# Project export: Kindred

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: UC Berkeley AI Hackathon 2026
- Tagline: Kindred is an AI safety layer for your browser that protects less tech-savvy users — flagging scams, simplifying pages, and completing tasks by voice. Making the web safe for those it leaves behind.
- Devpost: https://devpost.com/software/kindred-9cksgi
- GitHub: not linked
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

We watched older relatives freeze up online — second-guessing every link, falling for scams, giving up on sites that were just too cluttered. The web wasn't built with them in mind, and we wanted to fix that.

### What it does

Kindred is an AI accessibility and safety layer for your browser. It flags scams before you click, simplifies messy pages into something readable, accepts voice input, and can even complete tasks for you with an Autopilot mode.

### How we built it

A Chrome MV3 extension for the in-browser experience, voice input for hands-free use, and Browserbase for cloud automation and security checks.

### What we learned

Tuning scam detection is genuinely hard — cutting false positives without missing real threats took real iteration. Challenges Wrangling Git workflows across the team and balancing accuracy against speed in our detection pipeline.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.