Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Project Mariner: an agent that helps you accomplish complex tasks in your browser 💻✨It’s a research prototype built with Gemini 2.0. Learn more:

Google Labs

210,189 subscribers

101,032 views • 1 year ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

labs.google1 year ago

Project Mariner leverages Gemini 2.0's advanced capabilities to understand complex instructions, reason, and take action across websites. 🧠🌐 It achieves an 83.5% score on the WebVoyager benchmark acting as a single agent, demonstrating its proficiency in real-world web tasks.

labs.google1 year ago

Project Mariner is currently available to a small group of trusted testers to start using as an experimental Chrome extension. Learn more at

Wasiu1 year ago

You guys are moving too slow. Open this up for everyone to use. Claude is beating you to the punch

Suchintan Singh1 year ago

If anyone is interested in an open source version of this check out Skyvern!

George1 year ago

@NewsFromGoogle

Muhamed Bright Kasule1 year ago

Cool. Just a thought: it would be even better if the agent can take the task completed (email addresses) and paste them into sheets, this way more time and energy is saved by the user. End-to-end task completion. 😊

Crypto Révolution 🇫🇷1 year ago

Did you know that either you've one employee who leak the entire Project Mariner and rebuilt it by its own months ago? or you've just decide to make an exact copy-cat of DoBrowser from @sawyerhood 🧐 or is it a pure coincidence?? 🤭

⟁ndrew V1 year ago

Love love love this. I'm all in on testing and giving this a spin. So excited about the opportunities this might unlock.

E Schneider1 year ago

What kind of tasks do you envision Project Mariner automating in the browser? Could this be a game-changer for productivity?

Duke 'Burrito Haver' Zero1 year ago

oh wow that's really cool i can't wait for you guys to never release it and then fob it off on Apache or something

Related Videos

What could the future of human-agent interaction look like in your browser? 🌐 Project Mariner is a research prototype built with Gemini 2.0 that’s able to research information and carry out tasks directed by you through an experimental Chrome extension. See it in action ↓

What could the future of human-agent interaction look like in your browser? 🌐 Project Mariner is a research prototype built with Gemini 2.0 that’s able to research information and carry out tasks directed by you through an experimental Chrome extension. See it in action ↓

Google DeepMind

71,263 views • 1 year ago

Introducing Gemini Spark ✨ a 24/7 personal AI agent that helps you navigate your digital life. Set recurring tasks, teach it new skills and create complete workflows. #GoogleIO

Introducing Gemini Spark ✨ a 24/7 personal AI agent that helps you navigate your digital life. Set recurring tasks, teach it new skills and create complete workflows. #GoogleIO

Google

72,507 views • 25 days ago

A research preview of Operator, an agent that can use its own browser to perform tasks for you.

A research preview of Operator, an agent that can use its own browser to perform tasks for you.

OpenAI

3,935,910 views • 1 year ago

OpenAI Operator looks great here is a open source version of it you can use now see an agent that uses your browser to perform tasks for you developers get started in a few lines of code pip install 'ai-gradio[browser]' import gradio as gr import ai_gradio gr.load( name='browser:gpt-4o', src=ai_gradio.registry, title='AI Browser Agent', description='Agent that helps with web tasks' ).launch()

OpenAI Operator looks great here is a open source version of it you can use now see an agent that uses your browser to perform tasks for you developers get started in a few lines of code pip install 'ai-gradio[browser]' import gradio as gr import ai_gradio gr.load( name='browser:gpt-4o', src=ai_gradio.registry, title='AI Browser Agent', description='Agent that helps with web tasks' ).launch()

AK

98,797 views • 1 year ago

Introducing Opera’s Browser Operator! Imagine a browser that can just do things for you. Finish tasks you might just find too complex or too boring. Today, we're previewing a browser AI agent that gets shit done for you. Let’s dig deeper! 🧵

Introducing Opera’s Browser Operator! Imagine a browser that can just do things for you. Finish tasks you might just find too complex or too boring. Today, we're previewing a browser AI agent that gets shit done for you. Let’s dig deeper! 🧵

Opera

214,911 views • 1 year ago

Google Project Mariner: NEW Browser Use AI Agent 🤯

Google Project Mariner: NEW Browser Use AI Agent 🤯

Julian Goldie SEO

21,868 views • 1 year ago

Introducing Googlebook, the first laptop designed for Gemini Intelligence. It’s crafted for heavyweight performance, built with Gemini at the core and perfectly synced with your Android phone. Coming this fall. 💻✨ #TheAndroidShow

Introducing Googlebook, the first laptop designed for Gemini Intelligence. It’s crafted for heavyweight performance, built with Gemini at the core and perfectly synced with your Android phone. Coming this fall. 💻✨ #TheAndroidShow

Google

2,508,085 views • 1 month ago

🚀 Monica 9.0 is LIVE now Meet Monica Agent, your most powerful agent yet. Deep Research: Research deeply and write a solid report Create Slides: Turn your ideas into professional slides Browser Operator: Automate tasks in your own browser Premium AI Agent. Startup Pricing.

🚀 Monica 9.0 is LIVE now Meet Monica Agent, your most powerful agent yet. Deep Research: Research deeply and write a solid report Create Slides: Turn your ideas into professional slides Browser Operator: Automate tasks in your own browser Premium AI Agent. Startup Pricing.

