Hey Product Hunt I m Patrick, and Sift is the first app I ve shipped solo this year.
The idea came from a simple frustration: I d flip over a box of something marketed as healthy or clean, squint at the ingredients, and have no real way to evaluate what I was looking at. Reading labels is a skill most of us were never taught.
So I built Sift to do the work for you: Scan any food label or barcode Get an honest health score (no brand favoritism) Ask the Sift Assistant questions like is maltodextrin actually bad? in plain English Family plan: up to 6 allergen profiles with per-person safety indicators on every scan
Free to download. Premium is $4.99/mo for unlimited scans + unlimited chat. Family is $9.99/mo.
Stack: Expo, React Native, Supabase, RevenueCat, Claude API for the assistant.
What I d love from you: 1. Scan something in your pantry you think is healthy and tell me what you found 2. Brutal feedback on the onboarding flow 3. Any ingredient or category Sift gets wrong I want to know
I ll be in the comments all day. Thanks for checking it out
the app listens to upi payment notifications and automatically add them to them as expenses or income, the data is stored locally and the app does not connect to the internet, so no data is being collected and sent, it also has features to split bill with nearby devices of using bluetooth, creating an group audience i.e. if one person uses the app it's highly likely for him to refer others. it send an immediate notification to adress the description and category of each transaction so u never skip a bill. I want know if this is something actually fun or basic bs that no one cares about, any comment or opinion will definitely help a lot. this is the ui of the app. going for a straight forward just what u need right where u need it vibe.
I've been building IntelGraph, an open-source Threat Intelligence Platform that correlates IOCs from multiple sources, builds a knowledge graph, and explains why each alert is generated through an evidence-based workflow.
I'm currently looking for feedback from cybersecurity professionals, SOC analysts, threat intelligence teams, and security researchers.
AI didn't slow your team down. Misalignment and lack of visibility did. AI just exposed it. We spent the last two years doing agentic engineering work across our own teams and clients. Same thing kept happening: code was moving fast, everything around it wasn't. Docs weeks behind. Tickets missing. Leadership asking what was shipping and getting answers that depended on someone remembering to update the board. Speed up one layer of the system and every gap compounds fast: the more code ships, the less of that speed survives. We built FlyDocs to close those gaps. It runs inside your existing AI coding workflow, connecting your editor to Linear or Jira without changing how developers work. You define your team's standards once, and every AI session inherits them. When an agent does the work, it opens the issue, moves it through your workflow, and updates the board on its own. The lead watches the card cross the board in real time while the dev is still in the editor. We're launching on Product Hunt tomorrow. If you're shipping with AI-assisted development and this sounds familiar, follow us on PH to get notified when we go live: Launch Page Happy to answer questions in the comments, what part of this breaks down first on your team?
A few months ago I started using OpenWolf, a project that gives Claude Code a persistent "second brain" by indexing the project, tracking context, and remembering previous decisions.
I really liked the idea, but after using it on larger and longer-lived projects I ran into a few practical problems:
So I started building Focusel - a desktop workspace that brings everything together with AI-powered roadmaps, flashcards, mind maps, and distraction-free learning.
Still early, and I'd love honest feedback from fellow makers.
