Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key... features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️show more

Here is how it works:

Introducing OPEN, the first genre-defining AAA metaverse gaming experience with top-tier IP powered by web3 technology. Coming to @thereadyverse. #opensoon

@GoogleDeepMind @browser_use Try @nanobrowser_ai ! We’ve been supporting Gemini models since beginning!

@GoogleDeepMind @browser_use @nanobrowser_ai Cool. Does it work with chromium? or is it always a extension?

@GoogleDeepMind @browser_use I literally integrated same implementation using vertex ai for enterprise and won the hackathon award in my company . Here is the url

@GoogleDeepMind @browser_use Exploring the synergy between MCP and Function Calling in AI!

@GoogleDeepMind @browser_use Browsers obeying commands? 🤖 My vintage business books predicted *something* like this, just with more slide rules.

@GoogleDeepMind @browser_use But it needs api, no? how do you get its api? I can't get 2.5's api more than the free usage allows.

@GoogleDeepMind @browser_use That's cool

@GoogleDeepMind @browser_use Awesome. This is amazing and Gemini flash is the perfect model for this because of the low cost 💲