Lightsplit
Split shared expenses inside Telegram and LINE chats
Lightsplit launched on May 3, 2026 with 3 votes, #3,449 of 20,538 launches that month and more than 50% of that year's launches.
What it does
Most expense splitters make every friend download a separate app. Lightsplit lives inside Telegram and LINE, where your group already chats. Add the bot, log expenses with quick commands, and see who owes whom in real time. Multi-currency with auto-conversion, smart settlement that minimizes payments, and a built-in Mini App for richer flows when you need them. No app to install. No sign-ups for friends. Just split where you already chat.
Lightsplit is the simplest way to split expenses with LINE and Telegram integration. Track, split, and settle bills automatically, with multi-currency support for all your group needs.
Lightsplit tracks every shared expense and tells everyone exactly what they owe. Works right inside LINE and Telegram, no app download needed. See what people are saying about splitting expenses with Lightsplit. “ We used Lightsplit for our 10-day Japan trip. Everyone knew exactly what they owed, no spreadsheet drama. ” “ As roommates, we split rent, groceries, and utilities. Lightsplit keeps everything transparent and fair. ” “ I love that it works right in Telegram. No need to get everyone to download another app. ” Powerful features that make splitting expenses feel effortless, not like a part-time job. Snap a photo of your receipt and let AI do the work. Automatically detects items,…from lightsplit.com
Does a similar job
all alternatives →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