garrytan

The People Running The Bubble Are Very Normal Right Now So a point that Ed has covered in numerous recent newsletters is the idea that the impressive revenue figures of the AI labs, which still despite their immensity can't come close to making up for their expenses, are largely the result of a sea of small downstream AI startups that leverage their models to provide products and services. Much like how consumer Claude subscriptions are known to be subsidized heavily, giving you far more tokens than you're actually paying for, these AI startups use the same tactic to make what they're offering seem more attractive and get more users, only to fall into the same trap of unprofitability. We saw this in a big way lately with Character.AI, which effectively imploded due to this dynamic and had to file for bankruptcy. Ultimately this bubble could have burst a long time ago, but didn't, more or less because of the old 'market can remain irrational longer, etc' thing. It's really just a matter of investment people dumping more money into this cooked industry to keep it chugging along. If it weren't for that, everyone would have run out of funds by now, as they certainly aren't making returns. We've spent plenty of time talking about the Sam Altmans and Dario Amodeis of the world, so let's check in on how things are going on the startup investing side, particularly Y Combinator. Take it away, Garry! >Y Combinator CEO Garry Tan has, in the past, jokingly admitted that he’s suffered from “cyber psychosis” and sometimes barely sleeps because he’s so excited to be working with his AI agents. Much like that other semi-recent story, AI bros taking the often-used 'psychosis' label as a badge of honor of sorts. >“I spend about maybe $100[,000] to $200,000 a year on tokens,” he told Isaacson. He uses agents for countless work projects and coding tasks and has freely shared his set of 23 Claude Code skills, called gstack, on GitHub — an effort to help teach others what agents can do, he said. gstack, by the way, is primarily a repo full of markdown files containing giant, rambling AI prompts. >“It’s read all of my email and all of my Dropbox. It’s read, like, all of my Apple Notes, even my therapy notes going back 20 years,” he said. >He describes using AI agents as getting help with “almost anything that you do in your day-to-day life, and for it to do it somewhat more autonomously. Think of it as a Jiminy Cricket on your shoulder at all times. Like, almost anything you want to do, it knows you, and it’s there to help. And it will actually sort of run ahead and say, ‘What about this?’ Or it’ll help you see around corners.” Ah yes, feed all of your personal, most sensitive information to the AI companies. Become totally dependent on your token-burning agents for everything! >Tan says one thing he’s learned is not to treat AI agents like traditional software. Some people are so worried about “repeatability and safety that they actually trade off all of the beautiful parts of working with an AI agent, which basically can be so similar to a human,” They're not humans, Garry. They're LLMs. Also, with this attitude towards safety and security, Proton should hire this man. He'd fit in well there, I'd reckon. So yeah, in case you were wondering why they keep throwing money into this crap, this is who's running one of the most well-known tech VC investing firms. Now I know that the whole idea of 'venture capital' is that you cast a wide net and invest mostly small amounts into a large number of startups as early as possible, hoping to strike gold on a few that pay off in a big way. I'm not a fan of it, but I get the idea at least. Still though, I have to imagine this level of AI obsession has to be a part of why one would throw money at: - Fanfiction slop bot platform right after Character proved it doesn't work out - Convincing all Indians to plug all their finances into AI - "We're gonna cure cancer trust me bro" - Making terrawatt datacenters by turning the moon into solar panels - Literally just Theranos again

Particle-1 is as good as much larger models for agentic retrieval but 1/23 the price github.com/garrytan/gbrain-evals/blob/b392700f2f6…

Particle-1 is as good as much larger models for agentic retrieval but 1/23 the price github.com/garrytan/gbrain-evals/blob/b392700f2f6… t.co

