Hercules is the world's first open-source testing agent, enabling UI, API, Security, Accessibility, and Visual validations without code or maintenance. It transforms simple Gherkin steps into fully automated end-to-end tests, making testing effortless and efficient.
One-Minute Overview#
Hercules is a revolutionary open-source testing agent that transforms simple Gherkin steps into fully automated end-to-end tests without writing any code. Whether you're working with complex platforms like Salesforce or running tests in your CI/CD pipeline, Hercules adapts to your needs and handles all the details. It provides every team with a "testing hero," democratizing high-quality test automation that's no longer limited to elite teams.
Core Value: Makes testing simple and reliable without requiring coding skills to create and maintain complex test suites.
Getting Started#
Installation Difficulty: Medium - Requires Python environment and some configuration
# Install Hercules
pip install testzeus-hercules
# Install Playwright and its dependencies
playwright install --with-deps
Is this suitable for me?
- ✅ Complex Web Applications: Especially those with frequent changes and complex features
- ✅ CI/CD Integration: Can seamlessly integrate into existing development workflows
- ✅ Cross-Platform Testing: Supports hard-to-test platforms like Salesforce
- ❌ Simple Static Websites: May be overkill for very simple websites
Core Capabilities#
1. Codeless Test Execution - Solving test script maintenance challenges#
- Transforms simple Gherkin steps into fully automated end-to-end tests without writing any code Actual Value: Significantly reduces test maintenance costs and enables non-technical staff to create test cases
2. Multi-Type Test Support - Solving comprehensive quality assurance needs#
- Supports various testing types including UI, API, Security, Accessibility, and Visual validations Actual Value: One-stop solution for all quality testing needs, eliminating the need for multiple testing tools
3. Natural Language Testing - Solving technical barrier issues#
- Allows writing test cases in natural language, which are then converted to executable tests by AI Actual Value: Enables business analysts and product managers to participate in test case creation
4. Python Sandbox Execution - Solving complex testing scenario requirements#
- Execute custom Python scripts directly from Gherkin tests with full Playwright API access Actual Value: Handles complex business logic and advanced selector strategies for more flexible test automation
5. Multi-AI Model Support - Solving cost and flexibility needs#
- Supports multiple AI models including OpenAI, Anthropic, Gemini, etc., allowing selection based on needs Actual Value: Optimizes costs while maintaining test quality, adapting to different budgets and requirements
Technology Stack and Integration#
Development Language: Python Key Dependencies: Playwright, various AI model APIs Integration Method: CLI tool, Python library
Maintenance Status#
- Development Activity: High - Project has continuous updates and feature enhancements
- Recent Updates: Recent feature additions including Python sandbox execution and multi-AI model support
- Community Response: Active maintenance with Slack community, comprehensive video tutorials, and documentation
Documentation and Learning Resources#
- Documentation Quality: Comprehensive - Provides detailed installation guides, configuration options, and API documentation
- Official Documentation: README and Run Guide in GitHub repository
- Sample Code: Complete test case examples and Python script samples provided
Usage Guide#
Basic Command#
testzeus-hercules --input-file opt/input/test.feature --output-path opt/output --test-data-path opt/test_data --llm-model gpt-4o --llm-model-api-key sk-proj-xxxxxxx
Key Parameters#
--input-file: Path to Gherkin feature file--output-path: Output directory path (contains results and reports)--test-data-path: Test data directory path--project-base: Project base directory path (optional)--llm-model: Name of AI model to use (recommended gpt-4o)--llm-model-api-key: API key for the AI model
Environment Variables#
BROWSER_TYPE: Browser type (chromium, firefox, webkit)HEADLESS: Run in headless mode (true/false)BROWSER_RESOLUTION: Browser window resolution (format: width,height)RECORD_VIDEO: Record test execution videos (true/false)TAKE_SCREENSHOTS: Take screenshots during tests (true/false)