Finance and accounting decision

KASH

A competent developer can build a usable self-hosted replacement for the core budgeting and chat features (using open-source personal-finance projects and an aggregator), but the vendor's accredited aggregator partnership, managed WhatsApp reliability and bundled support/credits are hard to reproduce, so keeping the paid service is reasonable for full parity.

Visit website
You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off88 h to build

$120/mo6 h/mo upkeep

No published price to break even against.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All KASH alternatives, with the arithmetic →

What a replacement has to do

  • Ingest bank transactions, classify and store them, expose balances and budgets, answer natural-language queries via chat interfaces (WhatsApp / LLM), and show a simple dashboard.

What it still won’t have

  • DSP2 / ACPR accredited aggregator partnership (official certification and any partner-negotiated pricing)
  • Managed WhatsApp / phone-number reliability and scale that a vendor-grade integration provides
  • Bundled 24/7 customer-facing support and included IA credits
  • Proprietary product polish, simulators, and prebuilt ChatGPT/Claude connectors

What remains hard

  • Compliance and regulationVia notre partenaire Bridge, leader de l'open banking en France et en Europe. Agrégateur certifié DSP2 et accrédité ACPR.
Read the build prompt

First-year cost

No published price

KASH does not publish a price we could read, so there is nothing to compare against. What building costs is below.

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

Time you would spend

—

—

What you would spend

What we assumed

The verdict above measures whether you could build it. This one is only about money.

Runnable build prompt

Not run yet
Build a self-hosted personal finance assistant using Node.js (NestJS) + Postgres + Redis. Scope: (1) user auth, Postgres schema for users/accounts/transactions/budgets, (2) connector module to a PSD2/open-banking aggregator (configurable base URL and API keys), (3) ETL worker to import and normalize transactions with a rules engine and basic ML categorizer, (4) WhatsApp bot using Twilio's WhatsApp API that forwards user messages to an LLM and returns templated answers, (5) small React dashboard showing balances, recent transactions, budget planner, and CSV export, (6) LLM integration layer supporting OpenAI/Anthropic with stored prompt templates and conversation state. Out of scope: obtaining DSP2/ACPR accreditation, multitenant billing, advanced simulators, and native mobile apps. Include error handling, retries for aggregator calls, authentication and authorization tests, and unit tests for ETL and API endpoints.
How we checked5 sources · 2/3 runs agreed · evidence score 57

How the score was reached

  • Partly verdict base52
  • An open-source build was found+5
  • 5 cited sources+3
  • Hard moats found in the evidence-3
  • Evidence score57

The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.

How scoring works →

Cited sources · 5

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat quoted from the page