GitHub

Waitlist | Discord
Taxy uses GPT-4 to control your browser and perform repetitive actions on your behalf. Currently it allows you to define ad-hoc instructions. In the future it will also support saved and scheduled workflows.
Taxy's current status is **research preview**. Many workflows fail or confuse the agent. If you'd like to hack on Taxy to make it better or test it on your own workflows, follow the instructions below to run it locally. If you'd like to know once it's available for wider usage, you can sign up for our waitlist.
Taxy is fully open-source, and we don't send any page contents or instructions to our servers.
Here's Taxy using Google Calendar with the prompt "Schedule standup tomorrow at 10am. Invite david@taxy.ai"
Table of Contents
- Taxy AI: Full Browser Automation
- Table of Contents
- Installing and Running
- Installing the extension
- Running in your browser
- How it Works - The Action Cycle
- Simple Demos
- Protecting the main branch in GitHub
- Searching for and playing the movie Oblivion in Netflix
- Creating a calendar event
- Writing an essay in the OpenAI playground
- Add your own!
- Tech Stack
- Resources
Installing and Running
Currently this extension is only available through this GitHub repo. We'll release it on the Chrome Web Store after adding features to increase its usability for a non-technical audience. To build and install the extension locally on your machine, follow the instructions below.
Installing the extension
1. Ensure you have Node.js >= **16**.
2. Clone this repository
3. Run yarn to install the dependencies
4. Run yarn start to build the package
5. Load your extension on Chrome by doing the following:
1. Navigate to chrome://extensions/
2. Toggle Developer mode
3. Click on Load unpacked extension
4. Select the build folder that yarn start generated
Running in your browser
1. Once installed, the browser plugin will be available in two forms:
1. As a Popup. Activate by pressing cmd+shift+y on mac or ctrl+shift+y on windows/linux, or by clicking the extension logo in your browser.
2. As a devtools panel. Activate by first opening the browser's developer tools, then navigating to the Taxy AI panel.
2. The next thing you need to do is create or access an existing OpenAI API Key and paste it in the provided box. This key will be stored securely in your browser, and will not be uploaded to a third party.
3. Finally, navigate to a webpage you want Taxy to act upon (for instance the OpenAI playground) and start experimenting!
How it Works - The Action Cycle
1. Taxy runs a content script on the webpage to pull the entire DOM. It simplifies the html it receives to only include interactive or semantically important elements, like buttons or text. It assigns an id to each interactive element. It then "templatizes" the DOM to reduce the token count even further.
2. Taxy sends the simplified DOM, along with the user's instructions, to a selected LLM (currently GPT-3.5 and GPT-4 are supported). Taxy informs the LLM of two methods to interact with the webpage: