Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Yes, CAD! Releasing today – my second open-source project. With AI rapidly learning how to output 3d models, I feel like I needed an app that standardized the way I made fast iterations, controlled versions per-chat, custom tools and interactions per-project and files ready to print at home! You... show more

Glauber

3,421 subscribers

37,674 views • 16 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

31 Comments

Glauber16 days ago

You can create something new, from scratch, or simply drag and drop a project you’ve been working on. This app is shortcut-heavy, check settings for more info.

KSM16 days ago

Every single website you make is so clean !! Care to suggest any skills or your workflow? Congrats on your launch @glauberxyz !

Glauber16 days ago

thank you! :) For this one I went for @shadcn UI preset to prototype, then refine the preset later. I use Figma to think about ideas in high-level structure. The refinement comes with usual Claude chat

KSM16 days ago

@shadcn love your design language man. everything you make looks so clean. followed to see what you build next!

Sami16 days ago

The per-chat versioning stood out to me. Once you start iterating on a shape, keeping track of which export came from what can get messy fast. Followed to see how this develops.

Glauber16 days ago

Glad you like it!

Kai15 days ago

truly incredible. this seems FAR BETTER than any random fusion MCP. And open source. thanks :))

Sean16 days ago

Very cool!

Glauber16 days ago

thanks!!

01azPublic16 days ago

Sending the part and click coordinates along with the message should save a lot of 'no, the other little cylinder' 😄

Subsidy Bro16 days ago

Nicely done. Keep up the great work!

Glauber16 days ago

Thank you

demmon standafer16 days ago

Mac only? :(

Glauber16 days ago

For now yes! I would need help to build and test for other systems. Hope that happens soon

E_genius16 days ago

version control per change for 3d models is the part nobody talks about. AI can spit out a model but diffing two meshes is still pain. does it handle that?

Kaveri Engine16 days ago

I don't understand. Is this a wrapper on some CAD engine or you built the CAD engine too? Can you share the link to the project source code?

Akash Soni 🇮🇳15 days ago

Wow Awesome

Shoaib khan16 days ago

Can we use this for indoor maps?

Charles Murlin16 days ago

Instructional manual included in the box?

Glauber16 days ago

You mean an onboarding?

Charles Murlin16 days ago

I am shopping at IKEA

anish15 days ago

a tool that standardizes how you iterate on ai generated 3d models fills a real gap, the versioning of each attempt is the part nobody has solved well

alalei16 days ago

@grok 这是什么

Nao16 days ago

Great work, Glauber!

Glauber15 days ago

thank you ;)

BitcoinCMP15 days ago

@grok can you give an current status of ai assist or intergrade CAD which one so far is trending in this space?

Ryan Mallin16 days ago

@bot can you look in to this. Let’s talk it through.

Crio Songo15 days ago

Great idea for aligning AI 3D output with rapid iteration. I will go check the project out later.

CloudDog15 days ago

open sourcing it right as AI starts eating 3d modeling is a bold move, respect

bassim15 days ago

awesome! i was building my own version of this a few weeks ago, this is much better! i appreciate you making this open source, will be fun to fork and iterate on whenever im back in the cad headspace

Marcelo Eduardo Oliveira16 days ago

Super cool Glauber !

Related Videos

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

I recreated Meta’s new AI Glasses on my Quest, and the complete source code is available! 👓 Hey everyone! I’ve received a lot of feedback and messages about my latest project, where I used the Quest to recreate the features shown during Meta’s keynote. To answer your questions I decided to create a cool video to explain how I built it but also, share the full source code on Patreon 👇 Watch the making-of: Download the source code: This project includes: ✨ A UI navigable with microgestures 🤏 A pinch & twist hand-tracking input system 🎧 An audio player with volume control via pinch & twist 📸 A camera that zooms with pinch & twist 🖼️ A carousel to browse captured pictures 🧠 And a contextual AI that reacts to what you’re looking at Hope you guys will like it and that it will help you on your own project!! 😊

Quentin Valembois

15,977 views • 1 year ago

Try this out, it’s really cool! You can sketch a mockup, talk about what it should look like, and in seconds the UI is built. Powered by Groq Inc. Then you can iterate with voice to make improvements. (App is open source, btw 🔥)

Try this out, it’s really cool! You can sketch a mockup, talk about what it should look like, and in seconds the UI is built. Powered by Groq Inc. Then you can iterate with voice to make improvements. (App is open source, btw 🔥)

