Autonomous Web Browsing With Chrome Extension

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

Unique: Uses a Chrome extension for real browser automation (not headless) combined with vision/OCR for page understanding, enabling interaction with JavaScript-heavy sites and visual elements, rather than pure DOM-based automation or API-only approaches

vs others: More reliable than pure DOM scraping for modern SPAs and visual interactions, but slower and less scalable than API-based automation; better for human-like browsing patterns but requires more infrastructure than Selenium/Playwright