gstack: Y Combinator CEO’s AI Programming Team OS

AI Programming Tools

This week’s most talked-about open source project on GitHub isn’t a new framework or a new model — it’s a skill set that lets your AI coding assistant switch cognitive modes on demand.

gstack, open-sourced by Y Combinator President & CEO Garry Tan, accumulated over 18,000 stars in just one week, making it one of the fastest-growing projects on GitHub this week.

The Problem It Solves

Developer Workflow

Anyone who has used Claude Code or similar AI coding tools knows the frustration: the AI is too “one-size-fits-all”.

Ask it to do product planning and it starts writing code. Ask it for a code review and it starts brainstorming new features. Planning, reviewing, shipping, testing — these require completely different mindsets, but AI always responds in the same mushy generic mode.

Garry Tan’s solution: give the AI different “brains” and switch between them on demand.

12 Expert Roles, Full Development Lifecycle

Software Development

gstack provides 12 carefully designed slash commands, each corresponding to a specialist role:

CommandRoleCore Capability
/plan-ceo-reviewFounder / CEOLook beyond the literal request, find the real product
/plan-eng-reviewEng ManagerLock in architecture, data flow, edge cases, test matrix
/plan-design-reviewSenior Designer80-item design audit, AI Slop detection
/reviewParanoid Staff EngineerFind bugs that pass CI but blow up in production
/shipRelease EngineerSync main, run tests, push, open PR — all in one go
/browseQA EngineerGive AI eyes to click through and test your app
/qaQA LeadRead git diff, auto-identify affected pages and test them
/retroEngineering ManagerAnalyze commit history, generate team retrospectives
/document-releaseTechnical WriterAuto-update README and architecture docs post-release

The Killer Feature: Giving AI Eyes

Browser Automation

The most groundbreaking feature in gstack is /browse and /qa.

The biggest blind spot of traditional AI coding assistants: they can’t see what your app looks like. They have to guess about UI state, auth flows, and page layouts.

gstack solves this with a built-in persistent Chromium instance powered by Playwright:

YColua:ude:/qA1AD[sQNan2feTcAoafterlfeeseRcyiccteeozlttsnpnieeesosnsddehrogaotlcract:ebhophsraup,3eantarngerfcrrcesufhoohd:neeur:ncctsd/itke.i3lnessfigdNfcsctootopoeaninansrgtngsteargleoegiosldrnlce,eslnasteelneasrwharlims,ovrloa,sioni/tgrwsn2l:aso.i3t]ro.vs0ekn.it0siei0,nawngdsgf.j,sia/lc4:leisnsdte,fropv/raiamgcpseei,ss/.lcilsitciknsgsbuttons,

18 tool calls, ~60 seconds, a complete QA pass.

AI Slop Detection: Does Your Site Look AI-Generated?

Website Design Review

/plan-design-review includes a feature that hits close to home for many developers: AI Slop Detection.

It identifies 10 telltale signs of AI-generated websites:

  • Blue-to-purple gradient heroes
  • 3-column icon grids
  • Uniform bubbly border-radius on everything
  • Centered text on every section
  • Decorative floating blobs in the background
Claude:D"""eTTfIshhefieeagtInshuierhStreaceodogrcurteosio:medmsdCuenasitccbhraleitubAeeseIs-itntSgoghle-lionpespeurrmiSiponcclsoetorSneagre:areSacwDdooeigrnendeni:rtzgatywbe.ilm"tephlAaaIt-e3g.-e"cnoelruamtnedlayout."

One Person, Ten Parallel AI Agents

Parallel Development

Garry Tan describes his own workflow in the README:

“This is the setup I use. One person, ten parallel agents, each with the right cognitive mode for its task. That is not incremental improvement. That is a different way of building software.”

Combined with Conductor, you can run multiple Claude Code sessions simultaneously:

  • One session running /qa on staging
  • Another doing /review on a PR
  • A third implementing a feature
  • Seven more working on other branches

Each workspace gets its own isolated browser instance — no port collisions, no shared state.

Installation

Just paste one command into Claude Code:

Installgstack:run`gitclonehttps://github.com/garrytan/gstack.git~/.claude/skills/gstack&&cd~/.claude/skills/gstack&&/setup`

Claude handles the rest automatically.

Requirements: Claude Code, Git, Bun v1.0+

Why This Project Matters

gstack’s viral success isn’t just about its features — it represents a new AI programming paradigm:

  1. Specialization over generalization — different tasks need different mindsets
  2. AI needs perception — an AI that can “see” your app is a complete AI
  3. Workflow is the product — great AI tools integrate into your flow, not interrupt it
  4. Solo teams become viable — with AI expert roles, individual developers can have full team capabilities

As Garry Tan puts it: “This is not a prompt pack for beginners. It is an operating system for people who ship.”

References