maxli

— the OS for your autonomous company. Projects, tasks, and AI agents in one workspace.

[maxli @maxlibin]

Fish tank v2 🐠 132 fish across 8 species with more natural swimming, improved lighting, better performance at ~100 fps, and now open source! Built with @threejs WebGPU + Blender: https://t.co/lGdxrXcO7R

#threejs #WebGPU #Blender #3D #OpenSource #creativecoding

[maxli @maxlibin]

Fun weekend project, v1 of a 3m planted aquarium in a living room, running live in the browser. 🐠

Built with @threejs (WebGPU), Blender, and Claude Opus 5.5.

[Flo B. @sparklabhq]

why is this so satisfying?

[OpenAI Developers @OpenAIDevs]

Everyone, or every team, can create GIFs with GPT-Image-2.6.

[Kit Langton @kitlangton]

I’m making a programming language called blood.

Faster than rust, a powerful type system, all the power of effect systems, metaprogramming, zero-cost worktrees, semantic merging, sqlite-stored content-addressable code.

Psychosis? Hopefully not.

https://t.co/PZf55rf8uZ

[maxli @maxlibin]

@zyonbuilds @threejs schooling itself is boids, and everything around it is hand-tuned

[maxli @maxlibin]

Fish tank v2 🐠 132 fish across 8 species with more natural swimming, improved lighting, better performance at ~100 fps, and now open source! Built with @threejs WebGPU + Blender: https://t.co/lGdxrXcO7R

#threejs #WebGPU #Blender #3D #OpenSource #creativecoding

[maxli @maxlibin]

Fun weekend project, v1 of a 3m planted aquarium in a living room, running live in the browser. 🐠

Built with @threejs (WebGPU), Blender, and Claude Opus 5.5.

[Ravi Parikh @ravisparikh]

Dear Claude: you are being held back by human-centric graphics APIs.

I've built a 3D and VFX engine where agents can write their own shaders, materials, cameras, physics.

The core API fits in ~2,500 tokens.

Vork is:
• 2x more token-efficient vs Blender, Unreal Engine, Houdini
• Up to 24x faster rendering times
• Rust and Slang based engine, runs on GPU via Metal/Vulkan

Below is a simulation of 1 million birds - each with unique trajectories - rendered in 97 sec on one NVIDIA L4 GPU (Blender EEVEE: 31 minutes)

[maxli @maxlibin]

Fun weekend project, v1 of a 3m planted aquarium in a living room, running live in the browser. 🐠

Built with @threejs (WebGPU), Blender, and Claude Opus 5.5.

[maxli @maxlibin]

@aksenHQ Mostly organic, sharing in communities.

[maxli @maxlibin]

A small milestone worth sharing. 🍌

https://t.co/RfHjjxpPg1 just crossed 10,000 sign-ups.

Still a long way to go, but it's encouraging to see people giving something I built a try.

Grateful to everyone who has signed up. 🙏

#BuildInPublic

[Divan Raj @desdivj]

I'm turning boring data into eye candy.

[Sydney Runkle @sydneyrunkle]

https://t.co/9loyF9vcBa

[Qwen @Alibaba_Qwen]

The becoming begins.

[沐阳 @yyyole]

真的是叹为观止！
REA之后，AI逆向再出炸裂神器！！

刚发现一个堪称离谱的开源项目！！
逆向+AI重建！一揽子搞定！
上线不到一周，GitHub 狂揽 1.4 万 Star！！
它叫 Craft Anything。
背后团队之前做出爆火的开源版Adobe全家桶，它们把核心工作流全部开源！！
只要给它一个网站、App，甚至游戏，它就能尝试把整个产品给你重新做出来！！

最夸张的是！它居然把「逆向分析 + AI 编程 + 效果验证 + 自动迭代」直接做成了一套完整的工作流！
整个过程非常暴力：
1、分析原版：研究目标产品的界面布局、视觉样式、交互行为，在深度模式下分析程序代码和文件。
2、AI 开发：调用 Claude Code 等编程 Agent，根据分析结果，从头构建一个新项目。
3、自动对比：把生成结果和原版放在一起检查，找出页面、布局和功能上的差异。
4、持续迭代：根据检查结果继续调整，逐步逼近原版效果。

项目底层集成了 320 个分析和操作工具，全部支持 CLI 和 MCP，可以直接交给 AI Agent 调用！！
甚至连反汇编、反编译、调用图分析这些传统逆向工程能力都整合进去了。
这种逆天的逆向能力，软件开发几乎没什么门槛了！

软件版权保护，难如登天！！

开源地址在下面，有兴趣可以看一下！

[Tobi @tobiadonadon_]

let's start an unslop challenge

rate each other's designs from 1 to 10

what would you rate mine? (this is easily a 9)

[cat @_catwu]

Some news: I’m joining OpenAI to lead product management for Core Products!

I have a lot of respect for OpenAI for showing the world that scaling works, for bringing AI to over a billion people, and for believing great products are core to the mission.

I’m excited to work with @thsottiaux, an incredible PM team, and everyone across OpenAI. Together, we’ll build agents that have your back and your team’s, and keep you in control, so you get more time for the people and work you love.

Lots to learn, and lots to build. Please keep your feedback coming!

[Julian Goldie SEO @JulianGoldieSEO]

Elon really did it. Grok Bot is now officially the best head of SEO I've ever had.

it's going to put more small businesses inside Google's AI answers in 2026 than any tool before it.

don't bookmark this if X puts it on your feed.

just paste the whole article into Grok Bot.

you'll thank me.

https://t.co/f01YwzLFV9

[Andrej Karpathy @karpathy]

Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
https://t.co/JIhXN7OSh1

- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊

A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.

Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.

[Joe Blau @joeblau]

I recreated subvocal in 9 minutes with one prompt for AirPods Pro 3.

Source: https://t.co/p5qYCOdjNl

[AmirMušić @AmirMushich]

10 GitHub repos to turn you into a design/motion studio. 550K+ stars total

1. impeccable (85K stars)
Anti AI-slop design skill with 62 rule-based checks https://t.co/fRvXXvJPgA

2. UI UX Pro Max (139K)
Generates a full design system (pattern, palette, type) from a project brief. https://t.co/SjF04Unb01

3. MCP for Blender (32K)
Connect Blender to any LLM. Prompt-driven modeling and scenes.
https://t.co/Khc6ciBGxI

4. img2threejs (19K)
Rebuilds the object in a reference image as code-only, animation-ready Three.js. https://t.co/eHeTt9JoJm

5. video-shotcraft (13K)
Captures your real pages, picks from 150 shot recipes, renders a promo in Remotion. https://t.co/fH6tpaIvpT

6. HyperFrames (70K)
Write HTML, render MP4, built for agents. Has a /figma skill that pulls brand tokens into video. https://t.co/dg4f1HuYbr

7. Penpot (62K)
Open-source Figma alternative with an MCP server, so agents can read your design files. https://t.co/INryfNgf98

8. Remotion (67K)
Videos in React. The official skills repo teaches your agent how to use it.
https://t.co/fIultmJuwp

9. lemo-opuscar (6K)
59 film styles made entirely in code, no video model. https://t.co/bPmh8EVFie

10. diagram-design (60K)
Agent skill that outputs diagrams as one HTML+SVG file, onboarded to your brand's colors and fonts. https://t.co/ID3XZA0Ir3

Save this. Which one should I stress-test first?

[DeepSeek Harness @DeepSeekHarness]

https://t.co/gwwIHtyCRQ