AI-powered browser automation tool that extracts interactive web elements for AI agents. Features include HTML extraction, multi-tab management, element tracking, custom actions, self-correcting capabilities, and support for various language models.
Features
Vision + HTML Extraction
Combines visual understanding with HTML structure extraction for comprehensive web interaction.
Multi-tab Management
Automatically handles multiple browser tabs for complex workflows and parallel processing.
Element Tracking
Extracts clicked elements' XPaths and repeats exact LLM actions for consistent automation.
Custom Actions
Add custom actions like saving to files, database operations, notifications, or human input handling.
Self-correcting
Intelligent error handling and automatic recovery for robust automation workflows.
Any LLM Support
Compatible with any LangChain LLMs including GPT-4, Claude 3, and Llama 2.
WebVoyager Benchmark
Achieving a state-of-the-art performance with an 80% success rate across 586 diverse web tasks.
Open Source
Browser Use is fully open-source, providing transparency and the ability for others to modify and improve the software.
Model Adaptation
Adaptation of the existing WebVoyager codebase and integration with large language models like Langchain.
Custom Evaluation
Custom evaluation with various models, ensuring flexibility in assessing performance over time.