Ben Klieger

142,674 views • 1 year ago

I’m obsessed with this review on the Comfy Cubz, they made the diaper sound so cool. I’m still shocked that i even made diaper, as that has always been my biggest goal for starting this shop. Going from selling wristbands on etsy with a very small budget (bootstrapped it), to being able to save to the point I can can invest in a DIAPER. 🤯 I feel like my dream came true, and to see videos like this makes me feel accomplished that i made a good first diaper 😭😭😭 It’s so surreal, and I have to give a big thanks to the community for supporting me. Thank you so much, I honestly can’t tell you how much I appreciate everything. Even the likes and sweet comments, to buying my items. It’s been an amazing adventure and something I hope I can do for many years! I love creating things for this community 🥺

Sensitive content

I’m obsessed with this review on the Comfy Cubz, they made the diaper sound so cool. I’m still shocked that i even made diaper, as that has always been my biggest goal for starting this shop. Going from selling wristbands on etsy with a very small budget (bootstrapped it), to being able to save to the point I can can invest in a DIAPER. 🤯 I feel like my dream came true, and to see videos like this makes me feel accomplished that i made a good first diaper 😭😭😭 It’s so surreal, and I have to give a big thanks to the community for supporting me. Thank you so much, I honestly can’t tell you how much I appreciate everything. Even the likes and sweet comments, to buying my items. It’s been an amazing adventure and something I hope I can do for many years! I love creating things for this community 🥺

Lil Comforts

18,153 views • 2 years ago

The best way to learn about AI is to build an AI app yourself. With tools like Bubble and OpenAI, you can create apps like an AI chatbot without writing code 🤯 Stay ahead on AI and start learning today:

The best way to learn about AI is to build an AI app yourself. With tools like Bubble and OpenAI, you can create apps like an AI chatbot without writing code 🤯 Stay ahead on AI and start learning today:

Seth Kramer

2,614,004 views • 3 years ago

My buddy who works in CAD said AI isn't good enough for him yet. I took that as a challenge and wanted to prove to him this is a limitation of CAD tools, not the models. 3 beers later, we decided to try something out. Personal CAD software that builds CAD models. I'll let you be the judge...

My buddy who works in CAD said AI isn't good enough for him yet. I took that as a challenge and wanted to prove to him this is a limitation of CAD tools, not the models. 3 beers later, we decided to try something out. Personal CAD software that builds CAD models. I'll let you be the judge...

CJ Hess

117,162 views • 25 days ago

Zara Larsson answers what was the key to getting out of the Khia Asylum. “I’ve always known I’m a cool girl. I think my taste is good or fun, it’s my taste. I like what I do. I just need to express it to the world so they can understand. And now I feel like I have, and people connect with it because I’m just being true to myself. But I kind of feel like I don’t like when people say that they’re a flop. I don’t say that, you know what I mean? Don’t manifest it. No, because it doesn’t matter, what even is that, you know?

Zara Larsson answers what was the key to getting out of the Khia Asylum. “I’ve always known I’m a cool girl. I think my taste is good or fun, it’s my taste. I like what I do. I just need to express it to the world so they can understand. And now I feel like I have, and people connect with it because I’m just being true to myself. But I kind of feel like I don’t like when people say that they’re a flop. I don’t say that, you know what I mean? Don’t manifest it. No, because it doesn’t matter, what even is that, you know?

Updates Zara Larsson

30,001 views • 7 months ago

A highly affordable, fully 3D-printed robotic arm. [📍 open source] Features: > Fully 3D printed design > 7+1 DOF > or physical AI research & imitation learning Zero custom hardware needed, just print and add your servo kit! > URDF files > STEP & STL files > Step-by-step assembly manual > Ready-to-print Bambu Lab projects Great project, Alex Batsuev! Download and build yours here: —— Weekly robotics and AI insights. Subscribe free:

A highly affordable, fully 3D-printed robotic arm. [📍 open source] Features: > Fully 3D printed design > 7+1 DOF > or physical AI research & imitation learning Zero custom hardware needed, just print and add your servo kit! > URDF files > STEP & STL files > Step-by-step assembly manual > Ready-to-print Bambu Lab projects Great project, Alex Batsuev! Download and build yours here: —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

36,556 views • 8 months ago

Working on a cool project that I will launch in the fall and I am sure many of you will like. Come and ride with me!

Working on a cool project that I will launch in the fall and I am sure many of you will like. Come and ride with me!

