LaVague
StaleDescription
LaVague is a Large Action Model (LAM) framework for developing AI web agents, combining RAG techniques for natural-language-driven browser automation.
LaVague is a Large Action Model (LAM) framework for developing AI web agents, combining RAG techniques for natural-language-driven browser automation.
A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.
Notte is a framework for building web agents and deploying serverless browser automation functions, providing reliable browser infrastructure and web-aware agent capabilities.
An adaptive web scraping framework that intelligently handles anti-bot measures, from single requests to full-scale crawls, designed for AI agent data collection.
Open-sourced computer use agents that can operate on cross-platform environments including Windows, macOS, Ubuntu, and Android. ICLR 2026 Oral paper project.