A browser automation agent that prioritizes visual recognition over DOM-based selectors for web interaction. It enables LLMs to navigate and interact with websites as a human would through visual cues.
Tech Stack
TypeScriptAI, ML & Data
Why browser-agent?
• Resilient to DOM changes
• Supports complex visual interactions
• Vision-first architecture
Limitations
• Higher latency than DOM scripts
• Requires GPU for vision processing
• Experimental API stability
3/5/2026
Last Update
217
Forks
27
Issues
Apache-2.0
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to browser-agent instantly boosts your runway.
