CNcookies: []

Functional Testing Notes

• AI Mode: When specifying the number of test cases to generate in the configuration file, the system may re-plan based on actual testing conditions. This may result in the final number of executed test cases differing from the initial configuration to ensure testing accuracy and effectiveness.
• Default Mode: Thedefaultmode of functional testing primarily verifies whether UI element clicks execute successfully, including basic interactive functions like button clicks and link navigation.

User Experience Testing Notes

UX testing focuses on evaluating website interaction design, usability, and user-friendliness. The model output in the test results provides suggestions for improvement based on user experience best practices to guide development and design teams in optimization.

View Results

Test results will be generated in thereportsdirectory. Open the HTML report within the generated folder to view results.

Roadmap

1. Continuous optimization of AI functional testing: Improve coverage and accuracy
2. Functional traversal and page validation: Verify business logic correctness and data integrity
3. Interaction and visualization: Test case visualization and local service real-time reasoning process display
4. Capability expansion: Multi-model integration and more evaluation dimensions

Open Source License

This project is licensed under the .

About

WebQA Agent is an autonomous web browser agent that audits performance, functionality, and UX for QA and vibe-coding creators.