30 Best Claude Plugins on GitHub (Sorted by Your Job) 30 Claude plugins with 3.9 million GitHub stars between them, sorted into 5 rows so you only need yours: coding, research, saving tokens, design, and writing + video. Don't add all 30. Pick the row that fits your week, add one plugin, and open its repo first to check what it can touch on your machine. 💬 Comment ANYLANCER and I'll send you all 30 links, or grab them here: 1) You write code • Superpowers: obra/superpowers • Matt Pocock's Skills: mattpocock/skills • ECC: affaan-m/ECC • Karpathy Skills: multica-ai/andrej-karpathy-skills • Ponytail: DietrichGebert/ponytail • Agent Skills: addyosmani/agent-skills 2) You research big things • Graphify: Graphify-Labs/graphify • Agent Reach: Panniantong/Agent-Reach • Understand Anything: Egonex-AI/Understand-Anything • Last 30 Days: mvanhorn/last30days-skill • Career Ops: career-ops-hq/career-ops • REA: morluto/rea 3) Huge projects, few tokens • gstack: garrytan/gstack • Caveman: JuliusBrussee/caveman • Claude-Mem: thedotmack/claude-mem • Headroom: headroomlabs-ai/headroom • GSD: gsd-build/get-shit-done • BMAD Method: bmad-code-org/BMAD-METHOD 4) Design & visuals • UI UX Pro Max: nextlevelbuilder/ui-ux-pro-max-skill • Taste: Leonxlnx/taste-skill • Archify: tt-a1i/archify • Impeccable: pbakaus/impeccable • PPT Master: hugohe3/ppt-master • Diagram Design: cathrynlavery/diagram-design 5) Writing & video • Anthropic Skills: anthropics/skills • OpenMontage: calesthio/OpenMontage • HyperFrames: heygen-com/hyperframes • Humanizer: blader/humanizer • I Have ADHD: ayghri/i-have-adhd • Marketing Skills: coreyhaines31/marketingskills Built a skill people would pay for? Sell it on Anylancer: anylancer.com Which row are you? 👇 Star counts from GitHub on Oct 29, 2026. This video was made with HyperFrames. #ClaudeCode #AIAgents #GitHub #Shorts

YC CEO 把自己的 Claude Code 配置 gstack 开源了，@goan999999 说两个月 10 万 star。他本人同时开 10 到 15 个 Claude Code 窗口并行干活，用的就是这套。都是斜杠命令，敲个 / 就能叫出对应角色。 garrytan/gstack

Garry Tan open sourced his Claude Code setup: 23 slash-command specialists from CEO review to security audits and real-browser QA. 🔗 garrytan/gstack Credits: garrytan/gstack #gstack #typescript #claudecode

10 dépôts GitHub gratuits qui explosent en ce moment 🔗 LES 10 PROJETS DE LA VIDÉO 1. REA (Reverse Engineer Anything) ➜ morluto/rea 2. Les plugins officiels d'Anthropic ➜ anthropics/claude-plugins-official 3. HyperFrames ➜ heygen-com/hyperframes 4. VoiceStudio ➜ debpalash/VoiceStudio 5. ComfyUI ➜ Comfy-Org/ComfyUI (serveur MCP officiel : Comfy-Org/comfy-mcp) 6. gstack ➜ garrytan/gstack 7. OpenCode ➜ anomalyco/opencode 8. Orca ➜ stablyai/orca 9. Ruflo ➜ ruvnet/ruflo 10. L'audit de sécurité de Cloudflare ➜ cloudflare/security-audit-skill ⚠️ REA : installez-le uniquement depuis le dépôt officiel morluto/rea (ou rea.tools), des copies circulent sous des noms proches. REA, HyperFrames, gstack, ComfyUI… Voici 10 projets gratuits sur GitHub qui changent pas mal ce qu'on peut faire avec Claude et Claude Code en ce moment. Pour chacun, je vous montre à quoi il sert, comment il s'installe et où sont ses limites. ⏱️ CHAPITRES 0:00 Le repo dont tout le monde parle 0:27 1. REA 2:04 2. Les plugins officiels d'Anthropic 3:16 3. HyperFrames 4:39 4. VoiceStudio 5:25 5. ComfyUI 6:36 6. gstack 8:05 7. OpenCode 8:58 8. Orca 9:59 9. Ruflo 10:57 10. L'audit de sécurité de Cloudflare 📺 À VOIR AUSSI • Comment j'ai automatisé mon montage vidéo avec Claude Code ➜ youtube.com • 10 outils INDISPENSABLES pour créer un SaaS avec Claude Code ➜ youtube.com ✉️ Newsletter ➜ digitiz.fr #ClaudeCode #Claude #GitHub [en-US] 10 Free GitHub Repos Exploding Right Now 🔗 THE 10 PROJECTS FEATURED IN THE VIDEO 1. REA (Reverse Engineer Anything) ➜ morluto/rea 2. Anthropic's Official Plugins ➜ anthropics/claude-plugins-official 3. HyperFrames ➜ heygen-com/hyperframes 4. VoiceStudio ➜ debpalash/VoiceStudio 5. ComfyUI ➜ Comfy-Org/ComfyUI (Official MCP server: Comfy-Org/comfy-mcp) 6. gstack ➜ garrytan/gstack 7. OpenCode ➜ anomalyco/opencode 8. Orca ➜ stablyai/orca 9. Ruflo ➜ ruvnet/ruflo 10. Cloudflare Security Audit Skill ➜ cloudflare/security-audit-skill ⚠️ REA: Install it only from the official repository morluto/rea (or rea.tools). Copies are circulating under similar names. REA, HyperFrames, gstack, ComfyUI… Here are 10 free projects on GitHub that significantly change what you can do with Claude and Claude Code right now. For each one, I'll show you what it does, how to install it, and its limitations. ⏱️ CHAPTERS 0:00 The Repo Everyone's Talking About 0:27 1. REA 2:04 2. Anthropic's Official Plugins 3:16 3. HyperFrames 4:39 4. VoiceStudio 5:25 5. ComfyUI 6:36 6. gstack 8:05 7. OpenCode 8:58 8. Orca 9:59 9. Ruflo 10:57 10. Cloudflare's Security Audit 📺 ALSO WATCH • How I automated my video editing with Claude Code ➜ youtube.com • 10 ESSENTIAL tools for creating a SaaS with Claude Code ➜ youtube.com ✉️ Newsletter ➜ digitiz.fr #ClaudeCode #Claude #GitHub

