Concept·Agents & Automation·Added 1 month ago

Project Mariner

Also known as: Google Project Mariner, Mariner

Google's web-browsing agent built on Gemini. It can navigate websites, fill forms, and complete multi-step tasks in a browser on your behalf, the Google counterpart to OpenAI's Operator.

Project Mariner is Google's implementation of browser-based computer use: a Gemini-powered agent that can see and interact with web pages, navigate flows, extract information, and complete tasks that require moving through multiple sites or UI states. It operates inside a Chrome browser environment and is aimed at automating the kind of repetitive web work that currently requires a human at a keyboard.

Google announced Mariner alongside Project Astra at I/O 2025, framing the pair as its two major agentic bets: Astra for ambient, real-world assistance via camera and voice; Mariner for structured, goal-oriented web task completion. Both are Gemini-powered and feed into the broader Gemini agentic stack.

The most relevant comparison for builders is to Anthropic's computer use capability and OpenAI's Operator: all three represent the same underlying capability (a model that can see and interact with UI) but different product form factors and API surfaces. Mariner is tightly integrated with Chrome, which is both a constraint and an advantage given Chrome's install base.

This definition is AI-generated and refreshed weekly. It may contain inaccuracies. Use your own judgment, especially for production decisions.

Related terms