@jenidesignns · X

Day 19 challenge by @IwuezeAmarachi built with Claude AI 🤖 Live link:

@zeuscode21 · X

Save time when building with

@ErwanCodes · X

I created Helios Control entirely with Grok 4.5. From concept to code, the whole project was generated, structured, and built with AI. A real test to see how far vibe coding can go in 2026. Live app 👇 Thank @SpaceXAI & @cursor_ai !

@Lathithaa_Mdayi · X

@clicknify · X

@ShakibMd93031 · X

Built an Equipment Rental Management System to simplify rentals, payments, and equipment tracking. Looking for businesses interested in a demo or a customized solution.

@AiShivam · X

AgentStacKPro is an OS for AI agents designed to make them production-ready, and it holds incredible potential. You can also check out the project I currently developed

@shiftibis · X

Indie project 📝 ReBox: visual boards where color = group and branches = a file tree — both at once. Share links open without login (anyone with the link can edit). A Claude connector builds boards for you. English UI just shipped. #buildinpublic

@VMS2907 · X

Get your office to get meaningful output from AI -

@max21226 · X

Let's connect my friend. I'm building a product launch kit creator and organizer. Love to see what #solofounder #buildinpublic

videlov · HN

I was interested in answering this question so I built a benchmark comparing git, jj and gitbutler in agentic context https://vcbench.dev/ Disclaimer - I am a co-founder of GitButler

@harryjwang · X

I've used many of the major conference systems. Plenty still have docs as an unsearchable static site — or worse, as PDFs that stopped tracking the product three versions ago. Somehow, still true in 2026. We took an AI-first path with instead. Our docs are generated from the codebase itself. A custom Claude Code skill writes each page and retakes the screenshots whenever a feature changes — so the docs don't drift from the product. Every page still gets reviewed by a human before it ships. Now you can talk to them, too. We just shipped "Ask AI" over our docs: This feature also turned out to be a nice teaching case for agentic RAG vs. classic RAG: • Classic RAG: chunk → embed → vector DB → retrieve once, by fixed rules • Agentic RAG: hand the model a search tool and let it drive — write a query, read the results, rewrite, retry At more than 100 pages, still no vector database needed. And every answer cites the exact page it came from. #Age