Skip to content

K-Decoder

K-Decoder is an AI-powered cross-cultural communication analyzer designed to bridge the gap between Korean (high-context) and Western (low-context) cultures.

Code Video Cerebral Valley

Core trick

Parses exported KakaoTalk logs, isolates the two main speakers, and sends their messages to Gemini for per-message cultural analysis.

Tags

education

Description

K-Decoder is an AI-powered cross-cultural communication analyzer designed to bridge the gap between Korean (high-context) and Western (low-context) cultures. Users can upload or paste their conversations(like KakaoTalk chat log) , and the app uses Google Gemini to analyze potential misunderstandings, cultural nuances, and communication patterns between the two speakers. It provides a structured breakdown including context analysis, cultural insights, behavior patterns, and actionable advice. The app also features a live decoding mode for real-time conversation analysis. Built with Next.js, it supports both Korean and English interfaces to serve users from either cultural background.
Laeyoung/K-Decoder★ 00 forksTypeScriptCreated Feb 28, 2026 · last push Feb 28, 2026

README excerpt

# Love Decoder

AI-powered KakaoTalk conversation analyzer for cross-cultural relationships between Koreans and foreigners.

## Features

- **KakaoTalk Chat Parsing** — Paste or upload exported KakaoTalk `.txt` files
- **AI Relationship Analysis** — Powered by Google Gemini, provides insights on relationship status, emotions, cultural differences, communication patterns, and advice
- **Bilingual (ko/en)** — Full Korean and English support with seamless locale switching
- **Group Chat Detection** — Warns when 3+ participants are detected and focuses analysis on the top 2 speakers

## Tech Stack

- **Framework**: Next.js 16 (App Router, Turbopack)
- **Language**: TypeScript
- **Styling**: Tailwind CSS 4 + shadcn/ui
- **AI**: Google Gemini (`@google/genai`)
- **i18n**: next-intl
- **Testing**: Vitest

## Getting Started

### Prerequisites

- Node.js 20+
- pnpm

### Installation

```bash
pnpm install
```

### Environment Variables

Copy the example file and add your Gemini API key:

```bash
cp .env.example .env
```

```env
GEMINI_API_KEY=your_gemini_api_key_here
```

Get your API key from [Google AI Studio](https://aistudio.google.com/apikey).

### Development

```bash
pnpm dev
```

Open [http://localhost:3000](http://localhost:3000).

### Testing

```bash
pnpm test          # Run tests once
pnpm test:watch    # Watch mode
```

### Production Build

```bash
pnpm build
pnpm start
```

## Deployment

This project is optimized for [Vercel](https://vercel.com):

1. Push to your Git r

Team