OpenAI 2026 hackathon

NKKakeist

Turn messy financial exports into trustworthy, explainable personal finance records.

Solo project by naoki hagiwara · 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 #5,574 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

NKKakeist is a personal finance and asset-management web application built by one developer (Naoki Hagiwara) as a self-contained tool for managing financial data from multiple sources, with an emphasis on explainability, accuracy, and avoiding double-counting of transactions.

What changed

The project was submitted to the OpenAI 2026 hackathon. It is described as a personal finance tool that imports data from various financial services (e.g., Money Forward CSVs, Mobile Suica PDFs), reconciles it, and presents a clean view of income, expenses, assets, liabilities, and net worth — while distinguishing between real spending and internal transfers.

Single most important open question

Is there any evidence that NKKakeist has been used beyond the author’s own personal use or testing? The description does not indicate adoption by others, nor does it show any traction, revenue, or customer base.

Back to contents

What The Product Actually Is

The description states that NKKakeist is a personal finance and asset-management web application. It supports:

  • Management of various account types: cash, bank, credit card, e-money, payment service, investment, pension, liability, and reward-point accounts.
  • Tracking income, expenses, and transfers without double-counting internal movements.
  • Importing data from:
    • Money Forward transaction CSV files
    • Balance snapshots
    • Per-security valuations
    • Asset-history data
    • Mobile Suica statements directly from PDF files
    • Semi-automated JRE POINT imports

It uses a staged import workflow, where imported rows go through parsing, normalization, validation, preview, and confirmation before being committed. The system is designed to not commit data unless it can explain why each record was classified in a particular way.

The application also includes features such as:

  • Duplicate detection with explanations
  • Category suggestions and reusable classification rules
  • Reconciliation of calculated balances with official balances
  • Display of monthly/yearly income, expenses, assets, liabilities, net worth, account balances, and security-level trends

Evidence All of this is self-reported by the author.

Inference This suggests a domain-specific solution aimed at individuals who manage complex financial data from multiple providers and want to avoid misclassification or double-counting. It is not a general-purpose finance tool but rather one tailored for users with nuanced financial flows.

Back to contents

Positioning & Claim Evolution

The author positions NKKakeist as a tool that turns messy financial exports into trustworthy, explainable personal finance records. The core claim is that it avoids the pitfalls of standard financial services — particularly those that fail to handle modern payment flows correctly.

Key claims:

  • It distinguishes real spending from credit-card payments, prepaid charges, and investment contributions.
  • It handles overlapping or duplicate imports without silent errors.
  • It provides explainability over classifications and decisions.
  • It allows users to review and correct imported data before committing it.
  • It models connected payment events as a flow rather than unrelated expenses.

The evolution of the positioning appears to be from a personal problem-solving effort (the author’s own experience with financial services) into a tool that addresses broader issues in financial data handling, especially around data integrity and traceability.

Evidence All claims are self-reported by the author.

Inference This is not positioned as a commercial product or service yet. It is presented more like a prototype or personal project with potential for expansion.

Back to contents

Target Customer & ICP

The description does not explicitly define a target customer segment or ideal customer profile (ICP). However, based on the stated use cases and complexity of the tool:

  • Users who manage multiple financial accounts across different platforms.
  • Individuals who experience confusion or double-counting in traditional personal finance tools.
  • People who value transparency and control over their financial data.
  • Those who may already be using services like Money Forward, Mobile Suica, or similar systems but want better integration and clarity.

It is implied that the tool targets tech-savvy individuals, possibly with some familiarity with financial data formats (CSVs, PDFs), rather than casual users of mainstream finance apps.

Evidence No explicit ICP defined; inference drawn from functional scope and user needs described.

Back to contents

Business Model & Pricing Evidence

There is no evidence in the description of a business model or pricing structure. The project is presented as a self-contained personal tool, built by one developer, without indication of monetization plans, subscriptions, or paid features.

Evidence Not evidenced.

Back to contents

Technical & Delivery Signals

The author states that NKKakeist is built with:

  • PHP and Laravel 13
  • Inertia.js
  • React
  • TypeScript
  • Tailwind CSS
  • MySQL
  • Docker Compose
  • Custom CSV and PDF import pipelines

It uses Codex and GPT-5.6 for development assistance, including:

  • Analyzing edge cases
  • Designing the staged import architecture
  • Implementing specific import logic
  • Writing tests and documentation

The system supports:

  • Staged imports (parsing → normalization → validation → preview → confirmation)
  • Transfer matching
  • Duplicate detection
  • Balance reconciliation
  • Reusable classification rules

Evidence All technical details are self-reported.

Inference This indicates a pragmatic, modern stack, combining backend familiarity with contemporary frontend development. The use of AI tools during development suggests rapid iteration and experimentation — but not necessarily scalability or production readiness.

Back to contents

Traction & Maturity Signals

There is no evidence of traction, revenue, customers, or adoption beyond the author’s own use. The project is described as a personal solution, submitted to a hackathon, and built by a single developer.

Evidence Not evidenced.

Inference The lack of any mention of users, usage metrics, or product-market fit suggests that this is an early-stage prototype or proof-of-concept, not yet mature for commercial deployment.

Back to contents

Competitive Context

The description does not reference direct competitors. However, the problem space — managing complex financial data from multiple sources and avoiding double-counting — aligns with existing personal finance tools such as:

  • Mint
  • YNAB (You Need A Budget)
  • Money Forward
  • PocketGuard
  • Personal Capital

These typically offer automated categorization, import capabilities, and dashboards. NKKakeist’s key differentiator appears to be its emphasis on explainability, avoidance of automatic commit, and handling of complex payment flows.

Evidence No direct competitor comparison provided.

Inference If the tool gains traction, it may appeal to users dissatisfied with current tools’ handling of edge cases or lack of transparency in classification.

Back to contents

Key Risks & Red Flags

  • Single-person development: The project is built by one person (Naoki Hagiwara), which raises questions about long-term maintenance, scalability, and support.
  • No evidence of adoption or traction: No customers, users, or revenue are mentioned — indicating no proven market demand or product-market fit.
  • Limited scope: The tool is described as a personal solution, not a scalable SaaS offering.
  • AI dependency: While Codex helped build the system, there’s no indication that this reliance on AI will be sustainable or replicable in a commercial context.
  • No monetization strategy: No pricing model, subscription plans, or business model are discussed.

Evidence All risks inferred from lack of evidence and self-reported nature.

Back to contents

Diligence Questions To Ask The Founders

  1. Has anyone else used NKKakeist beyond yourself? If so, what feedback did you receive?
  2. Are there any known limitations in how well it handles certain types of financial data (e.g., international transfers, complex investment flows)?
  3. What are your plans for scaling or commercializing the tool?
  4. How do you plan to ensure long-term maintenance and updates given that it's currently a solo project?
  5. Have you considered integrating with existing finance platforms (e.g., APIs from banks or fintechs)?
  6. What is the expected timeline for moving from prototype to a stable, scalable product?

Back to contents

Investment/Partnership Verdict

There is no evidence of traction, revenue, or customer base. The project is described as a personal tool built by one developer and submitted to a hackathon.

It shows promise in solving a real-world problem — particularly for users who deal with complex financial flows and require transparency in their data handling. However, it lacks commercial viability indicators such as:

  • Market validation
  • Product-market fit
  • Scalable architecture
  • Monetization strategy

Verdict Not ready for investment or partnership at this stage. It may be a strong candidate for future development if the author builds out a user base and demonstrates traction.

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.