Ron Kurti

@shashpicious_ repo-explainer.com

designers who can code, reply with what you built. designers who can't, reply with what's stopping you. let's fix both.

@GitHub_Daily Oh my. Should I implement this? repo-explainer.com/oh-my-mermaid/…

用 AI 开发项目越来越大，想回头看自己的代码库，架构是什么样的、数据怎么流转的，反而越来越模糊。 可以试下 Oh-my-mermaid 这个工具，让 AI 自动扫描代码库，生成可视化的架构文档。 在 AI 编程工具里输入一条指令，就能自动分析项目结构，生成带有 Mermaid 图表的多维度架构文档，还能在浏览器里交互查看。 GitHub：github.com/oh-my-mermaid/… 遇到复杂的逻辑节点还会自动进行递归分析，拆解出带有独立图表的嵌套子元素，并在本地生成清晰的目录树。 目前已适配 Claude Code、Codex 等主流 AI 编程工具，一条命令自动配置，还能把文档同步到云端分享给团队。 如果你的项目已经大到自己都记不清架构了，用它扫一遍，比手动画图省事不少。

@orhundev @ratatui_rs The Multi-modal dispatcher repo-explainer.com/emanuele-em/pr…

Wow, this is a gem 💯 🕵️ proxelar — Intercept HTTP traffic from the terminal 🔥 MITM proxy with TUI, web UI & Lua scripting ⚡ Inspect, modify, mock requests in real time with full HTTPS interception 🦀 Written in Rust & built with @ratatui_rs ⭐ GitHub: github.com/emanuele-em/pr… #rustlang #ratatui #tui #networking #proxy #security #http #terminal

@maxfaber_Om Thank you, this is my explainer: repo-explainer.com/seahorsecastle…

@RonKurti I admire repo-explain UI/UX . Would love to learn more how it’s built. Did you share it somewhere?

Started repo-explainer.com 2 weeks ago. Yesterday I had to add category filters and lazy loading, because there are just too many repos to list. What next?

So I built repo-explainer.com 7 to 8 minute reads. No jargon. Just the idea, the architecture in plain english, and why it matters. For people who think in products, not files. Who ship first and understand later. Who spent years feeling slightly outside the conversation, and now suddenly aren't. 6/6

What I actually want when I find a repo isn't the docs. I want someone to sit next to me and explain it like I'm smart but not technical. Tell me the idea. Tell me what problem it's solving. Tell me why someone stayed up late to build it. That's the part that makes it click. Not the code. The intent behind the code. Visual thinkers have always understood software. We just needed a better door in. 5/6

I can't read code... but I do understand it. There's a difference. I think in systems. I am technical. I see how things connect. Give me a diagram, a prototype, something I can poke at, and I get it immediately. Put a file tree in front of me and my brain just... nopes. I've always been this way... a visual learner. Reading was always a challenge. School was fine until it wasn't. Not because the ideas were hard. Because the format was wrong for how I think. LLMs changed something fundamental for me. For the first time I can be a developer too. Not a developer who reads code. A developer who thinks out loud, describes what I want, iterates on feel. The ideas were always there. Now I have repo-explainer.com. It matches how my brain works. 1/6

@garrytan YC in your terminal repo-explainer.com/garrytan/gstack

Do you want this for yourself? Tell your Claude Code to "Install GStack" and it'll just work Start with /office-hours and then /autoplan on your next plan mode, and watch how much better your software ends up being github.com/garrytan/gstack

"Ready to build" after one prompt is literally just-in-time software realized It's not a pipe dream. It's happening today. We don't have to be so precious about software anymore. With the right prompts, anyone can build anything Also: We should have 100x more open source

@wey_gu Grep-friendly YAML is the way repo-explainer.com/nowledge-co/Op…

哈哈 说起来一直专注在 Mem 上，我们的 OpenKL 没继续做下去 github.com/nowledge-co/Op… 类似的项目这几个月一直在涌现👍

@minchoi Netflix is on board! repo-explainer.com/Netflix/void-m…

Project page: github.com/Netflix/void-m… Demo: huggingface.co/spaces/sam-mot…

Netflix just dropped VOID. This AI removes objects from video... And even corrects the physics after objects/people are removed. Demo in commets👇

@fuho What should it do next?

@RonKurti This is really good, thanks for creating it and letting people use it.

@Dontsuspe Tell me more

@RonKurti need a subscribe option

@bindureddy 👊 x.com/RonKurti/statu…

LLMs are slowly automating white-collar work, even as haters continue to hate 🤷‍♀️ In 2026, they will - - create new features, test them, and release to prod - run vibe-marketing campaigns and run social media accounts - analyze data, generate reports, and come up with insights - run support, legal, procurement, and operations in general Literally everyone will feel the AGI 😍

@Saboo_Shubham_ 👊 x.com/RonKurti/statu…

Self-healing Agent Skills. This is the piece I've been doing with my agents and didn't have a name for. I run a team of 6 AI agents. Each one has instruction files, memory, shared context. When something drifts, I tell the agent to go fix its own skill file. It reads the problem, rewrites the instruction, and updates the file. Already works. But I'm still the one noticing the drift. I'm still the trigger. Self-healing closes that gap. The agent watches its own execution. When a skill starts degrading, it rewrites the instruction, tests it, and rolls back if it made things worse. Observe → Inspect → Patch → Evaluate → Rollback. No human noticing. No human triggering. Context engineering got us to "agents that know things." Self-healing skills get us to "agents that stay good at things" without you babysitting.

@aakashgupta x.com/RonKurti/statu…

Karpathy just mass-distributed a product without writing any code for it. The gist is one page of markdown describing how to build an LLM-maintained personal wiki. Raw docs go into a folder, an LLM "compiles" them into 100+ interlinked articles, and the whole thing self-heals through automated linting passes. His version runs on Obsidian with custom scripts and 400K words of compiled research. He calls it an "idea file." One page of markdown. Your agent reads it and builds the entire system customized to your stack in an afternoon. His Obsidian setup is probably thousands of lines of hacky Python. You'll never see any of it. A one-page spec and a capable agent gets you 90% of the way there, tuned for your own tools and workflow. The economics of this are wild. In the old model, someone shares a repo and maybe 2% of people actually clone it, install the dependencies, and get it running. Idea files flip that ratio. The agent handles all the translation work between "what Karpathy built" and "what works on your machine." The conversion rate from "saw a cool project" to "have my own version running" collapses from days to hours. Karpathy is basically saying the era of "here's my repo, go figure out the dependencies" is being replaced by "here's what I built and why, go tell your agent to make you one." Software distribution is becoming a game of telephone where every recipient gets a better version than the original.