adityasasidhar/browsercontrol
BrowserControl is an MCP server that gives your AI agent full browser access with a vision-first approach inspired by Google's AntiGravity IDE.
This project empowers your AI assistant, like Claude or Gemini, to fully interact with websites just like a human user would. Instead of complex coding, your AI sees numbered, interactive elements on a webpage screenshot and can simply 'click 7' or 'type in 3'. This allows AI agents to perform tasks such as signing into accounts, navigating multi-step forms, or gathering information across dynamic web pages.
Available on PyPI.
Use this if you want your AI agent to browse and interact with websites visually, rather than relying on brittle code selectors.
Not ideal if your automation needs are limited to simple API calls or static content scraping that doesn't require dynamic interaction or 'seeing' the page.
Stars
7
Forks
2
Language
Python
License
MIT
Category
Last pushed
Mar 11, 2026
Monthly downloads
73
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/adityasasidhar/browsercontrol"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
alibaba/page-agent
JavaScript in-page GUI agent. Control web interfaces with natural language.
steel-dev/steel-browser
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser...
violettoolssite/CFspider
Cloudflare Workers 代理 IP 池，VLESS 动态 IP，内置 AI 智能浏览器支持自然语言控制
4ier/neo
Turn any web app into an API. Chrome extension captures browser traffic, auto-generates schemas,...
actionbook/actionbook
Browser action engine for AI agents. 10× faster, resilient by design.