An advanced autonomous browser agent powered by AI
Navigate, search, automate, and get things done — all through natural conversation.
Features • Screenshots • Installation • Usage • API Keys • Privacy
Choose from the best AI models available:
- Google Gemini (3.1 Pro Preview, 3 Flash Preview, 3 Pro Preview, 2.5 Pro, 2.5 Flash) — Free tier available!
- OpenAI (GPT-5.1, GPT-5)
- Anthropic Claude (Opus 4.6, Sonnet 4.6, Opus 4.5/4, Sonnet 4.5/4, 3.7 Sonnet)
- Perplexity (Sonar Pro, Sonar Reasoning Pro, Sonar Reasoning, Sonar, Deep Research) — Real-time web search
- OpenRouter — Access 100+ models through a single key (GPT-5.1/5/4.1, Claude 4.6/4.5/3.7, Gemini 3.1/3/2.5, Llama 4, DeepSeek R1/V3, Qwen 3, Mistral, Codestral, Command R+)
- Custom Provider — Use any OpenAI-compatible API (Ollama, LM Studio, Together AI, Bytez)
The AI can control your browser to:
- Navigate to any URL
- Search Google, Bing, or any search engine
- Click buttons, links, and interactive elements
- Type in forms, search boxes, and text fields
- Press keys (Enter, Tab, Escape) for form submission
- Scroll pages up, down, or to specific positions
- Manage tabs (open, close, switch)
Set reminders using natural language:
- "Remind me to take a break in 5 minutes"
- "Set a timer for 30 seconds"
- Features:
- 🔔 Chrome notifications with sound
- 📋 Reminders panel with filter tabs (All/Pending/Completed)
- 🔄 Snooze completed reminders
- 🗑️ Manage and delete reminders
- Modern, responsive design with premium glassmorphism and dark theme
- Color-coded provider pills for easy model identification
- Gradient chat bubbles with smooth animations
- Quick-action suggestion buttons on empty state
- Chat history with session management
- Rename, delete, and organize conversations
- Copy messages to clipboard
- Markdown support in responses
- Page Awareness: AI reads current page content, URL, and title
- Memory System: Save preferences (name, timezone, etc.)
- Interactive Elements: AI can see and use buttons, links, forms
The clean, modern chat interface with model selection and conversation history.
Watch the AI navigate, search, click, and type for you automatically.
Set, track, and manage reminders with the intuitive panel.
Configure API keys, custom providers, and memory preferences.
Easily manage past conversations with rename and delete options.
Coming soon!
-
Clone the repository:
git clone https://github.com/TrixCoder/multiai_extension.git cd multiai_extension -
Install dependencies:
npm install
-
Build the extension:
npm run build
-
Load into Chrome:
- Open
chrome://extensions/ - Enable "Developer mode" (top right toggle)
- Click "Load unpacked"
- Select the
distfolder
- Open
- Click the extension icon in your browser toolbar
- Open Settings (⚙️) and enter your API key(s)
- Select your preferred AI model
- Start chatting!
"Hello! How are you?"
"What's the weather like in New York?"
"Explain quantum computing in simple terms"
"Search Google for React tutorials"
"Go to github.com"
"Open YouTube and search for cooking videos"
"Click the login button"
"Type my email in the form"
"Scroll down to see more"
"Remind me to check emails in 10 minutes"
"Set a timer for 30 seconds"
"Remind me to take a break in 1 hour"
"Open a new tab to google.com"
"Close this tab"
"Switch to the YouTube tab"
Gemini offers a generous free tier — perfect for getting started!
- Go to Google AI Studio
- Sign in with your Google account
- Click "Get API key" in the top left
- Click "Create API key in new project"
- Copy the generated key
Real-time web search capabilities. Pro subscribers get $5/month credits.
- Go to Perplexity API Settings
- Add a payment method or use Pro credits
- Click "Generate" to create a new API key
Access to GPT-5.1, GPT-5, and other cutting-edge models.
- Go to OpenAI Platform
- Sign up or log in
- Go to Settings > Billing and add credits
- Go to API Keys and click "Create new secret key"
Access to Claude Opus 4.6, Sonnet 4.6, Claude 3.7 Sonnet and other models.
- Go to Anthropic Console
- Sign up or log in
- Go to Settings > Plans & Billing to add funds
- Go to "Get API Keys" and click "Create Key"
Access 100+ models with a single API key — GPT-5.1, Claude Opus 4.6, Gemini 3.1, Llama 4, DeepSeek, and more!
- Go to OpenRouter
- Sign up or log in
- Go to "Keys" and click "Create Key"
- Add credits via Billing (pay-as-you-go)
Use any OpenAI-compatible API (like Ollama, LM Studio, etc.):
- Open Settings
- Select "Custom" model
- Enter your Base URL (e.g.,
http://localhost:11434/v1) - Enter your Model Name (e.g.,
llama3)
Your privacy is important to us:
- ✅ API keys stored locally in your browser (never sent to our servers)
- ✅ No data collection — we don't track your usage
- ✅ Open source — inspect the code yourself!
Please read our full Privacy Policy for details.
# Install dependencies
npm install
# Run development server
npm run dev
# Build for production
npm run build
# Type check
npm run typecheckContributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
If you find this extension useful, consider:
- ⭐ Starring the repository
- 🐛 Reporting bugs or suggesting features
- 💝 Sponsoring the developer
Made with ❤️ by TrixCoder