I made Byte, a native Mac app for chatting with AI models. You bring your own API key (Claude, GPT, Gemini, whatever you use) and pay the provider directly instead of stacking a subscription on top. Or skip keys entirely and run local models like Llama for free.
I ve been mapping out a roadmap for an Instagram Creator & Growth Platform aimed at moving beyond simple scheduling. The goal is to build a "Media Ops" ecosystem that handles everything from deep tech to financial compliance.
However, before diving deep into development, I d love to get some "Makers' perspective" on whether such a comprehensive tool solves a real pain point or if it s trying to do too much at once.
Small thing for anyone who supported us on launch and works on open source. We're comping the Hobby plan for the next 100 OSS maintainers who apply. One month, full plan, no card.
I got obsessed with a weird edge case: cruise ports. You get off the ship at 8am, you're back on by 4pm, and if you're late the ship leaves without you. No other kind of travel has that hard a deadline.
Most people either pay for a scripted ship excursion or wing it and hope they judged the walk back correctly. So I stress-tested Routinex against that exact constraint give it a port and your reboarding time, and it plans backward from "get back with room to spare."
Clay and Apollo market their product extremely well and they are blasted all over LinkedIn and X.
I decided to try both out and Clay is definitely not easy to use. I've heard great things, but as a first time found beginning my lead generation and prospecting phase, there has to be easier tools. The learning curve felt steep to me.
Let s be honest: Building an app is the easy part now. But 35% of startups still fail because they build something the market doesn't actually need. Most AI "research" tools just give you plausible-sounding lies.
We built an agentic workflow that doesn't just "chat" it executes the boring, painful parts of market validation.
For years we tracked time across scattered Excel files nothing integrated, no security, and constant version-control headaches.
After months of building, we finally have something that works for us: LogSheet.ch
It's one simple app for daily time tracking (with automatic lunch and overtime calculations), one-click holiday requests with a full team calendar for managers, multi-company management with role-based access, and clean Excel exports with live formulas and an auditable archive.
Best part: every new company that registers in 2026 gets LogSheet free and stays free forever.
I'm testing Haku, a small Telegram-native AI companion beta. The product thesis is simple: most companion chats feel good on day one, then start to feel generic when corrections, tone, boundaries, and running context don't survive across days.
The beta is focused on memory + continuity rather than a bigger character marketplace. It is early, free to try, and I am mainly looking for people who care enough to stress-test whether the companion still feels coherent after several conversations.