Iñigo San Millán

11,784 views • 1 month ago

Old Art to full 3D using Cinema 4D . Created a free and open-source plugin to bring Hunyuan 3D directly into Cinema 4D. This workflow combines multiple tools that are available today into a single, cohesive pipeline. I wanted to show that AI is never an end product by itself, it’s not the finality. Used properly, AI becomes an extremely powerful tool that lets you build exactly what you want. I hope you like it. The final step will be to bake all textures so I can share the project as a WebGL experience, a small interactive website to explore it directly in the browser. Made with heart, and with fal ❤️

Old Art to full 3D using Cinema 4D . Created a free and open-source plugin to bring Hunyuan 3D directly into Cinema 4D. This workflow combines multiple tools that are available today into a single, cohesive pipeline. I wanted to show that AI is never an end product by itself, it’s not the finality. Used properly, AI becomes an extremely powerful tool that lets you build exactly what you want. I hope you like it. The final step will be to bake all textures so I can share the project as a WebGL experience, a small interactive website to explore it directly in the browser. Made with heart, and with fal ❤️

Lovis Odin

21,909 views • 9 months ago

I have revived Javi Lopez ⛩️'s 28 year old custom map he made and made a web-based Quake 2 with Fable on fast mode 🤓 You can now play it here: 👉 👈 It took a bit of hacking because the textures didn't load the first time, so I repacked some PAK files and now it works! AI is so good at reviving old stuff from your backups, I was always waiting for some backup app to come to finally be able to browse all my old files and figure stuff out from it, and now you can with AI

I have revived Javi Lopez ⛩️'s 28 year old custom map he made and made a web-based Quake 2 with Fable on fast mode 🤓 You can now play it here: 👉 👈 It took a bit of hacking because the textures didn't load the first time, so I repacked some PAK files and now it works! AI is so good at reviving old stuff from your backups, I was always waiting for some backup app to come to finally be able to browse all my old files and figure stuff out from it, and now you can with AI

@levelsio

208,405 views • 4 months ago

I’ve been messing around with AI 3D tools lately, and I honestly didn’t expect this to work as well as it did. I gave Hyper3D a single reference with information of the same object and basically told it to figure out the 3D workflow for me. What surprised me was that it didn’t just generate a model from one image. It actually understood the different views and used them together to build a complete asset. And then you can keep working on it. With the Low-Poly N-GONS workflow, I could ask it to add custom controls for different parts, change dimensions, create animations, and even change specific materials just by describing what I wanted. So it feels less like “generate a 3D model and download it” and more like having something you can actually keep iterating on. Generate something → look at it → tell it what to change → keep going. I’ve been having a lot of fun experimenting with this. Try Agentic Mode on Hyper3D by Deemos #Hyper3D #DeemosTech #Rodin #AI3D #AgenticMode #3DModeling #AI

I’ve been messing around with AI 3D tools lately, and I honestly didn’t expect this to work as well as it did. I gave Hyper3D a single reference with information of the same object and basically told it to figure out the 3D workflow for me. What surprised me was that it didn’t just generate a model from one image. It actually understood the different views and used them together to build a complete asset. And then you can keep working on it. With the Low-Poly N-GONS workflow, I could ask it to add custom controls for different parts, change dimensions, create animations, and even change specific materials just by describing what I wanted. So it feels less like “generate a 3D model and download it” and more like having something you can actually keep iterating on. Generate something → look at it → tell it what to change → keep going. I’ve been having a lot of fun experimenting with this. Try Agentic Mode on Hyper3D by Deemos #Hyper3D #DeemosTech #Rodin #AI3D #AgenticMode #3DModeling #AI

JOY JULIET

80,473 views • 19 days ago

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

I built a mobile app to check Paddle revenue (because they don't have one): 👉 - Use your Paddle API key (read-only and scoped) - Live data with beautiful and useful graphs built with native Swift UI. - Multi-account supported, unified revenue metrics. - Data stay on device, no server (api requests are sent directly from your phone) - Home widgets - I made it free to download on App Store (once it's approved) - Buy the source code for $19 and customize it however you want (save 5hrs of prompting if you try to do it yourself). Some interesting facts about this side project: - I vibe coded with 100% claude code remotely on my Mac Mini (with my AI assistant setup) in less than 24 hours. - I have read 0 line of code in this project and never opened Xcode myself. - My AI assistant designed the app with GPT Image 2, built the app with Swift UI, test it on simulator (via screenshots), send the test build to TestFlight for me to test, and invited me to the app store connect account so I can test on my phone, then the AI submitted the app to App Store and currently waiting for approval. - For the website, I ask it to come up with a domain name, I bought it via manually and give it access via Cloudflare API, the AI design and create a static website with GitHub, test it with lighthouse CLI, deploy via GitHub pages, config the domain DNS, deploy the website. - Then I sign up an account with Polar payment, create an API key and ask the AI to setup a store, add payment, link with the account, and add the payment to the website. The entire process happened in the last 24 hours with me only talking to the AI via Telegram. This is such a fun side project not only to create an app that I wish exists, but also to push the limit of what I can use AI for, and so far I'm very impressed. I'll create so much more apps! It feels like I have unlocked a super power.

Tony Dinh

43,922 views • 5 months ago

.Naval: The easiest way to see that AI is not taking jobs but creating opportunities is to go learn AI and then reapply for the job that rejected you. Watch how they pull you in. “My last startup, Airchat, could not have existed without AI because we needed the transcription/translation. And even the current thing I’m working on—it’s not an AI company, but it cannot exist without AI. It is relying on AI. Even at AngelList, we’re significantly adopting AI. Like everywhere you turn, it’s more opportunity, more opportunity, more opportunity. And people like to go on Twitter—or the artist formerly known as Twitter—and basically, they like to exaggerate. Like, ‘Oh my God, we’ve hit AGI.’ ‘Oh my God, I just replaced all my mid-level engineers.’ ‘Oh my God, I’ve stopped hiring.’ To me, that’s moronic. The two valid perspectives are the one-man entrepreneur shows, where there’s one guy or one gal, and they’re scaling up like crazy thanks to AI. Or there are people who are embracing AI and being like, ‘I need to hire, and I need to hire anyone who can even spell ‘AI’—anyone who’s even used AI. Just come on in, come on in.’ Again, I would say the easiest way to see that AI is not taking jobs but creating opportunities is this: go brush up on your AI, learn a little bit, watch a few videos, use the AI, tinker with it, and then go reapply for that job that rejected you. Watch how they pull you in.”

.Naval: The easiest way to see that AI is not taking jobs but creating opportunities is to go learn AI and then reapply for the job that rejected you. Watch how they pull you in. “My last startup, Airchat, could not have existed without AI because we needed the transcription/translation. And even the current thing I’m working on—it’s not an AI company, but it cannot exist without AI. It is relying on AI. Even at AngelList, we’re significantly adopting AI. Like everywhere you turn, it’s more opportunity, more opportunity, more opportunity. And people like to go on Twitter—or the artist formerly known as Twitter—and basically, they like to exaggerate. Like, ‘Oh my God, we’ve hit AGI.’ ‘Oh my God, I just replaced all my mid-level engineers.’ ‘Oh my God, I’ve stopped hiring.’ To me, that’s moronic. The two valid perspectives are the one-man entrepreneur shows, where there’s one guy or one gal, and they’re scaling up like crazy thanks to AI. Or there are people who are embracing AI and being like, ‘I need to hire, and I need to hire anyone who can even spell ‘AI’—anyone who’s even used AI. Just come on in, come on in.’ Again, I would say the easiest way to see that AI is not taking jobs but creating opportunities is this: go brush up on your AI, learn a little bit, watch a few videos, use the AI, tinker with it, and then go reapply for that job that rejected you. Watch how they pull you in.”

Arjun Khemani

167,746 views • 1 year ago

"the people who struggle with coding agents are those who try to push their way too hard. partially why I find coding with agents easy is that I've led engineering teams before". this is a unique view on AI coding, that to maximize your output you have to "let go" a bit and accept that the way AI will build the project might not be 100% aligned with your way, it might not even be 100% correct, but it will push the project forward. and if you realize later that you don't like an approach, you can always go back to it later and iterate over it. so there's not always an absolute total gain, but the overall performance is what matters in the end.

"the people who struggle with coding agents are those who try to push their way too hard. partially why I find coding with agents easy is that I've led engineering teams before". this is a unique view on AI coding, that to maximize your output you have to "let go" a bit and accept that the way AI will build the project might not be 100% aligned with your way, it might not even be 100% correct, but it will push the project forward. and if you realize later that you don't like an approach, you can always go back to it later and iterate over it. so there's not always an absolute total gain, but the overall performance is what matters in the end.

ℏεsam

165,093 views • 8 months ago

Say hello to text-to-cad, an open source tool for generating 3D models in Codex! Prompt and edit complex 3D models. Export STEP, STL, GLB, DXF and URDF files. Built for CAD newbies. Link to github below. CAD is hard. As a software engineer getting back into robotics, I’ve been humbled by new tools like Onshape. Struggling to kick old habits, I started prompting Codex to generate 3D models and had some limited succes. After a few iterations I found a recipe that actually works: 1. Generate a python script for every STEP file. The agent can easily edit each part’s source without touching the raw STEP file. Use build123d > cadquery. 2. Reference specific faces and edges in prompts for precise edits. I built a basic local ui to inspect / cache STEP B-reps to make this easier. 3. Maintain markdown explaining important part features in plain English so the model can index on project context quickly. 4. Verify results with screenshots and geometry. Models don’t have great spatial awareness, but they can interpret images and verify constraints very well. For the best results I’ve been using GPT 5.4 xhigh / Opus 4.6+. Fair warning, this will burn through tokens, I recommend the Pro/Max plans if you’re planning on building anything serious. PRs welcome!

