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
@ai_fn decorator for LLM-powered Python functions
@ai_classifier decorator for text classification
Structured data extraction via Pydantic models
Agent loops with tool calling and function calling
Built-in streaming (SSE) support
Async-first API for concurrent applications
Rate limiting and automatic retries
LLM response caching for performance
Concurrency control for workload management
CLI tool for monitoring and debugging
SQLite state store for persistence
OpenAI and Anthropic model support
Embeddings generation for semantic search
Local execution with no cloud dependency
Self-hosted deployable as a library
