Features
World Model interprets objectives and page context into instructions
Action Engine compiles instructions into Selenium/Playwright code
Supports OpenAI, Azure, Anthropic, Gemini, Fireworks LLM backends
LaVague QA converts Gherkin specs into automated tests
Gradio interface for interactive agent demos
TokenCounter tool for tracking API costs
Headless and headed browser execution
Built-in contexts for easy configuration
Test runner for benchmarking agent performance
Logging and debugging tools
Chrome Extension driver for interactive use
Custom action support for extensibility
End-to-end examples for knowledge retrieval and data entry
Community-driven open-source development
Telemetry data collection for improving community datasets
Role-based agent assignment (PM, architect, engineer, QA)
Structured output generation (requirements, design, code)
Data Interpreter for data analysis tasks
SELA module for self-evolving agents
Multi-agent collaboration and workflow orchestration
Meta-programming support for custom agent behaviors
Modular and extensible architecture
Built-in demo projects and case studies
MIT License fully open-source
Flow orchestration for complex agent pipelines
Integration with GitHub Actions and CI/CD
Community-driven with GitHub and Discord
