Describe a product. Approve twice. Ship the software.
npx great-cto init
Website · One real run → · Live demo · Blog · Changelog
Русский · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français
great_cto is the orchestration layer above the coding agent you already use.
A pipeline of 69 specialist agents — architect, design-advisor, senior-dev,
code-reviewer, QA, security, devops — plans, builds, reviews, and deploys a real
application: backend, frontend, generated tests, live URL.
You are stopped exactly twice: once on what gets built, once on whether it
ships. Everything between runs unattended.
describe a product
│
🤖 spec · architecture · data model · screens
▼
👤 checkpoint 1 — approve the design
│
🤖 scaffold → backend → frontend → tests → review → security
▼
👤 checkpoint 2 — approve the deploy
│
🤖 deployed · repo · live URL
The board at localhost:3141 fills itself in — pipeline state, pending gates,
per-agent cost, 30-day spend. You do not feed it; you check it.
Numbers, measured
| |
|---|
| One feature, end to end, fully traced | 1h 26m · $3.40 in tokens — the receipts |
| A whole product — 7 built in the open benchmark | median $171 in tokens · 70/100 quality (58–86) — reproduce it |
| Typical month, 20 pipeline runs | ~$34 — you pay your own LLM provider, nothing else |
| Products it knows how to build | 60, across 15 US industries, through 6 reusable pipelines |
The quality score is produced by running each product's own tests, not by
counting files — which is why it says 70 and not a rounder, prettier number.
Quick start
npx great-cto init # Claude Code (default) · add --host codex for OpenAI Codex
Restart your AI host, then:
/start "build a dispatch & scheduling app for an HVAC business"
The pipeline takes it from there. Day to day you touch three things:
| |
|---|
/start "…" | describe a product or feature — the pipeline runs it |
/inbox | what needs you: pending gates, P0s, blocked tasks |
/digest | weekly DORA metrics + cost-per-feature roll-up |
Requires Node ≥ 18.17. Companion plugins (Superpowers, Beads) install
automatically. After init, verify the host actually loaded the plugin —
claude plugin list --json should show no errors for great_cto.
When it asks you
One setting in .great_cto/PROJECT.md decides where the pipeline stops:
approval-level | Stops at | Per feature |
|---|
product-only | what we build · whether it ships | 2 |
gates-only (default) | the design · the deploy | 2 |
strict | + code review | 3 |
auto | nothing | 0 |
A regulated archetype — fintech, healthcare, gov — keeps its security,
compliance and ship gates at every level, including auto. A lighter level
delegates judgement; it never skips compliance. Full table: docs/GATES.md.
What makes it different
- Specialists, not a generalist — 69 agents with narrow jobs and their own
review gates, instead of one assistant that types faster than it thinks.
The roster →
- Critics before code — architecture, spec, and schema critics run before
planning, where a mistake still costs hours instead of days.
- Scope enforced at write time — an agent physically cannot touch files
outside its brief. Not flagged at review; refused at write.
- QA that distrusts itself — critical paths written as Gherkin before test
code, then mutation testing asks whether the suite would catch anything at all.
- Memory across sessions — decisions, lessons, and promoted patterns persist
per project and globally; an interrupted run resumes knowing which stages ran.
- Cost you can see — per-agent spend, estimate-vs-actual drift, and
cost-per-accepted-change on the board, not in a spreadsheet.
Everything runs locally, MIT-licensed, on your own keys. Your code stays on your
machine; prompts go to your LLM provider and nowhere else. Telemetry is
off by default (docs/PRIVACY.md).
Limitations
- For one builder — a solo founder or CTO. Two or more engineers sharing the
pipeline have outgrown it.
- Not a CI/CD system — gates run locally; you still merge through GitHub Actions.
- Not certification-audited — PCI/HIPAA/SOC2 scaffolds are starting points,
not certifications.
- Not deterministic — LLM output. Gate verdicts deserve a sanity check.
Documentation
Docs hub → ·
Getting started ·
Gates & approval levels ·
Agents · Commands ·
Archetypes · Architecture ·
MCP · FAQ ·
Everything else — critics, jurisdictions, cost breakdown, CI, alerts
Community
Issues ·
Discussions ·
Blog ·
Security policy · Contributing
MIT — LICENSE. Built by @avelikiy:
CTO building AI-native trading and fintech platforms; great_cto is my own loops,
automated one agent at a time.
If it saved you time, a star helps other solo builders find it.
Stop being the only person who can ship.
