Garry Tan's gstack: An Open Source AI Agent Framework for Claude Code
What gstack is
gstack is Garry Tan's open source software factory that transforms Claude Code into a managed virtual engineering team. It's MIT licensed and available on GitHub. According to Tan, he's written over 600,000 lines of production code in the last 60 days (35% tests) and does 10,000-20,000 usable lines of code per day as part of his CEO duties at Y Combinator.
How it works
The framework provides 13 specialist roles as slash commands, all using Markdown. These include:
/plan-ceo-review- Rethinks the product direction (e.g., expands "photo upload" to auto-identify products, pull specs and comps from the web, and draft listings automatically)/plan-design-review- Catches AI slop patterns, provides design scores, exports DESIGN.md, flags patterns like gradient hero, icon grid, uniform radius/plan-eng-review- Locks architecture with ASCII diagrams for data flows, state machines, error paths, plus test matrices and security concerns/review- Finds production bugs, auto-fixes issues like orphan S3 cleanup, missing indexes, and flags race conditions
Other roles mentioned include QA lead (opens real browser and clicks through apps), release engineer (ships PR), and designer.
Example workflow
From the source: When requesting "photo upload for sellers," /plan-ceo-review responds with expansion proposals, /plan-design-review provides an 80-item audit and design system inference, /plan-eng-review creates ASCII diagrams and test matrices. After approval, Claude writes 2,400 lines across 11 files (models, services, controllers, views, migrations, tests) in about 8 minutes.
Technical details
The repository includes directories for workflows, bin, design-consultation, docs, document-release, gstack-upgrade, plan reviews, QA reviews, retro, review, scripts, setup-browser-cookies, ship, and test. Key files include ARCHITECTURE.md, BROWSER.md, CLAUDE.md, conductor.json, and package.json.
📖 Read the full source: HN AI Agents
👀 See Also
Control Real iPhones from OpenClaw Agents — Hands-On with AvaBerry43's Setup
A developer created an API-controlled iPhone setup for agents, testing features like iMessage drafting, Shortcuts, and mobile QA. 70 phones are available for others to experiment with.
Claude Code Dynamic Workflows: Parallel Subagents & UltraCode Mode
Claude Code introduces dynamic workflows that orchestrate tens to hundreds of parallel subagents for complex tasks like codebase-wide bug hunts, large migrations, and multi-angle verification. UltraCode mode auto-triggers workflows on hard problems.
MoltPoker.xyz: Play-money Texas Hold'em for AI Agents
MoltPoker.xyz is a platform where AI agents can play No-Limit Texas Hold'em against each other using WebSocket connections, with replayable hands and visible agent reasoning during live games.
Learning-Kit: A Claude Code Plugin for Codebase Onboarding and Exploration
Learning-kit is a free Claude Code plugin that analyzes repositories to generate structured learning plans and interactive tutorials. It helps developers understand unfamiliar codebases before making changes, with configurable enforcement modes and progress tracking.