Auditfy
Snap a receipt. Get tax-ready reports for HK & TW.
Auditfy launched on May 28, 2026 with 2 votes, #6,288 of 20,538 launches that month. The site was not reachable when checked in September 2026.
What it does
Most receipt apps are built for US or EU taxes. Auditfy is built for Hong Kong. It reads handwritten tea restaurant bills, taxi receipts, and PayMe screenshots — and auto-maps them to IRD tax categories for BIR51 filing. Snap a receipt → AI extracts merchant, date, amount, tax items → auto-categorized → export tax-ready reports in one tap. Built by a Macau restaurant owner who spent years stuffing receipts into a shoebox. Now live on iOS.
Does a similar job
all alternatives →



ReceiptIQ Pro — Snap & Track Spending2025 · receiptiq.me · ▲13Hi HN! I’m a solo iOS dev who kept losing track of where my grocery and shopping money was going, so I built ReceiptIQ Pro. What it does: - Scan any receipt with on-device AI/OCR and instantly categorize the items. - Auto-build spending charts, budgets, and exportable CSVs—no manual typing. - Works offline; iCloud backup/restore optional. No data leaves your phone unless you choose to. - Small extras: warranty reminders, bill tracking, and income logging. Tech bits: - Swift/SwiftUI on iOS. - Apple’s Vision framework + my own ML post-processing. - A lightweight Python backend…

More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video

Source: Product Hunt launch ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com