KeepiAI

Company: KeepiAI

Self-reported basis: The description provided is entirely self-reported and unverified, based on a Devpost submission for the OpenAI 2026 hackathon. No external corroboration exists.

What it appears to be: A voice-based AI assistant designed to capture notes, todos, and journal entries via voice input, with persistent memory of conversations. It is built using Flutter and integrates with OpenAI APIs and Supabase.

What changed: The project was submitted as a hackathon entry; no indication of prior development or commercial traction exists.

Single most important open question: What is the actual product functionality, and how does it differ from existing voice-based note-taking tools?

The description states that KeepiAI is “an AI companion who captures your notes, todos, and journal by voice, remembers every conversation, and makes sure your reminders never go silent.”

• Evidenced: Yes.
• Inferred: No.

It is built using Flutter (with Dart), Android widgets, Kotlin, OpenAI APIs, Supabase, SQLite, Riverpod, WorkManager, and RemoteViews.

• Evidenced: Yes.
• Inferred: No.

The author declares it as a hackathon project submitted to the OpenAI 2026 hackathon.

• Evidenced: Yes.
• Inferred: No.

No further details on product architecture, user interface, or core functionality are provided beyond the tagline and tech stack.

The tagline positions KeepiAI as an AI companion that captures notes, todos, and journals via voice, with persistent memory of conversations.

• Evidenced: Yes.
• Inferred: No.

There is no evidence of prior positioning or evolution of claims — this is a single self-reported statement from a hackathon submission.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

The description does not state who the target customer is or what the Ideal Customer Profile (ICP) might be.

• Evidenced: No.
• Inferred: No.

It is implied that the product targets individuals seeking voice-based note-taking and task management, but this is not explicitly stated.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

There is no evidence of a business model or pricing structure in the description.

• Evidenced: No.
• Inferred: No.

The project was submitted as a hackathon entry; no indication of monetization or commercial intent exists.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

The product is built using Flutter and integrates with:

• OpenAI APIs (including Realtime API)
• Supabase
• SQLite for local storage
• Riverpod for state management
• WorkManager for background tasks
• Android widgets and RemoteViews
• Kotlin and Dart
• Function-calling capabilities

These technologies suggest a mobile-first, voice-enabled application with backend integration and local data persistence.

• Evidenced: Yes.
• Inferred: No.

The project is described as a hackathon submission, implying it may not be production-ready or fully functional.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

There is no evidence of traction, adoption, or customer base.

• Evidenced: No.
• Inferred: No.

The project was submitted to a hackathon and has no mention of user testing, feedback, or product usage.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

There is no evidence of competitive analysis or positioning relative to other tools in the voice-based note-taking or AI assistant space.

• Evidenced: No.
• Inferred: No.

The description does not mention competitors or market differentiation.

• Evidenced: No.
• Inferred: Yes, but not substantiated.

• The project is a hackathon submission; no evidence of product-market fit, traction, or commercial viability.
• No evidence of revenue model, pricing, or monetization strategy.
• No evidence of user feedback, testing, or adoption.
• The product’s functionality and delivery are not described beyond the tagline and tech stack — it is unclear if it works as intended.
• The team size is listed as 1, suggesting limited development capacity.
• No mention of scalability, security, or privacy features.
• The project lacks any indication of a go-to-market strategy or commercialization plan.

1. What specific problem does KeepiAI solve that existing tools do not?
2. How does the product capture and process voice input, and how is it integrated with AI models?
3. Is there any user testing or feedback collected so far?
4. What is the intended business model and monetization strategy?
5. What are the key technical challenges in delivering persistent memory of conversations?
6. How does the product handle data privacy and local vs. cloud storage?
7. What is the roadmap for development beyond this hackathon submission?
8. Are there any partnerships or integrations planned with other platforms?