Who's been carrying
this whole time?

Upload your chat. Get a brutally honest breakdown of who texts first, who replies faster, and who actually gives a damn.

View History

3 Steps to Clarity

See the Numbers

Export your chat. See instant stats on message share, longest streaks, and exact median reply times.

Export Guide →

Get the Meaning

Unlock the AI. Find out your attachment style, subtle emotional red flags, and hidden power dynamics.

Know What to Do

Get brutally honest relationship advice and a final verdict based entirely on your actual chat patterns.

sample report

What Your Report Looks Like

attachment style

Secure-Anxious

You show stable patterns but seek extra reassurance during stress periods.

compatibility score

82/100

Strong alignment in values with room for communication growth.

growth area

Active Listening

Partner responds 2.3× faster but with shorter messages, which may indicate surface-level engagement.

drop your chat

Start Your Analysis

1. Details

Your Name

Partner's Name

Connection Type

Language

Context (Optional)

0 / 2000

Analysis Tone

Clear, helpful insights with context.

2. Chat Export

Drop your chats here

Browse Files

3. Process

API

AI Provider

API Key Required

faq

Frequently Asked Questions

Yes. The entire analysis payload is calculated locally. Your chat export never leaves your device's browser. Only completely anonymous numerical statistics (like total message counts or response times) are forwarded to our backend for the AI to interpret. We process these raw numbers in temporary RAM without writing to any database, destroying them instantly.

No. Your API key is stored only in your browser's sessionStorage and is sent directly to the LLM provider. We never log, store, or cache your key on our servers.

All supported models (GPT-4o, Claude 3.5, Gemini Pro) produce excellent results. GPT-4o tends to give the most detailed coaching recommendations, while Claude excels at nuanced emotional analysis.

The analytics engine runs in under 1 second. The AI narrative generation takes 10–20 seconds depending on your LLM provider and chat length.

WhatsApp (.txt export), Telegram (.html export), Instagram (.json export), and Discord (.json export). We're working on iMessage support.

Who's been carrying this whole time?