Project Mariner
Research prototype by Google DeepMind
From Wikipedia, the free encyclopedia
Project Mariner is a research prototype developed by Google DeepMind that explores human-agent interactions, particularly within web browsers. It automates tasks such as online shopping, information retrieval, and form-filling, aiming to enhance user productivity by delegating routine web-based tasks to an AI agent.[1]
| Project Mariner | |
|---|---|
| Developer | Google DeepMind |
| Initial release | December 11, 2024 (Research prototype) |
| Stable release | 2025 Update
/ May 20, 2025 |
| Engine | Gemini 2.0 / Gemini 2.5 |
| Operating system | Web browser |
| Platform | Google Chrome, Cloud-based VM |
| Type | AI agent, Automation |
| License | Proprietary (SaaS) |
| Website | deepmind |
Project Mariner operates as an experimental Chrome extension that understands the contents of your screen, including images, code, forms, and more. It can interpret complex goals, plan actionable steps, and navigate websites to carry out tasks, while keeping the user informed and allowing them to intervene at any time.[2][3]
As of May 2025, Project Mariner is available to Google AI Ultra subscribers in the US and is being integrated into the Gemini API and Vertex AI, allowing developers to build applications powered by the agent Google plans to bring Project Mariner’s capabilities to more countries and integrate it into Google Search's AI Mode, which is currently in the Search Labs testing phase.[4]
