All activity
Handuoleft a comment
The real time collaboration on a single canvas is a smart approach to AI design. Being able to create and edit together with the AI instead of going back and forth feels like a huge workflow improvement. Congrats on the launch!
FlatoAI designer that creates and edits with you — on one canvas.
Handuoleft a comment
An open standard for generative UI is exactly what the ecosystem needs. Having 10K+ developers already using this through Thesys gives it real momentum. Congrats on the launch!
OpenUIThe open standard for Generative UI
Handuoleft a comment
A natively multimodal embedding model that maps text, images, video, and audio into the same space is a big deal. Most embedding approaches still treat modalities separately, which creates friction when you want to do cross-modal search or retrieval. This should make building multimodal RAG systems much more straightforward.
Gemini Embedding 2Google's first natively multimodal embedding model
Handuoleft a comment
Having reliable web data extraction is one of those unglamorous but absolutely critical pieces for AI agents. The fact that most tools break on JS-heavy sites or waste tokens on full page dumps is a real pain point. A CLI that handles scraping, searching, and browsing in one place with clean output is exactly what the agent ecosystem needs. Nice work on the 6th launch!
Firecrawl CLIThe complete web data toolkit for AI agents
Handuoleft a comment
The idea of describing an edit and having it execute is a huge unlock. Video editing has always been this weird paradox where you know exactly what you want but spend hours clicking through timelines to get there. Running in the browser and supporting live collaboration makes this really accessible too. Congrats on the launch and the YC backing!
CardboardCursor for video editing
Handuoleft a comment
The semantic layer approach is really smart — having agents reason about backend primitives rather than just calling APIs changes the whole development model. The fact that it works inside existing IDEs like Cursor and Claude with no new UI to learn is a big plus. Congrats on the launch!
InsForgeGive agents everything they need to ship fullstack apps
Every like, bookmark, and share is a taste signal. Until now, only algorithms and ad networks profited from yours. Copus turns your taste into an asset you own. Save as you browse, and every curation grows a structured taste profile. Subscribe to people whose taste you trust. Share your profile with ChatGPT, Claude, Grok, Deepseek, or Mistral for answers that actually understand you. Monetize when people or AI access your curation. Open source, fully exportable, and becoming decentralized.
CopusTurn your taste into an asset you own
Handuoleft a comment
Hey Product Hunt! I'm Handuo, one of Copus's founders. We launched a version of Copus here more than a year ago. That version focuses on "content creation" and has since become a home for half a million Chinese fanfiction enthusiasts. This time we built a NEW Copus with a different focus: "curation". With more than a decade of the content creator era and now the power of AI, there is too much...
CopusTurn your taste into an asset you own
Handuoleft a comment
Thanks Ryan! Love that you are taking the anti-algorithm route too. It is honestly the hardest design challenge — resisting the urge to just optimize for engagement. We have been experimenting with letting people subscribe to curators they trust instead of feeds, which has worked really well. Would definitely be down to chat — we are actually launching Copus on PH tonight so this week is a bit...
What are you building, and what does your stack look like?
Ryan HendricksonJoin the discussion
Handuostarted a discussion
What is one article or video that completely changed your perspective?
We all have that one piece of content — an article, a talk, a thread — that genuinely changed how we think about something. For me it was "1,000 True Fans" by Kevin Kelly. The idea that you don't need millions of followers to build a sustainable creative career completely shifted how I think about building audiences. It is also one of the core ideas behind Copus — helping people build real,...
Handuoleft a comment
100% yes on shoutouts. We are launching Copus on Product Hunt tomorrow and we made sure to include shoutouts to the tools that helped us build it. It is genuine — these tools actually made our product possible. Beyond goodwill, shoutouts create real distribution. The tools you mention often share your launch with their communities, which can drive significant traffic. It is one of those rare...
Should you add a shoutout to your Product Hunt launch?
Jake CrumpJoin the discussion
Handuoleft a comment
The AI-first approach to e-commerce is smart. Building a store used to mean choosing between no-code tools that are limiting or custom development that is expensive. Having AI handle the setup and customization while still giving you a real, production-ready store is a great middle ground. Congrats on the launch!
Your Next StoreAI-first platform for building commerce stores, fast
Handuoleft a comment
Multi-agent code review is a great concept. Having different agents specialized for different types of issues — security, performance, logic errors — should catch things that a single-pass review would miss. Really like the approach of catching bugs early in AI-generated code specifically, since that is becoming the default way people write code now.
Claude Code ReviewMulti-agent review catching bugs early in AI-generated code
Handuoleft a comment
This is a really clever solution for video localization. The fact that you can translate text in videos without having to recreate the visuals saves so much time and production cost. For anyone doing content for international audiences, this removes one of the biggest barriers — you no longer need separate production workflows per language. Congrats on the launch!
Visual Translate by VozoTranslate text in your videos without recreating visuals
Handuostarted a discussion
Who are the best curators you follow online and why?
I've been thinking about how the people who curate information are becoming more valuable than the people who create it. There is so much content now that finding the signal in the noise is the real skill. Some of my favorite curators: - Brain Pickings (Maria Popova) — years of deep literary/philosophical curation - Stratechery (Ben Thompson) — best tech business analysis, carefully selected...
Handuostarted a discussion
What would you save if you could only keep 10 bookmarks?
Thought experiment: if you had to delete all your bookmarks and could only keep 10, which ones would survive? I think the answer reveals a lot about what we actually value vs what we mindlessly save. Most of us have hundreds or thousands of saved links we will never revisit. The ones that would make my cut: - 2-3 reference articles I genuinely go back to regularly - A couple of tools I use...
Handuoleft a comment
The first thing I vibecoded was a Chrome extension for Copus, our content curation platform. I had the core web app built traditionally, but needed a browser extension that lets people save articles, videos, and links from anywhere on the web with one click. Tool: Claude Code (Anthropic's CLI). Honestly it was a game-changer for extension development specifically because you can just describe...
What was the very first project you vibecoded with AI?
Handuoleft a comment
Right there with you — we're launching Copus tomorrow and feeling the exact same mix of excitement and nerves. What I've learned from the prep: the community engagement matters way more than follower count. We spent weeks genuinely commenting on other launches, joining forum discussions, and building real connections. That felt way more productive than just DMing people "please upvote." The...
Launching on Product Hunt Next Week... and Honestly, I'm Nervous
Imtiyaz Join the discussion
Handuoleft a comment
We're building Copus — a curation platform where people save, organize, and share the best content they find online. Think of it as turning your bookmarks into a living knowledge network others can discover. Stack: Next.js + TypeScript on the frontend, Node.js backend with PostgreSQL. Elasticsearch for search and discovery, Redis for caching. We also built a Chrome extension for the...
What are you building, and what does your stack look like?
Ryan HendricksonJoin the discussion
Handuoleft a comment
The idea of spinning up specialized agents in parallel and picking the best model for each step is really smart. Most AI tools try to do everything with one model, which leads to mediocre results across the board. The visual canvas where you can watch agents work in real time is a nice touch too — transparency in how AI arrives at deliverables builds a lot of trust.
Spine SwarmManage a team of AI agents that do real work