7 kostenlose Repos, die Claude unglaublich mächtig machen | GitHub | KI-Skills | Konnektoren Claude hat mittlerweile tausende Repos – aber diese 7 Claude Skills, Tools und Konnektoren können deinen kompletten Workflow verändern. Von echter Marktrecherche über Kundenfindung und SEO bis hin zu Videos, Werbekampagnen und einem Team aus 282 KI-Agenten: Ich teste alle sieben an einem einzigen Beispiel. 🔗 REPOS: last30days: mvanhorn/last30days-skill gstack: garrytan/gstack Apify MCP Server: apify/apify-mcp-server OpenSEO: every-app/open-seo HyperFrames: heygen-com/hyperframes Claude Ads: AgriciDaniel/claude-ads agency agents: msitarzewski/agency-agents Das erwartet dich im Video: ✅ last30days – findet heraus, worüber echte Menschen gerade sprechen ✅ gstack – prüft deine Geschäftsidee wie ein Startup-Investor ✅ Apify – findet potenzielle Kunden und relevante Unternehmen ✅ OpenSEO – analysiert Keywords, Rankings und KI-Sichtbarkeit ✅ HyperFrames – erstellt Videos direkt aus Claude ✅ Claude Ads – entwickelt und prüft Werbekampagnen ✅ agency agents – gibt dir Zugriff auf 282 spezialisierte KI-Rollen Das Spannende daran: Ich teste die Tools nicht einzeln, sondern verbinde sie zu einem kompletten Workflow – von der ersten Idee über Recherche und Validierung bis zur fertigen Marketingkampagne. Kapitel: 00:00 Intro – 7 kostenlose Claude Repos, Skills & Konnektoren 00:23 last30days – Marktrecherche mit echten Meinungen 01:50 gstack – Geschäftsideen kritisch prüfen 03:33 Apify – Potenzielle Kunden finden 04:51 OpenSEO – SEO, Keywords & KI-Sichtbarkeit 05:59 HyperFrames – KI-Videos erstellen 06:52 Claude Ads – Werbekampagnen planen & optimieren 08:03 agency agents – 282 KI-Spezialisten für Claude 09:26 Fazit – Welche Tools lohnen sich wirklich? **LASS UNS VERNETZEN** ✔️ Website: shakeelazq.de ✔️ Instagram: instagram.com ✔️ TikTok: tiktok.com ✔️ LinkedIn: linkedin.com ✔️ Newsletter: 8g2tqd.subscribepage.io **✉️ BUSINESS-ANFRAGEN** Für Kooperationen, Projekte und geschäftliche Anfragen erreichst du mich hier: kontakt.shakeelazq@gmail.com #Claude #ClaudeAI #GitHub #ClaudeSkills #KI

