HackStack

Project Info

Locking In

Devpost

Inspiration

We all know that feeling: you open your laptop to study... and suddenly it’s three hours later, you’ve watched five cooking videos, and somehow you’re reading about penguin migration patterns. So we made Locking In, an app that keeps you from wandering into the depths of distraction — by literally watching you (nicely).

What it does

You tell the app what you’re supposed to be doing — “study math,” “code,” “pretend to study math while coding,” whatever. Then the app starts taking screenshots every few seconds to see if you’re actually working or, uh, "researching" memes again. Stay focused? You earn points. Get distracted? Lose points. Your friends can see your score, so there’s extra motivation not to go down a YouTube rabbit hole.

How we built it

We built both the client and server sides, glued them together with an API, and sprinkled in some AI magic to figure out what you’re doing on your screen.

Challenges we ran into

Gemini API had an update that broke everything right when we thought we were done. So yeah, we got some surprise learning opportunities.

Accomplishments we're proud of

The app gives feedback in around 20–30 seconds — fast enough to catch your distraction before you’ve fully spiraled into Wikipedia.

What we learned

The MacOS accessibility API is... an adventure. Let’s just say it taught us patience, resilience, and a deep appreciation for working documentation.

What's next

The core app works, but we’re dreaming big — think “social media meets productivity.” Imagine liking your friend’s focus streaks, sending accountability memes, or competing to see who can stay locked in the longest (without crying).

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • HTMLIn code
  • ReactIn code
  • RustIn code
  • SQLIn code
  • Tailwind CSSIn code
  • TypeScriptIn code
  • Google GeminiClaimed

7 of 8 appear in the indexed code. 1 claimed on Devpost could not be matched to code, which may simply mean the tool leaves no trace in the repository.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

109 KB

Source files

40

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars