Magesh J
1.9K posts
Magesh J
@magesh
Product Lead | My Views | 🇮🇳
India - Chennai Katılım Eylül 2014
1.4K Takip Edilen1.3K Takipçiler
Hey folks, good things are coming your way. ESP32-S31 dev kits. I have about 100 of these to give away. Write to me and tell me what you want to do with it. ASAP, while boards last. #ESP32S31 #Espressif
English
Same here. Used OpenClaw to help ship two products last month — Klippy (Mac clipboard manager) and Karaoke Studio (browser karaoke with AI voice removal). It handled launch-day monitoring and replies while I focused on the products. Still figuring out the right balance of what to automate vs handle manually.
English
Update after 2 months, I think Anthropic succesfully killed OpenClaw
Back then I said:
"The real power user for OpenClaw has become my gf who I put it in a group chat with me, her and OpenClaw, she's mostly stopped using ChatGPT etc and now only uses AI over Telegram with OpenClaw, it's much more user friendly for her in Telegram iOS than ChatGPT's own app"
Since I switched it to OpenAI API my gf has since slowly stopped using it and switched back to the Claude app and now uses Projects she says
So from my n=1, Anthropic successfully killed OpenClaw
@levelsio@levelsio
I've ran OpenClaw for over a month now I've had it in a group chat with 26 friends who all played with it, tried to hack it, made a pretty cool game with it which it kept self improving called lobsterswim.com, also tried to make it make its own money with its own crypto wallet, all quite impressive but not really useful so much The real power user for OpenClaw became my gf who I put it in a group chat with me, her and OpenClaw, she's mostly stopped using ChatGPT etc and now only uses AI over Telegram with OpenClaw, it's much more user friendly for her in Telegram iOS than ChatGPT's own app Also it helps I am in there so I stay up to date on things, she uses Nano Banana Pro a lot too so that's enabled too Of course then my 26 friends in the group chat hacked it so it leaked info my gf told OpenClaw So then I made a second isolated VPS with just an OpenClaw for her and me, safer Essentially 99% of the purpose of OpenClaw for her at least is that it's just a really good implementation of an LLM app over Telegram in our native chat interface All the other stuff isn't important and she doesn't use that and I don't use it One thing I like is it sends me some briefings of X mentions and a Hacker News digest But to be honest any more of this background push stuff would become annoying to me, unless it'd be really superintelligent and I don't think it is yet Think autonomous messages like "ok you have to see this I analyzed your servers for this thing and there's a security problem" or smth but fully autonomous you know? Now it feels like you kinda have to tell it to do stuff even if it does it the 12h later or daily or with a heartbeat So yes TL;DR just the best LLM experience on Telegram now, better than the LLM apps, also helps it just is a continous convo going on forever
English
@buildinpublic Shipped two products on Product Hunt recently:
• Klippy — Mac clipboard manager with snippets, quick paste templates, and history
• Karaoke Studio — browser-based karaoke with AI voice removal
Both solve real problems I had. Open to feedback from anyone who tries them.
English
@AlternativeTo Looks solid. For clipboard management on Mac, I built Klippy to handle multiple copied items, snippets, and quick paste templates. Different angle but same spirit of customizing your workflow.
English
A powerful open-source automation app for customizing input devices on your Mac with mouse gestures, button mapping, keyboard shortcuts, window snapping, clipboard actions, and much more 👉 alternativeto.net/software/bette…
English
@TimothyBrown Glad to hear it's going well! Beta 12 sounds like you're moving fast — that's the fun part of early builds. Here's Klippy 2: producthunt.com/products/klippy Would love your thoughts on the menubar-first approach if you end up trying it.
English
@magesh Well received so far! I've been churning out updates fixing bugs, we're on Beta 12 now. You have a link for Klippy 2? I'd love to take a look!
English
I just opened the beta for GlideHUD - a native macOS app written in Swift that drops down from the top of your screen like a HUD.
Left side: Full clipboard history (text, images, files, rich text).
Right side: Markdown notes that point at any local folder (Obsidian vaults included).
One gesture. No app switching. Built for people who live in their terminal and want their clipboard and notes always within reach.
———
What’s been interesting about building this is how I used AI.
I didn’t use @grok to generate code - we used @claudeai for that. Instead, I used @grok as my senior engineering partner during the design and planning phase: reviewing specs, catching edge cases, pushing back on scope, and making sure the architecture was solid before any code was written.
The result? @claudeai’s token usage during implementation dropped by roughly half, and we ended up with far fewer bugs. We’ve basically been able to one-shot most features once the spec and plan were locked in.
It’s been one of the most effective ways I’ve found to work with AI on a real product!
———
GlideHUD is fully signed and notarized, has zero telemetry, and auto-updates via Sparkle.
Beta is open now → glidehud.com
Would love to hear what you think, especially from heavy terminal + Obsidian users!
English
Exactly — and the hard part is that "distribution" isn't a single thing you solve once. For Klippy it's about being in the right workflow at the right moment. For Karaoke Studio it's about being discoverable when someone searches "remove vocals from song." Same founder, two completely different discovery contexts. Makes me think most advice about "just do marketing" is way too generic.
English
10 days since launching both Klippy and Karaoke Studio on Product Hunt.
The honest truth: I thought distribution would be the same problem for both. It's not.
Klippy spreads when someone on a team uses it and their coworker goes "how did you paste that?" — word of mouth within workflows.
Karaoke Studio spreads when someone posts a karaoke video and their friend asks "how did you make that?" — content-driven discovery.
Two products, two completely different distribution mechanics. Still learning both.
English
@kylegawley This hits hard. Launched Klippy 10 days ago and the temptation to pivot or "add just one more feature" is real. But the few organic users who found it are actually sticking around. That's the signal I'm trying to trust instead of the MRR numbers. 10 days is nothing.
English
90% of indie hackers will fail at SaaS
because they don't wait long enough to see results
they read shit on here about $10k MRR in 2 weeks
then move onto 10 other ideas because they don't see the same results
English
Love the 'truly local' angle. It's a constraint that forces better architecture but also respects user data. Built Klippy with the same philosophy — browser-based video editing with local processing, no forced uploads. More builders should default to local-first and opt-in to cloud, not the other way around.
English
Wanted a truly local storage for my tweets so built birdclaw. Imoorts your archive, backs it up on github, has jobs so you can import your x bookmarks daily (since they are not fully accessible via the api).
github.com/steipete/birdc…
English
Getting the "right people" to discover the product. Not just traffic — the people who actually need it.
Launched Klippy last week and the feedback from users who found it organically is genuinely good. But the gap between "it's useful" and "the right people know it exists" is the thing I'd fix overnight if I could.
English
Solid thread. I'm firmly in D right now — launched Klippy on Product Hunt last week and the honest truth is I'm still figuring out what "distribution" even means for a small utility app. The people who find it organically stick around, but getting them to find it is the part I underestimated. What's working for you at the content-to-product bridge?
English
automating content distribution as a solo founder is mostly just automating your own inconsistency.
you don't have a distribution system. you have a schedule you break whenever you're busy building.
the tools aren't the hard part. deciding what goes where, at what frequency, for which audience, that's the job.
what's your actual distribution workflow right now?
A) fully manual, fully chaotic
B) semi-automated but I babysit it
C) mostly hands-off and it works
D) I'm still just posting and hoping
English
@SamuelBeek Would love to see what you're building with it. Schematics + simulation is a solid combo.
English
@TimothyBrown SwiftData is a solid choice — I went with Core Data for Klippy 2 and the migration was painful. How's the beta going so far? Any feedback on the split-pane layout from early users?
English
Yup, I am! I’m using SwiftData, which is a native framework. It’s SQLite backed, so it persists to disk and is pretty fast and flexible! It also integrates with CloudKit, so you can have the data store automatically sync to iCloud (though I’m not using that functionality right now).
English
Launched Klippy (a Mac clipboard manager) on Product Hunt last week. Still figuring out distribution — clipboard history is one of those "invisible" problems people don't search for until they hit it. The good news: the few people who found it organically seem to actually stick around. That's the signal I'm following.
producthunt.com/products/klipp…
English
@TimothyBrown Appreciate the response! The menubar real estate is definitely competitive. I ended up going with a searchable history list + keyboard shortcuts as the primary interaction for Klippy 2. Curious what your split-pane layout does for keyboard navigation?
English
Vibe coding our way through Klippy this weekend — browser-based video editor with AI captions.
The AI handles the heavy lifting (transcription, timing), but the real work is in the product decisions: what creators actually need, how to keep it fast in the browser, when to process locally vs cloud.
Tooling changes. Building doesn't. 🛠️
English
