Fuji-Web is an intelligent AI partner that understands the user’s intent, navigates websites autonomously, and executes tasks on the user’s behalf while explaining each action step.
FujiWebCompressed.mp4
Please read our blog post for a demo video, benchmarks and deep-dive technical overview!
- Go to the releases page, find the latest version of the extension and download "fuji-extension.zip".
- Unzip the file.
- Load your extension on Chrome by doing the following:
- Navigate to
chrome://extensions/
- Toggle
Developer mode
- Click on
Load unpacked extension
- Select the unzipped folder
- Navigate to
Please note that you may need to refresh the page for the extension to work.
- Find the Fuji icon in the top right corner of your browser and click on it to open the sidepanel.
- Create or access an existing OpenAI API Key or Anthropic API key and paste it in the provided box. This key will be stored in your browser, and will not be uploaded to a third party.
- Finally, navigate to a webpage you want Fuji-Web and type in the task you want it to perform.
Note: all prompts (text and image) are sent directly to the API of your selection. Fuji-Web does not attempt to collect any information from you.
If you want to build the extension from source, follow these instructions:
- Ensure you have Node.js. The development was done on Node v20 but it should work with some lower versions.
- Clone this repository
- Install
pnpm
globally:npm install -g pnpm
- Run
pnpm install
- Run
pnpm dev
to start the development server, orpnpm build
to build the extension.
When loading the extension, you will need to load the dist
folder created by the build process.
- Expose API for easy integration with browser automation frameworks (e.g. Puppeteer, Playwright, Selenium)
- Add support for more complex & cross-tab workflows
- Add support for more browsing behaviors (select from dropdown, extract content from entire page etc.)
- Add support for saving workflows
- Add support for sharing workflows & instructions with others
- Create wikipedia-like knowledge base where users can work together to create knowledge that can improve the Fuji-Web's performance
Check out our Troubleshooting Guide for help with common problems.
Interested in contributing to Fuji-Web? We'd love your help! Check out our Contribution Guide for guidelines on how to contribute, report bugs, suggest enhancements, and more.
We also have set up a dedicated channel for Fuji-Web feedback on Discord at https://discord.gg/yfMjZ8udb5.
- Fuji-Web's image annotation method was inspired by Microsoft's UFO paper.
- Fuji as a tool that lives in the browser sidepanel was inspired by TaxyAI's browser extension. We also used some of its UI code.
- The Chrome extension set-up leveraged an awesome boilerplate project Jonghakseo/chrome-extension-boilerplate-react-vite.
- The Fuji logo is from Toss Face Emoji design set.