AI browser automation agent. Private with Ollama or LM Studio. When using cloud providers, page content is sent to their API.
Users
12
−1 in 30 days
Rating
5.0 / 5
unchanged in 30 days
Ratings
4
0 in 30 days
Store rank
#185K
#155K among extensions
Version
0.1.1
updated 27 Jul 2026
Users
monthly, 4 months
Latest, 21 Oct 2026:12 usersMove the mouse over the chart for any month
Ratings count
monthly, 4 months
Latest, 21 Oct 2026:4 ratingsMove the mouse over the chart for any month
The Chrome Web Store rounds user counts down to the leading digit, so the user line moves in steps. The ratings count is exact and is the better signal of real adoption.
About Navy
Navy — AI Browser Automation Agent
Navy is a browser automation agent built into Chrome. Type a goal in plain English — Navy carries it out by clicking, typing, scrolling, filling forms, switching tabs, running scripts, and more. No server required. No installation beyond loading the extension.
HOW IT WORKS
Navy attaches to your active tab, takes a screenshot, reads the page structure, and sends it to an AI model. The AI decides what action to take next. Navy executes it, takes another screenshot, and repeats until the goal is complete.
Because it runs inside your real browser session, Navy works with your existing logins, cookies, and saved state — no re-authentication needed.
LOCAL AND CLOUD AI
Navy supports both local and cloud AI providers.
Local (free, fully private — nothing leaves your machine):
• Run open-source models locally with Ollama or LM Studio. No account, no API key, no data sent anywhere.
Cloud:
• Navy works with any OpenAI-compatible API endpoint. Configure your preferred cloud AI service and API key in Settings. Swap providers at any time without reloading.
FEATURES
• Natural language goals — describe what you want in plain English
• Visual reasoning — numbered screenshot overlay lets the AI click precisely on specific elements
• Uses your real browser session — your logins and cookies are already there
• Two-tier planning — breaks complex goals into subtasks, re-plans dynamically when stuck
• Full action set — click, double-click, right-click, type, scroll, drag, hover, select dropdowns, fill and submit forms, fetch URLs, run JavaScript, manage tabs, upload files
• Panic stop — Ctrl+Shift+. (Cmd+Shift+. on Mac) immediately aborts any running task
• Audit log — every step is recorded locally for transparency
PRIVACY
With a local model: all processing is on your machine. Nothing leaves your device.
With a cloud provider: screenshots and page content are sent only to the API endpoint you configured. The extension developer never receives any of your data — there is no analytics, telemetry, or data collection of any kind.
Password fields and credential-like inputs are never sent to the AI.
Full privacy policy: https://github.com/zrnge/navybrowser/blob/main/PRIVACY.md
GETTING STARTED
1. Go to chrome://extensions, enable Developer mode, click "Load unpacked", and select the extension folder
2. Click the Navy icon or press Ctrl+Shift+L to open the side panel
3. Open Settings and configure your AI provider
4. Navigate to any website and type your goal
EXAMPLE TASKS
• "Search for USB-C hubs under $30 and show me the top results"
• "Fill out this contact form with my details"
• "Find the top headlines on this news page"
• "Summarise the last 5 unread emails in my inbox"