Sarathi AI Agent

Sarathi AI is a voice-based browser assistant that helps you control your web browser using simple commands. It works as a Chrome extension, allowing you to automate tasks on websites.

Benefits

Sarathi AI can understand web pages and follow your instructions, whether you speak them or type them. It can help you fill out forms with realistic information, reply to emails, and even shop online by adding items to your cart and starting the checkout process. It can read content aloud and handle tricky web elements like dropdown menus and pop-up windows. A key advantage is its speed and reliability because it works directly with the website's structure rather than analyzing images.

Use Cases

This tool is useful for automating everyday online tasks. For example, it can help you respond to emails in Gmail by understanding the original message and drafting a reply. It can also assist with online shopping by finding products, selecting options, and adding them to your cart. Filling out long or complex forms with accurate details is another area where Sarathi AI can save you time.

Vibes

Sarathi AI is described as an experimental tool with a general browsing reliability of about 90%. It is noted to have some challenges with very strict anti-bot systems and CAPTCHA verifications.

Additional Information

Sarathi AI uses a method called DOM-grounded analysis, which means it reads the website's underlying code rather than looking at pictures. This makes it faster and more efficient. To use Sarathi AI, you need to set up your own connection to an AI model provider like OpenAI or Google Gemini and provide your API keys. The extension is installed by loading it as an unpacked extension in Chrome. The project is open source and available under the MIT License.