# Project export: Drunk Buddy

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: A buddy that lives in your iMessage and looks out for you when you're drunk.
- Devpost: https://devpost.com/software/drunk-buddy
- GitHub: not linked
- Demo: https://drunk-buddy.vercel.app/
- Video: https://www.youtube.com/embed/0WC9Uvlz7MU?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

Drunk people making bad and regrettable decisions along with being in danger.

### What it does

Drunk Buddy is a buddy that lives in iMessage and helps look out for you when you’ve been drinking. It’s designed to feel like texting a real person, not using an app or dashboard. The thread is the product: you message it, and it replies in a casual, protective, slightly funny voice. Behind the scenes, it can: no text list check in on you call an Uber order food escalate to emergency contacts if you go silent or vitals spike, shares location of user to contact In short: it’s a harm-reduction buddy that helps get people home safely, with the whole experience happening inside the conversation.

### How we built it

We built the app as a TypeScript monorepo with a server-side AI agent that lives behind messaging channels instead of a traditional UI. The main user experience happens in an iMessage thread, where the backend handles inbound messages, maintains conversation and user state, and routes requests through an agent loop with tool-based actions. We structured the system around interfaces so external services like messaging, storage, rides, food, and vitals can be mocked for demos and swapped to real implementations later. The app emphasizes a friendly, protective tone and focuses on a smooth demo-ready flow over feature completeness.

### Challenges we ran into

Had issues with finding a way to use BlueBubbles since we don't have direct access to imessages via an API we had to use a third party. Integrations with Deepgram were also a challenge to deal with.

### Accomplishments we're proud of

Getting the core functionality to work.

### What's next

Trip Buddy

## 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.
- Anthropic (technology) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code
- Redis (technology) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.