I compared four Claude Code memory tools, and why I still keep a Second Brain TL;DR - Four memory tools for AI coding agents, compared on where memory lives, what it costs in tokens, how hard each is to set up and change, and how stale entries get caught. gstack and Superpowers teach the AI how to work, claude-mem records what happened, ECC stores memory files and treats them as unreviewed. - A Second Brain answers a fifth way: it keeps what is true about your project right now, with a date on every fact. The free Second Brain Starter has the files to copy. I write Code Meet AI, the newsletter where I document how I actually use AI to ship real products, receipts included. New guides land there first. Last time, in How to build a Second Brain that stays useful, I built one from five records and a fresh-session test. Four memory tools for coding agents keep showing up on builders' feeds. Here they are side by side, and next to it. Four ways to compare memory tools A new AI session starts empty. Everything it knows about your project comes from what gets loaded in the first seconds. Developers gave the AI a memory by hand long before these four existed. The best-known version was the Memory Bank: a folder of structured Markdown files that the assistant reads at the start of a session and updates as it works. Cline's documentation describes it that way. I wrote about it for Cursor in How to Enhance Cursor AI Memory Bank and about the habit itself in Give the AI a memory. Three things made it spread: - No tooling. The memory is ordinary Markdown files, so any assistant that can read a file can use it. - Visible. You open a file and see what the AI knows about the project. - Editable and versioned. The files live in the repo, so you correct a wrong line by hand and git keeps the history. Memory handling is more than the start of a session. The tools below are compared on where the memory lives, what loads at the start and what waits until it is asked for, what it costs in tokens, and how a wrong or old entry gets found. !A box on the left reads 'new session, empty' gstack: a team of roles gstack is Garry Tan's open-source pack of Markdown slash commands. Each command turns Claude Code into one member of a small team: a CEO who challenges the plan, a designer, an engineering manager, a QA tester, a release engineer. It has about 137,000 stars and an MIT license. You install it by cloning the repo into ~/.claude/skills/gstack and running ./setup. It needs Bun. Memory - /learn. Lets you review, search and prune what gstack picked up about your codebase. - Design taste. A profile of what you approve and reject that fades by 5% a week. - GBrain. An optional add-on with a separate knowledge base, which the README calls the memory your agent keeps between sessions. Superpowers: a method the AI follows Superpowers is a skills framework and a development method by Jesse Vincent and the Prime Radiant team. It has about 304,000 stars and an MIT license. On Claude Code you add it with /plugin install superpowers@claude-plugins-official. Its skills trigger on their own. Before a task, the agent checks whether a skill applies: brainstorming before building, a plan before code, a review before done. Memory - Session start. A short startup skill, called the bootstrap, is loaded at the start of each session so the agent knows the other skills exist. - Store. The README describes no memory store. What Superpowers carries from session to session is a way of working. claude-mem: record everything, replay what matters claude-mem is Alex Newman's plugin. It has about 103,000 stars and an Apache-2.0 license. Install is npx claude-mem install. The installer asks you to sign in. The README says sign-in unlocks a 30-day free trial of its hosted memory provider, and afterwards memory runs on your Anthropic plan unless you subscribe or bring your own key. Memory - Capture. Hooks fire at six moments in a session: start, prompt, before a tool, after a tool, stop and end. They send what the agent did to a small local service. - Storage. The service compresses it with AI and stores it in SQLite, with a vector index for search (a database index that finds notes by meaning as well as by keyword). A <private> tag keeps a passage out of storage. - Replay. At the next session start, relevant past context is put back in. !Six small hook markers along a session timeline (start, prompt, before tool, after tool, stop, end) send events to a local service box ECC: memory as unreviewed files Everything Claude Code, now at affaan-m/ECC, is Affaan Mustafa's bundle of skills, rules, hooks and memory for Claude Code, Codex and others. It has about 288,000 stars and an MIT license. Install is npx ecc-universal@2.2.3 setup, the pinned form the README gives, or through the plugin marketplace. Memory - Where it lives. A Memory Vault stores plain Markdown documents, in .ecc/memory/ for a project and ~/.ecc/memory/ for you. - Session hooks. A session-start hook loads context and a session-end hook saves it. A small set of learned patterns, called instincts, is injected at the start up to a cap. - Trust. The README calls memory unreviewed context, and it says a human promotes accepted knowledge into the project's own documents. !Session end saves a note into .ecc/memory/ with an amber 'unreviewed' chip What a Second Brain does differently This part is my approach. Here is how I read the gap each setup leaves: - gstack. The roles are the center of its pitch and memory is the smaller part. If the AI plans without being challenged, the roles are aimed at that. - Superpowers. It teaches the AI how to build. Your project's facts still have to come from somewhere else. - claude-mem. Say you spent Monday moving a login flow from one Supabase project to another. By Thursday it can hand the new session a summary of Monday, which is a strong answer to forgetting. The summary is a history written by a model, so if Monday's