Glenn Hernandez

How do you know when Claude Code is about to compact? I didn't!! Until I built ContextMeter. Real-time context % in your menu bar with floating window. $7 Mac App. No subscription. ghstudios.lemonsqueezy.com #ClaudeCode #MacApp #Anthropic @AnthropicAI @claudeai @ClaudeDevs

@daveylovescode Love this! Nice idea

Hey After Effects users: Today I decided that everything on Motion Fun will be free from here on out. This means Petals (which I used to charge $39 for) is now free. Oh, and I've got a crap ton more tools in the works, coming soon. Also free.

@EBogomolovs If there is a way to make the app even better but without making it to complex I’m all ears!

@ghsnyc A meter is the easy half. The hard one is what you do when you see 90%. Most people don't have a checklist for that moment. The bar just makes the panic earlier. What does ContextMeter want you to do once it warns you?

How do you know when Claude Code is about to compact? I didn't!! Until I built ContextMeter. Real-time context % in your menu bar with floating window. $7 Mac App. No subscription. ghstudios.lemonsqueezy.com #ClaudeCode #MacApp #Anthropic @AnthropicAI @claudeai @ClaudeDevs

@EBogomolovs How I use it is… I tell Claude to save progress, learnings and any relevant information for the task at hand so I can compact and continue or to start in a new session.

Genius!

Mesh2Motion Release 11 Out 🎉 - Switch out default models for a rig (13 added) - Add new Fish rig (shark and whale variations) - Many other small improvements Check out the full release 11 notes with all changes: mesh2motion.org/news Try it out and any feedback welcome: app.mesh2motion.org

@PaulHamilton8 Nice interface

Gave up on mesh conversion and Playing with Core ML Models again, this time with depth detection. Learning lots. Another vibe coded prototype, using claude + chat UI storyboard design help.

@SpartanDavie @PaulHamilton8 @dudutaulois @Apple @AppleEDU Dude, thank you. I've actually been trying to get trellis to work on Mac, but in comfyUI. This might help me in there. But will have to figure out how it might help with splats to mesh. Appreciate it!!!

@PaulHamilton8 @ghsnyc @dudutaulois @Apple @AppleEDU Might be worth looking at github.com/shivampkumar/t…

Spent Friday night testing @Apple ‘s new open-source ml-lito image-to-3D model running locally on Apple Silicon via Metal. No cloud, API, or uploads. Getting it working was harder than expected but got there. 👇👇👇@AppleEDU github.com/apple/ml-lito

@PaulHamilton8 @Apple @AppleEDU Hard to find MacOS ports of some of the things I see are working on the PC side. Shame.

@PaulHamilton8 @dudutaulois @Apple @AppleEDU 🙏 I'll do the same if I find anything.

@ghsnyc @dudutaulois @Apple @AppleEDU Looking into this today. Will share if I find anything.

@PaulHamilton8 @dudutaulois @Apple @AppleEDU making the mesh and the per texture has been an issue. Not sure where to look to get it done. Some repo somewhere has the answer. But I have not found it yet.

@dudutaulois @Apple @AppleEDU Looking into this.

Adding some quality of life improvements for Mesh2Motion. Reference images to help you know where to place joints. Different joint colors for limbs and torso elements. Trying to get another release out soon with everything.

@WangZhao_0849 @xen_studio Will this run on a Mac Studio, with 96gb or vram? Seems like most of this works on pc but you need a lot of memory and most graphics cards don't have that much.

@xen_studio Currently it cannot run on 16GB vram, since the model contains three 1.3B-parameter DiTs. It could be optimized by offloading the models, using lower 3D resolution, and some quantization techniques.

🚀🚀 Introducing Pixal3D (SIGGRAPH’26) — a new pixel-aligned image-to-3D generation paradigm for high-fidelity 3D asset creation. Today’s Image-to-3D has become pretty good at producing plausible 3D assets. But plausibility is not enough. Fidelity is a hidden bottleneck. ❓A generated model may look “about right,” yet still fail to truly align with the input pixels. Can we make 3D generation as faithful as reconstruction, while still allowing it to complete the unseen? Pixal3D is our answer. 💡We believe the core bottleneck behind fidelity is 2D–3D correspondence. Most 3D-native generators synthesize shapes in canonical space and inject image cues through cross-attention, forcing the model to implicitly search for which pixels correspond to which 3D regions. 🍀Pixal3D takes a different route. Instead of generating in canonical space, Pixal3D generates directly in pixel-aligned camera space — what you see is what you get. The generated 3D asset is aligned with the input view from the start. ☕️Meanwhile, Pixal3D introduces back-projection-based image condition scheme - explicitly back-projects multi-scale pixel features into 3D voxels, thus resolving the 2D-3D association problem. The input image is no longer just a prompt - it becomes a geometric anchor. 🚩Pixal3D shows that pixel-aligned 3D generation is not only feasible and scalable, but also significantly improves fidelity, pushing 3D-native generation closer to reconstruction-level faithfulness. It also naturally extends to multi-view and scene-level 3D generation. ✅Faithful to the input view. ✅Generative for the unseen. Closer to reconstruction-level fidelity, with the creativity of 3D generation. Pixal3D also represents an effort towards the unification of 3D generation and reconstruction. 📢Paper, code, and demo are fully released — try it out and let us know your feedback! 🌐Project page: ldyang694.github.io/projects/pixal… 🤗Huggingface Demo: huggingface.co/spaces/Tencent… 💻Code: github.com/TencentARC/Pix… 📄Paper: arxiv.org/abs/2605.10922

Hey there! I'm looking for some friendly faces to help beta test the Take Control #Cinema4D plugin for both Windows and macOS. If you’re interested, feel free to send me a direct message.

Link: ghstudios.lemonsqueezy.com

Claude Code doesn't tell you when you're about to run out of context. ContextMeter does. $7 Mac App. No subscription. #ClaudeCode #MacApp

@ClaudeDevs Thank you! This helps a lot, specially on the $20 plan

Happy Friday! We've reset everyone's 5-hour and weekly rate limits.

this AI is on another level. 3D rigged models generated in minutes from a single image! Create your own on tripo this way 👇

Just launched ContextMeter — a Mac menu bar app for Claude Code users. Shows context %, token usage, cost & rate limits in real time. Works with the claude CLI, desktop Code tab & VS Code. Not Claude chat. $7 one-time. ghstudios.lemonsqueezy.com #ClaudeCode #MacApp