Write browser tests in natural language, built on pytest and allure.

🤖 AgentiTest: Agentic Test Automation

This framework uses an LLM to automate browser testing through high-level, natural language commands. It's designed to be a flexible and developer-friendly tool for creating robust and maintainable browser tests.

🛠️ Tech Stack

• browser-use: Translates natural language into browser actions with an agent.
• pytest: A framework for structuring and running tests.
• Allure Report: For creating interactive and detailed test reports.

✨ Key Features

• Natural Language Tests: Write tests using descriptive, natural language tasks instead of brittle selectors.
• Adaptable Logic: The core testing logic is designed to be easily adapted for any website.
• Insightful Reports: Allure reports provide screenshots, agent actions, and AI "thoughts" for each step, giving you a clear view into the test execution.
• Environment Documentation: Key details about the test environment—such as the OS, Python version, and browser version—are automatically included in the Allure report for better debugging and context.
• Customizable Browser Settings: The framework allows for detailed configuration of browser settings. For more information, see the Browser Settings documentation.
• Example Implementation: test_community_website.py provides a practical example of how to write a test suite.

⚙️ How It Works

The framework's structure is designed for clarity and scalability, separating shared logic from individual tests. It's composed of two main parts:

• A common file (conftest.py): This central file contains pytest fixtures for setting up the browser and the LLM, along with a reusable run_agent_task helper function that executes test steps.