plan changed on Tuesday, the history holds both and the new session has to work out which one is current. - ECC. Someone has to decide which saved note is true, and it leaves that step to you. A Second Brain keeps current facts in plain files you own, and it makes the review step part of the system instead of leaving it open. The shape from Article 2 is five records per project. Rules name the route the AI follows. A facts file holds current values, each with a checked date. A decisions file holds one line per choice with its reason. A roadmap holds open work with evidence. A progress log ends with a Next line. The AI reads rules and facts first and the rest on demand. I run a fresh-session test to prove it recovers a decision from the files alone. At the last count, on 22 October 2026, my own vault had 645 memory files, 119 skills, 41 commands and 640 session reports. It stays usable because the project records are small, dated and reviewed weekly. The four answers side by side | Setup | Where memory lives | Loads at session start | How a stale entry gets caught | | --- | --- | --- | --- | | gstack | Per-project learnings, optional gbrain knowledge base | Roles load when you call them | /learn lets you review and prune | | Superpowers | No memory store in the README | A bootstrap skill, then skills as tasks need them | Not a memory feature | | claude-mem | SQLite plus a vector index, local service | Relevant past context, injected by hooks | No stale-entry check; <private> only keeps passages out of storage | | ECC | Markdown files in .ecc/memory/ | Hook-loaded context and a capped set of instincts | You review and promote into project docs | | Second Brain | Five Markdown records per project | Rules and facts first | Checked date on every fact, weekly review | The last column is the one I weigh most, because an old entry read with confidence is the failure that costs me the most time. Each of the four rows solves a different problem. Tokens and answer quality Each setup spends tokens in a different place. What follows is what the READMEs say about their own design. Measured token use and answer quality are a separate test. - gstack. It ships gstack-context-bill, a read-only audit of what an installed skills tree costs in tokens: the always-on frontmatter every session pays, against the skill text that loads when you call one. - Superpowers. The startup bootstrap loads each session and skills load when a task triggers them. The README has a diagnosing skill for sessions that burn more tokens than you expect. - claude-mem. Search works in layers: a compact index first, at about 50 to 100 tokens per result, then full details only for the results you pick, at about 500 to 1,000 each. The README claims about 10 times fewer tokens from filtering first. That figure is the author's claim. - ECC. Skills load on demand and rules are always loaded, so the README says to install rules selectively. Injected instincts are capped at 6 by default, with a minimum confidence of 0.7. - Second Brain. Rules and facts load first and the rest on demand. The records stay small because each holds one kind of thing and gets reviewed. Which one fits which problem 1. The AI plans without pushback. gstack's roles are built for that. Start there. 2. The AI skips steps or builds before it plans. Superpowers makes the steps a habit. 3. The AI forgets what happened last week. claude-mem replays history automatically. 4. You want portable memory files across tools. ECC's vault is plain Markdown. 5. The AI is confident about a fact that stopped being true. A dated record makes each fact's age visible. The other setups catch stale entries through manual review or pruning. You can run more than one. A skill pack for how to work and a Second Brain for what is true is a combination I would choose before any single one of these. !Five problems on the left (plans without pushback, skips steps, forgets last week, files across tools, confident about an old fact) each connect in turn to one Setup and personalization The same five, compared on how much work it is to start and how much you can change. | Tool | Setup | Personalization | | --- | --- | --- | | gstack | Clone the repo into ~/.claude/skills/gstack and run ./setup. It needs Bun. Team mode adds a command that commits the setup into the repo. | The commands are Markdown files and the README says to fork it and make it yours. Model choices per host are settings, and some hooks are opt-in. | | Superpowers | One plugin command on Claude Code. | The README points to forking the repo for changes and gives one opt-out setting, for telemetry. | | claude-mem | npx claude-mem install, a browser sign-in, and a local background service with its own database. | A settings file controls the AI model, worker port, data directory and what context is injected. A <private> tag keeps a passage out. | | ECC | An npx command or the plugin marketplace, across several coding tools. The README warns against stacking install methods. | A /ecc:configure-ecc skill reconfigures it, and a setting caps how many instincts are injected. Memory has a project scope and a user scope. | | Second Brain | Copy the plain Markdown files of the free Second Brain Starter. The assistant shows the setup plan before it writes anything. The initializer needs Node.js 22 or newer. | Everything it loads is a Markdown file you open and edit. The rules file decides the route, and you add the facts and decisions yourself. | The free Second Brain Starter is plain Markdown. Open it in Claude Code or Codex and type Set this up for me. This one came from Code Meet AI, the newsletter where I write up the setups I actually run on my own projects.

8위 아키파이 tt-a1i/archify 7위 버셀 리액트 베스트 프랙티스 vercel-labs/agent-skills 6위 애디 오스마니 에이전트 스킬 addyosmani/agent-skills 5위 맷 포콕 스킬 mattpocock/skills 4위 에브리씽 클로드 코드 affaan-m/everything-claude-code 3위 지스택 garrytan/gstack 2위 슈퍼파워스 obra/superpowers 1위 REA morluto/rea