gemini-browser-agent and gemini-computer-use
These are ecosystem siblings—one provides a Chrome extension interface for interactive browser control while the other offers a programmatic Playwright-based automation approach, serving different use cases (manual vs. scriptable) for the same underlying Gemini 2.5 Computer Use capability.
About gemini-browser-agent
pmbstyle/gemini-browser-agent
A browser agent with a Google Chrome extension that can work in your browser. Based on Google Gemini 2.5 computer use model.
This tool helps you automate repetitive online tasks by having a Google AI agent interact with your Chrome browser. You provide a goal in plain language, and the AI takes screenshots of your active tab, interprets them, and performs actions like clicking buttons or filling out forms directly in your browser. It's designed for anyone who needs to streamline web-based workflows without manual intervention.
About gemini-computer-use
pmbstyle/gemini-computer-use
A minimal browser automation agent using Google's Gemini 2.5 Computer Use Preview model and Playwright for web browser control.
This tool helps automate repetitive tasks on websites by using AI to "see" and interact with web pages just like a human. You provide a plain language instruction, and the system opens a web browser, navigates, clicks, types, and scrolls as needed. It's designed for anyone who spends a lot of time doing predictable actions online and wants to free up that time.
Scores updated daily from GitHub, PyPI, and npm data. How scores work