Project Mariner
https://deepmind.google/technologies/project-mariner/
Google DeepMind's experimental browser agent built on Gemini 2.0 — Chrome extension that takes actions on the user's behalf. Research-preview launched Dec 2024. The Google answer to OpenAI Operator / Anthropic Computer Use; integrated into Gemini app surfaces in 2025.
At a glance
- Type
- Google DeepMind browser-agent (research preview)
- Tier
- T1
- Section
- Computer-use & desktop agents
- Created
- 2024-12
- Latest release
- not applicable — not OSS
- License
- not applicable — not OSS
- GitHub
- not applicable — no GitHub repo
- Pricing
- Bundled with Gemini Advanced ($19.99/mo)
- Funding
- Google DeepMind parent (Alphabet)
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- agent-controlled
- unit
- turn
- governance
- opaque
- conflict
- stateless
When to use
Optimised for: Gemini 2.0-powered Chrome agent
Anti-fit: Research preview only; Chrome only; Gemini Advanced tier
Pros & cons
Pros
Strong WebVoyager numbers; Google distribution; A2A first-party adjacency.
Cons
Research preview; Chrome / Gemini Advanced tier; closed source.
Claims & capabilities
Powered by Gemini 2.0; WebVoyager 83.5% per launch eval; research preview Dec-2024
Technical surface
- API surface
- Chrome extension; underlying Gemini 2.0 API
- Backend storage
- Google-managed session state
- Deployment
- Chrome extension + Google Cloud
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- Single-tenant per Google account
- MCP
- searched not found
- A2A
- Google's own A2A protocol — likely first-party compatible
- OpenTelemetry
- searched not found
Compare Project Mariner with…
Similar systems
Other computer-use & desktop agents in the catalog, ranked by inbound references.
- UI-TARS T2
ByteDance Seed's open-source GUI-agent foundation model — released Jan 2025; trained end-to-end on screenshot → action pairs. Comes with UI-TARS-Desktop (Electron app) that runs the model against the user's screen. SOTA on OSWorld at release; weights on HuggingFace.
- Browser Use T1
Python library that turns any LLM into a browser agent — extracts DOM into a structured representation the LLM can act on (rather than pure screenshot). Browser Use Inc. raised $17M seed Q1 2025 (Felicis); cloud product at cloud.browser-use.com. Project is one of the most-starred browser-agent OSS repos (~60k stars).
- Bytebot T3
Open-source desktop-agent runtime that runs an LLM-controlled Linux desktop inside Docker — uses xdotool / X11 capture for control. Pitched as the 'self-hosted Operator' alternative; agent sees a real desktop screen, not just a browser.
- Claude for Chrome T1
Anthropic's Chrome extension that lets Claude act inside the user's existing browser (rather than a sandboxed one). Research preview launched August 2025 — limited to Claude Max tier. Distinct from Anthropic Computer Use (which is the API substrate); this is the consumer surface that uses it inside Chrome.
- Highlight AI T2
Always-on desktop AI assistant that watches the user's screen (across all apps) and answers questions / takes actions based on what's currently visible. Mac + Windows. Founded by Mac Bishop (ex-Mixpanel); raised $13M Series A from Aspect / Lightspeed (Oct 2024). Distinguishes itself from Rewind by being action-oriented (not just recall).
- Hyperbrowser T2
Cloud-hosted headless browser API tuned for AI agents — captcha solving, stealth mode, session recordings. Y Combinator S24; pitched as a faster / cheaper Browserbase alternative. Used as substrate by agents that need browser execution but don't want to run their own Chromium fleet.
Related systems
References (1)
- Google Gemini 3 family depends on at runtime — ental browser agent built on Gemini 2.0 — Chrome extension that takes actions on the user's behalf.