Envelope-style budgeting logic (assign income to categories, track spend against them) is clear, well-specified arithmetic. The gap is entirely at live bank-account sync — and there's a genuinely good open-source project already built around this exact idea.
Borderline
Effort: a weekendRunning cost: $10–$20/mo
Why CanICodeThis says Borderline
Budget categories with monthly limits and manually-logged transactions are ordinary CRUD
Rolling over unspent budget to next month is straightforward arithmetic
A dashboard showing budget vs. actual per category is standard charting
The parts that'll cause problems
Live bank-account sync (Plaid-style aggregation) is a serious integration and security surface — the same caution applies here as to every finance app on the register
CSV import from bank statements is a reasonable, much safer middle ground if you want less manual entry
Shared household budgets (multiple people, one budget) add real multi-user complexity
How I'd build this
frontend
Next.js
database
Supabase
auth
Supabase Auth
hosting
Vercel / Cloudflare Pages
MVP scope
Budget categories with monthly limits
Manual transaction entry or CSV import
Unspent budget rolling over to next month
A dashboard showing budget vs. actual
Postpone to v2
Live bank-account sync
Shared household budgets with multiple users
Recurring transaction detection
What it actually costs to build
AI agent — with a subscription (Claude Pro/Max, Cursor, etc.)
$0 marginal
AI agent — pay-per-use API, no subscription
$43–$86 one-time
Hosting, once it's running
$10–$20/mo
Domain name, if you want your own
~$12/yr
Existing tools solving a similar problem typically run $14.99–$14.99/mo — see how they compare below.
The build prompt
Build me an envelope-budgeting app: monthly income assigned to categories, transactions logged manually or imported from a CSV bank export, unspent category balances rolling over to next month. A dashboard showing budget vs. actual per category. SQLite behind a small API, single-user login. Don't attempt live bank-account sync — CSV import is the safer, sufficient starting point.