fuji-web  by normal-computing

AI agent for browser automation

created 1 year ago
465 stars

Top 66.2% on sourcepulse

GitHubView on GitHub
Project Summary

Fuji-Web is an AI-powered browser extension designed to automate tasks within the user's web browser. It targets users who need to perform repetitive or complex online actions, offering autonomous navigation and task execution with step-by-step explanations.

How It Works

Fuji-Web operates as a browser sidepanel extension. Users provide an OpenAI or Anthropic API key, which is stored locally. The AI agent then interprets user intent, navigates web pages, and executes tasks by interacting with the browser's DOM. Prompts and image data are sent directly to the selected LLM provider.

Quick Start & Requirements

Highlighted Details

  • AI-based full browser automation.
  • Autonomous website navigation and task execution.
  • Explains each action step.
  • Supports OpenAI and Anthropic APIs.

Maintenance & Community

Licensing & Compatibility

  • License details are not explicitly stated in the README.

Limitations & Caveats

The extension is currently designed for Chrome. Support for more complex cross-tab workflows and advanced browsing behaviors like dropdown selection or full-page content extraction is planned for future releases.

Health Check
Last commit

7 months ago

Responsiveness

1 week

Pull Requests (30d)
0
Issues (30d)
0
Star History
40 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.