Can AI replace Splitwise?
The ledger and the debt math are a solved problem; a link-shared DIY version covers a household or one trip in a single sitting, no accounts needed. The gap is not code, it is adoption: Splitwise works because the whole group already has it installed, and nobody downloads your homebrew app for one weekend away. Build it for the people who share your fridge; for everyone else, the moat is other people's phones.
01What it costs
Checked Aug 11, 2026 · source: splitwise.com. The free tier still creates groups, splits and simplifies debts, but caps expense adds at roughly three per day, shows ads, and keeps receipt scanning and automatic currency conversion for Pro.
02Could AI build it for you?
The core job: Create link-shared groups, log expenses with flexible splits, and settle up via minimum cash flow debt simplification.
The rare app whose moat is other people's phones.
03What you'd give up
- native iOS and Android apps, push reminders included
- your friends' existing accounts and muscle memory
- receipt scanning and itemized splits
- automatic currency conversion at live rates
- settle-up integrations with payment apps
Splitwise sits where the friction is lowest: everyone already has an account, the apps are polished, and the balance quietly nags people so you do not have to. Pro mostly sells relief from the free tier's daily expense cap and the ads, plus receipt scanning and automatic currency conversion for trips. The subscription monetizes the fact that the group, not you, picks the tool.
04Free and cheaper alternatives
Share a link, split, settle. No accounts, no ads. Use their instance or run your own.
spliit.app →Free and huge in Europe; closed source and bunq-owned, new signups get a bunq account, and CSV export left with the old Premium.
tricount.com →Around since 2011, proudly boring, in declared maintenance mode; use their free instance or one docker run.
ihatemoney.org →Splitwise for people who already run Nextcloud; pairs with the MoneyBuster Android app.
apps.nextcloud.com →05The build prompt
Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version.
Build a self-hosted group expense splitter: a single web app, no user accounts. Stack: Node 22, Express, better-sqlite3, server-rendered EJS, htmx for interactivity. No build step, no SPA framework. Features: - Groups are created with one click and live at an unguessable URL (nanoid, 21 chars). The link is the auth model; say so plainly in the README. - Members are names typed into the group, nothing more. - Expenses: payer, amount, currency, date, note, category, and a split that can be equal, exact amounts, percentages, or shares. - A balances view per group: each member's net position, plus a settle-up plan computed with minimum cash flow debt simplification. - Reimbursements logged as a special expense type. - Multi-currency: amounts stored in their own currency; a per-group manual rate table converts to the group's base currency. No external rate API. - Edit and delete with a simple activity log. - Export any group as CSV and JSON. Storage: one SQLite file at ./data/app.db; path via .env. Ship a Dockerfile, a docker-compose.yml, and a README covering backups and reverse-proxy setup. Out of scope, deliberately: accounts and OAuth, push notifications, receipt scanning, live exchange rates, payment integrations, native mobile apps. A PWA manifest so it installs to a home screen is the only concession.
06Open-source starting points
- spliit: open-source reference implementation worth stealing ideas from
- minimum cash flow algorithm: the debt simplification trick, explained
App prices, verdicts, alternatives and build prompts are adapted from Can I Vibecode It? (MIT License, © 2026 Rob Hallam). Each price shows the date it was checked and its source. Prices change; confirm on the vendor's site before you decide.
Get new verdicts in your inbox.
One short email when new verdicts land: what AI can now do for you, and what it still gets wrong. No spam. Unsubscribe anytime.