I built a free tool that simplifies generating Access Tokens for Shopify custom apps.
If you've worked with Shopify's API since their early 2026 update, you know the process got significantly worse multiple screens, manual URL copying, and way too many steps for something that should be simple.
Hey, We're building an open source tool for creating live, interactive product demos. Think Navattic or Arcade, but self-hosted and free to run yourself. The repo is at https://github.com/exploitx3/liv... and our homepage is https://livedemo.ai.
We kept running into the same problem: you build something great, but getting prospects or users to actually understand it before they sign up (or churn) is surprisingly hard. Existing demo tools are expensive and make it painful to export or customize anything. That felt wrong, so we built LiveDemo.ai. Here's what it does:
Capture and replay your product as an interactive walkthrough, with no heavy instrumentation required Self-hosted so your demo content and user data stay on your infrastructure, not ours Open source under MIT so you can inspect it, fork it, and extend it however you need
We've kept setup as simple as possible. The repo includes Docker local setup and one-click deploy for kubernetes so you can be up and running in minutes.(Will add the kubernetes manifest soon)
Hey everyone! I'm Hari from Zuno - we started out as a sustainability data management platform with built in custom dashboarding. But as we went more and more enterprise, the dashboards started to get more and more complex which led us down the path of using PowerBI embed to build these.
After years on the VC side evaluating hundreds of pitch decks, I kept seeing the same problem - great companies losing deals because the story wasn't landing. So I switched sides.
After selling my previous AI fintech startup in August 2025, I finally had the time to work on a side project I had been thinking about for a while. I became fascinated by one specific question: Can LLMs meaningfully answer questions about the future?
When I started digging deeper, I found benchmarks and platforms like ForecastBench [1], Prophet Arena [2], and Metaculus [3]. What stood out was that the results consistently suggested something interesting: LLMs are already outperforming many humans in forecasting tasks, and in some cases they are getting surprisingly close to superforecasters (experts with exceptional long-term prediction track records).
That made me think: if the benchmarks already show this potential, then the real missing piece is not the model capability itself, but the infrastructure around it -> So I started building exactly that.
The idea is simple: any user can ask a question about the future, and the system continuously tracks that question over time. Instead of giving a one-off answer, the LLM monitors developments, updates its reasoning, and improves the forecast as new information becomes available.
Hey PH community! I'm a solo dev who built two native Mac apps to scratch my own itches. Sharing them here in case they're useful to anyone else.
TokenBar (tokenbar.site) If you use multiple AI APIs (OpenAI, Claude, Gemini, Mistral, etc.), you know the pain of checking 5+ provider dashboards to track your spending. TokenBar sits in your Mac menu bar and shows real-time credit balances for 20+ AI providers in one glance. The Pro version ($5 lifetime) adds spending spike alerts so you catch runaway scripts before they burn through your credits. No subscription.
