OpenAI 2026 hackathon

ReApp

ReApp adds short breathing pause to AI-assisted work. It displays a 30, 60, or 90-second visual rhythm to help regulate your nervous system. Perfect for developers who spend hours staring at screens

Solo project by Allen Brouwer · 0 likes · 0 comments

Archive position — measured, not model output

0 likes on Devpost

2,264 of the 7,856 archived projects have more likes, and 5,592 share exactly 0 — so this project's #6,272 place in the like-ranked listing is a tie-break inside that group, not a ranking.

Projects (log scale)

1
10
100
1k
10k
05,592
11,758
2285
3–4132
5–975
10+14

Likes on Devpost. ▲ marks this project's group.

Show the figures
LikesProjectsShare of archive
05,59271.2%
11,75822.4%
22853.6%
3–41321.7%
5–9751.0%
10+140.2%
Devpost like counts for all 7,856 archived projects, captured when this archive was built.

Executive Summary

What the company appears to be

ReApp is a self-reported developer tool that integrates with AI-assisted development environments (ChatGPT, Codex) and runs as a native macOS application. It provides short, user-controlled breathing pauses during computer work, designed to help regulate the nervous system and support mental clarity.

What changed

The project was submitted as part of an OpenAI hackathon. It evolved from an iOS app into a multi-platform solution including a Mac menu-bar companion, browser experience, ChatGPT app, MCP service, and Codex skill. The author states that Codex played a central role in building the product within a short timeframe.

Single most important open question

Is there evidence of any traction or adoption beyond the hackathon submission? The description does not indicate whether ReApp has moved past prototype or received feedback from users beyond the development team.

Analysis basis

This report is based entirely on the self-reported, unverified project description provided by the author. No external verification or historical data are available.

Back to contents

What The Product Actually Is

The description states that ReApp is a tool that creates short, user-controlled breathing pauses during computer work. It includes:

  • A Mac Bar App (native macOS application) that schedules randomized breathing pauses between 30 and 90 minutes.
  • An interactive visual breathing pacer with fixed five-second inhale/exhale rhythm.
  • Options for 30, 60, or 90-second durations.
  • Pause/resume controls and early-exit options (Escape key).
  • Optional GPT-5.6-generated calming cue language.
  • Integration with ChatGPT and Codex via an Apps SDK-compatible interface.
  • A structured technical architecture involving:
    • An MCP server exposing four typed tools
    • A bundled Codex skill and SessionStart hook
    • A native SwiftUI macOS companion app

Inference The product is described as a hybrid of AI-assisted development integration and personal wellbeing tool. It is not clear if it functions independently or relies on external AI services for its core functionality.

Back to contents

Positioning & Claim Evolution

The author claims that ReApp helps developers take intentional breathing breaks during AI-assisted work, aiming to improve mental clarity and reduce stress without interrupting productivity.

Key positioning elements from the description:

  • Aims to "help developers return to work calmer, clearer, and more connected to what they are doing."
  • Positions itself as a tool that allows users to "connect back to themselves" while working.
  • Describes its goal as not interrupting productive work but helping users "return to it calmer."

Inference The positioning evolved from a general wellness product to one specifically tailored for AI-assisted developers, with the added benefit of being adaptable across platforms (iOS, macOS, ChatGPT, Codex). However, this evolution is based on the author’s own account and lacks evidence of market validation.

Back to contents

Target Customer & ICP

The description states that ReApp is intended for:

  • Developers who spend hours staring at screens.
  • Users who engage in AI-assisted work (e.g., using ChatGPT or Codex).
  • Anyone who spends significant time in front of a screen, including virtual assistants, content creators, stock traders, etc.

Inference The primary ICP appears to be developers using AI tools. However, the author also mentions broader applicability, suggesting potential for expansion beyond developers. No evidence exists regarding actual customer segments or user personas.

Back to contents

Business Model & Pricing Evidence

There is no mention of pricing, monetization strategy, or business model in the description.

Not evidenced. The description does not provide any information about how ReApp intends to generate revenue or whether it has a commercial model beyond its hackathon submission.

Back to contents

Technical & Delivery Signals

The author describes building the product using:

  • Codex for rapid prototyping and implementation
  • Node.js and Vercel for backend services
  • SwiftUI for macOS app development
  • OpenAI APIs (including GPT-5.6, Responses API, Structured Outputs)
  • MCP server architecture
  • Apps SDK-compatible interface

Key technical claims:

  • Native Mac companion runs locally without accessing source code or prompts.
  • The system supports offline behavior and fallbacks.
  • Escape key is always available during the breathing exercise.
  • No remote tracking of user wellbeing history.

Inference The product appears to be built with a focus on privacy, local execution, and minimal AI involvement in core timing functions. However, there is no evidence of scalability or production deployment beyond the hackathon context.

Back to contents

Traction & Maturity Signals

The description indicates that ReApp was submitted as part of an OpenAI 2026 hackathon and includes:

  • A signed and notarized macOS beta version
  • Submission to Apple and OpenAI plugin review processes
  • Unit, integration, accessibility, and testing completed
  • No revenue or customer data mentioned

Not evidenced. There is no indication of user adoption, retention metrics, or commercial traction beyond the hackathon submission.

Back to contents

Competitive Context

The description does not reference any competitors or existing solutions in this space.

Not evidenced. No competitive landscape or differentiation strategy is described.

Back to contents

Key Risks & Red Flags

  • Unproven market demand: The product exists only as a hackathon submission with no evidence of user traction or feedback.
  • Limited commercial viability: No pricing, monetization, or business model discussed.
  • Dependency on AI tools: Reliance on Codex and OpenAI APIs may create fragility if those platforms change or become unavailable.
  • Unclear long-term vision: While the author mentions future features, there is no indication of roadmap execution or strategic direction beyond the hackathon.

Inference The risk of failure lies in assuming that a prototype developed for a hackathon will translate into a viable product or business without further development, testing, or market validation.

Back to contents

Diligence Questions To Ask The Founders

  1. What specific feedback did you receive from developers during the hackathon?
  2. How do you plan to transition ReApp from a hackathon prototype to a sustainable product?
  3. Are there any plans for monetization or revenue generation?
  4. Have you conducted any user studies or usability tests beyond the development team?
  5. What are your thoughts on scaling this across other platforms (e.g., Windows, Linux)?
  6. How do you intend to ensure long-term stability and support for the AI integrations used?

Back to contents

Investment/Partnership Verdict

Not evidenced.

There is no evidence of revenue, customer base, or traction beyond the hackathon submission. The product is described as a prototype built in a short timeframe using AI tools like Codex. Without further data on adoption, user feedback, or commercial viability, it is not possible to assess whether ReApp represents a viable investment or partnership opportunity.

Confidence level Low — based solely on self-reported information with no external validation or performance metrics.

Back to contents

Source

Submitted to the OpenAI 2026 hackathon on Devpost. Project home on DevPost.

The analysis above was generated by a language model from the project's own one-line description. It is not independent research and contains no verified traction, revenue or customer data.