Marcel

@langpavel you replied to some of my PRs and would like to get in touch.

@usenaive Naive

Your AI Employees are now fully human. > Provisioned LLC > Email inbox, Bank Account > Computer + Browser > Full-stack App Deployment > Invoicing > Mobile Phone ... and more. Repost + Comment "Naive" for $100 in FREE Credits today. Case studies ↓

@katibmoe One

Introducing One. The simplest way to connect and monitor AI agents to hundreds of apps. And we’re open-sourcing the world’s largest integration database powering it: 47,000 agentic actions across 250+ apps. RT + comment “One” for access & 1M free API requests/month.

@markoilico I'll check it out!

If you're now designing or redesigning a website, this will help you a lot. I recently curated the best hero sections, footers, social proof and other website parts because I got tired of having 15+ tabs open (even with Mobbin). Giving it away 100% free. Comment on this post, and I'll send a Figma link to your inbox!

@actualTimWilson Is there a public demo of this? That looks super cool!

Satisfying isometric experiments

@Teddarific Yah, feel free to send it over!

This UI was one-shotted using a video as the prompt. It captures interactions, full flows, and animations — stuff that is typically painful to prompt for. Looking for early adopters to try our new Video → UI feature 👀

@borahm You have a link? Would love to check it out!

I love Granola, but what I really wanted was a simple markdown transcript for my agent. So I built something that automatically creates a markdown file, adds speaker diarization, and sends it straight to my agent. I have been using it for couple months now.

@emanueledpt Great stuff! Would love to be able to view and manage all sessions, not just one per qr

I just made Codex with Remote Control for your iPhone! And it's open-source! This is my first OSS project, so this is a special one I've been obsessed with Codex since it came out I loved it so much that I wanted to use it on my phone And so Remodex was born! Remodex lets you send prompts to Codex, manage git, and watch tasks complete all from your phone! Your Mac does all the heavy lifting locally. Your phone is just the controller. How it works: → Download the package → Run "remodex up" → A QR code appears in your terminal → Scan it with the Remodex iOS app → Happy coding from anywhere! I built it in 2 nights because the idea wouldn't let me sleep Go enjoy it! 👇

@ttx3000 @grok what website is this

MagicBook is the most fun way to create AI illustrations. It’s inspired by the charm of scrapbooking, hands-on, personal, and a little imperfect. I could automate everything, but I believe there’s magic in putting together something yourself.

@tejgw Chronicle

Cursor for Slides is finally here Watch the first 47 seconds. Then try going back to your old deck tool Reply "Chronicle" + RT to get two months of Pro for free. Make sure you follow so I can DM you asap.

@solomon_visuals Background

Need this high quality backgrounds for your next video ~comment "background"~ And I will send it to you📩

effortlessly and seamlessly transition between text with <TextMorph/> built on Intl.Locale and Web Animations API. dependency-free and ready to use in your favourite framework ✨ → torph.lochie.me

@sandykoshti @framer Ametrix

🎉 Giveaway Alert, 24 Hours Only..! My @framer template Ametrix is officially live on the Framer Marketplace. Preview Link: framer.com/marketplace/te… Normally priced at $99, but for the next 24 hours, I’m giving it away for FREE. Built for modern SaaS & AI startups, 8 pages, 25+ sections, fully responsive. To get it free: 1. Comment “Ametrix” 2. Repost 3. Make sure you're following so I can DM you the discount code This giveaway ends in 24 hours! ⏰

@learnframer @framer GRID

introducing: kinetic grid for @framer use this to add a cursor-reactive grid with subtle motion and click interaction comment “GRID” and i’ll send you the component for free :)

@k_grajeda Is there a live demo of this? 👀🥳

hypnotizing UI

@Motion_Viz INSTRUCT

Spent weeks perfecting AI system prompts. Here's what most people get wrong: They write instructions. I engineer architectures. The difference: ❌ "You are a helpful design assistant. Create landing pages when asked." ✓ "You are a conversion-focused UI architect. End goal: production-ready landing page that converts skeptical B2B buyers. Constraints: no gradients, max 3 colors, 8px radius. Style: swiss minimal, editorial whitespace. Output: section-by-section, not full page. Validate each section against the trust test before proceeding." The 5-step method: 1. Define the end goal first (what does success look like?) 2. Ask AI to draft a system prompt for that goal 3. Extract every important keyword and constraint 4. Rewrite with your domain expertise layered in 5. Run through Gemini Gem to structure it as clear instruction blocks Works on Claude design. Cursor code. Custom agents. Everything. Specificity isn't optional. It's the entire game. Like + reply "INSTRUCT" for my full prompt engineering method. (must be following for DM)

@v_computer 🙏🙏

Yep, the rumors are true. We are releasing the easiest way to build Web Apps and Mobile Apps with Claude Code from your browser (with custom skills) next week. Comment below for credits + early access. Then Check DM.

How can @useblacksmith restrict their service to only corporate organizations? By doing so, you're wasting thousands of hours of time for developers who are trying to contribute to open source projects. They sign up for the service, but then get disappointed when they can't use the tool.

@tbsrnstrm Would love to give it a spin!

A popular request from folks on the Alpha has been to copy things by dragging while holding down option. Easy enough in theory, kind of essential - but man such a gnarly one to get working right.. 🫠 This will be in Alpha no 3, and another batch will be getting an invite soon.