Say hello to text-to-cad, an open source tool for generating 3D models in Codex! Prompt and edit complex 3D models. Export STEP, STL, GLB, DXF and URDF files. Built for CAD newbies. Link to github below. CAD is hard. As a software engineer getting back into robotics, I’ve been humbled by new tools like Onshape. Struggling to kick old habits, I started prompting Codex to generate 3D models and had some limited succes. After a few iterations I found a recipe that actually works: 1. Generate a python script for every STEP file. The agent can easily edit each part’s source without touching the raw STEP file. Use build123d > cadquery. 2. Reference specific faces and edges in prompts for precise edits. I built a basic local ui to inspect / cache STEP B-reps to make this easier. 3. Maintain markdown explaining important part features in plain English so the model can index on project context quickly. 4. Verify results with screenshots and geometry. Models don’t have great spatial awareness, but they can interpret images and verify constraints very well. For the best results I’ve been using GPT 5.4 xhigh / Opus 4.6+. Fair warning, this will burn through tokens, I recommend the Pro/Max plans if you’re planning on building anything serious. PRs welcome!

Jake Fitzgerald

53,724 views • 6 months ago

Hey Twitter, here’s Hearth (at least until I find a cooler name for it). It’s a little app that lives in your Mac’s menu bar and connects to hundreds of smart home integrations through Home Assistant (I’ll be building support for other smart home ecosystems in the future). With Hearth, you can monitor and manage your home’s energy usage, cameras, speakers, lights, smart plugs, air conditioners, and just about every fucking smart thing in your home that’s compatible with Home Assistant. Yes, including supported electric cars. All without having to leave your Mac’s menu bar. I vibe-coded this over the weekend, with a few visual tweaks done in Figma. Built with SwiftUI, Python, and JavaScript, with help from Claude and Codex. It’s open source, so you can do whatever the license allows. Fork it, clone it, contribute to it. Doesn’t fucking matter. I just want people to build on it and make it better. I’ll continuously make improvements to Hearth over the next few months, and I’ll need all the support I can get. Raise issues, suggest features, share feedback, or contribute to the project as you try out my little app. I’m also considering building a mobile companion app and a full macOS desktop experience in the future. I made a little video from my Mac mini to showcase some of what Hearth can do. You can also check out the project on GitHub following the link below and give it a star if you like it :)

Hey Twitter, here’s Hearth (at least until I find a cooler name for it). It’s a little app that lives in your Mac’s menu bar and connects to hundreds of smart home integrations through Home Assistant (I’ll be building support for other smart home ecosystems in the future). With Hearth, you can monitor and manage your home’s energy usage, cameras, speakers, lights, smart plugs, air conditioners, and just about every fucking smart thing in your home that’s compatible with Home Assistant. Yes, including supported electric cars. All without having to leave your Mac’s menu bar. I vibe-coded this over the weekend, with a few visual tweaks done in Figma. Built with SwiftUI, Python, and JavaScript, with help from Claude and Codex. It’s open source, so you can do whatever the license allows. Fork it, clone it, contribute to it. Doesn’t fucking matter. I just want people to build on it and make it better. I’ll continuously make improvements to Hearth over the next few months, and I’ll need all the support I can get. Raise issues, suggest features, share feedback, or contribute to the project as you try out my little app. I’m also considering building a mobile companion app and a full macOS desktop experience in the future. I made a little video from my Mac mini to showcase some of what Hearth can do. You can also check out the project on GitHub following the link below and give it a star if you like it :)

Elvis Obi

15,928 views • 13 days ago

I created a clone of Dhruv Rathee's biggest project It took me 30 minutes to code this AI chatbot that shows responses from different AI models. It’s not up to the mark I can add many more features here. Anyway, I’m not making it live since I don’t want to spend money on API costs

I created a clone of Dhruv Rathee's biggest project It took me 30 minutes to code this AI chatbot that shows responses from different AI models. It’s not up to the mark I can add many more features here. Anyway, I’m not making it live since I don’t want to spend money on API costs

Karan

126,538 views • 1 year ago