Monica AI

536,600 views • 5 months ago

🚨BREAKING: New agentic browser alert and it’s INSANE. Sigma Browser isn’t just another AI add-on. This browser actually browses for you. - AI at the core - An Agent that works on your behalf - Handles tasks like project management, Jira tickets, testing, and code reviews

🚨BREAKING: New agentic browser alert and it’s INSANE. Sigma Browser isn’t just another AI add-on. This browser actually browses for you. - AI at the core - An Agent that works on your behalf - Handles tasks like project management, Jira tickets, testing, and code reviews

Future Stacked

57,042 views • 10 months ago

Introducing Expect Test your agent code in a real browser Works with your agent. Fully open source

Introducing Expect Test your agent code in a real browser Works with your agent. Fully open source

Aiden Bai

73,293 views • 2 months ago

We explored London with a little help from Project Astra. 🇬🇧 With Gemini 2.0, our early research prototype can have more natural conversations, comes with improved memory and can use Google tools - making it more useful for everyday life. 🤝

We explored London with a little help from Project Astra. 🇬🇧 With Gemini 2.0, our early research prototype can have more natural conversations, comes with improved memory and can use Google tools - making it more useful for everyday life. 🤝

Google DeepMind

237,942 views • 1 year ago

🤖 Meet Agent Mode in JetBrains AI Assistant for VS Code! 🔗 Go beyond simple code completion and delegate complex coding tasks to our AI agent that can: ✨ Analyze your entire codebase ✨ Make multi-file edits simultaneously ✨ Handle intricate refactoring operations ✨ Solve complex programming challenges under your supervision Think of it as having an intelligent coding partner that understands your project context and can execute sophisticated tasks while you maintain full control.

🤖 Meet Agent Mode in JetBrains AI Assistant for VS Code! 🔗 Go beyond simple code completion and delegate complex coding tasks to our AI agent that can: ✨ Analyze your entire codebase ✨ Make multi-file edits simultaneously ✨ Handle intricate refactoring operations ✨ Solve complex programming challenges under your supervision Think of it as having an intelligent coding partner that understands your project context and can execute sophisticated tasks while you maintain full control.

JetBrains

15,003 views • 1 year ago

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 views • 1 year ago

Handle high-volume tasks with better speed and efficiency. Gemini 3 Flash is designed to lower latency and optimize costs for complex workflows. It helps you build, test, and deploy without the wait. Learn more →

Handle high-volume tasks with better speed and efficiency. Gemini 3 Flash is designed to lower latency and optimize costs for complex workflows. It helps you build, test, and deploy without the wait. Learn more →

Google for Developers

21,545 views • 5 months ago

Introducing Google Flow Agent 🎬 ✅ Google Flow Agent can help you plan and reason through complex creative tasks with your inputs, all while under your control. 🧠 It's built with Gemini models and brings a deep understanding of your project to help with everything from early brainstorming to editing the final product. 💡 The agent can be a sounding board for dialogue between characters in a scene, and make plot recommendations when you need inspiration. 🎞️ Your Google Flow Agent can also create multiple variations of a scene at one time to give you more options and batch edit. 📂 And when you have all your final assets, your Google Flow Agent can organize them into collections, and even neatly rename them.

Introducing Google Flow Agent 🎬 ✅ Google Flow Agent can help you plan and reason through complex creative tasks with your inputs, all while under your control. 🧠 It's built with Gemini models and brings a deep understanding of your project to help with everything from early brainstorming to editing the final product. 💡 The agent can be a sounding board for dialogue between characters in a scene, and make plot recommendations when you need inspiration. 🎞️ Your Google Flow Agent can also create multiple variations of a scene at one time to give you more options and batch edit. 📂 And when you have all your final assets, your Google Flow Agent can organize them into collections, and even neatly rename them.

Google

151,859 views • 18 days ago

Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience. Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products. Learn how to get started with Antigravity 2.0 👇

Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience. Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products. Learn how to get started with Antigravity 2.0 👇

Google Antigravity

2,424,691 views • 28 days ago

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.

Trade research drudgery for research breakthroughs — @SciSpace_ Agent gives back an average of 1300 hours a year to researchers. SciSpace Agent is the first #AI built exclusively for the scientific research community. Learn more about your new AI co-scientist in this thread.

Kirk Borne

11,871 views • 10 months ago

Introducing your agent and the all-new Gemini Omni model in Google Flow. #GoogleIO ✨ Think of your agent as a creative partner. It reasons through complex tasks and helps you brainstorm, create, and edit, all while under your direction. ⚡ Gemini Omni is where Gemini’s intelligence meets our generative media models. Think of it as Nano Banana but for video. It is a major leap forward in world understanding, multimodality, and editing. Try all the latest Google Flow updates from I/O today at

Introducing your agent and the all-new Gemini Omni model in Google Flow. #GoogleIO ✨ Think of your agent as a creative partner. It reasons through complex tasks and helps you brainstorm, create, and edit, all while under your direction. ⚡ Gemini Omni is where Gemini’s intelligence meets our generative media models. Think of it as Nano Banana but for video. It is a major leap forward in world understanding, multimodality, and editing. Try all the latest Google Flow updates from I/O today at

Google Flow

167,843 views • 28 days ago

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

257,696 views • 12 days ago

Amazon Q Developer has a new agentic coding experience in the IDE that helps you seamlessly accomplish tasks. 💻🔍 Amazon Q Developer can now intelligently perform tasks on your behalf by automatically reading files, running shell commands, and generating code diffs. 👉

Amazon Q Developer has a new agentic coding experience in the IDE that helps you seamlessly accomplish tasks. 💻🔍 Amazon Q Developer can now intelligently perform tasks on your behalf by automatically reading files, running shell commands, and generating code diffs. 👉

Amazon Web Services

19,690 views • 1 year ago