Solo-CTO mode. Stop being the only person who can ship.

The engineering OS for Claude Code — open-source, local-first alternative to Devin. great_cto orchestrates 50 specialist agents around your Claude Code: architect, PM, senior-dev, code-reviewer, qa-engineer, security-officer, devops, plus 26 archetype reviewers and 15 domain packs (voice-AI · clinical · HR-AI · API platform · lending · clinical trials · robotics · EM-fintech · climate · drug-discovery · edtech · gov · gaming · enterprise · insurance).

You're the solo CTO. You're also the bottleneck. GreatCTO is 50 specialist agents that handle architecture, review, QA, security, and deploy — while you make two decisions per feature.

Built for the one-person engineering org. Indie hackers, solo founders, and technical CTOs running everything themselves. Not built for teams — see FAQ.

Website · Live demo · Packs explorer · Discussions · Changelog

Русский · 简体中文 · 繁體中文 · 日本語 · 한국어 · Español · Português · Deutsch · Français

You describe what you want (/start "build a billing endpoint"). 50 specialist agents — architect, PM, senior-dev, code-reviewer, qa-engineer, security-officer, devops, l3-support, plus 26 archetype reviewers and 15 domain packs (voice-AI · clinical · HR-AI · API platform · lending · clinical trials · robotics · EM-fintech · climate · drug-discovery · edtech · gov · gaming · enterprise · insurance) — orchestrate the SDLC: archetype detection → pack overlay → architecture + ADRs → threat model → plan + Beads tasks → TDD impl → 12-angle review → QA → security gate → deploy.

The pipeline scales to the work: a 1-line typo fix runs through 1 agent in 30s; a deep cross-cutting feature runs through 7+ agents over an hour. You confirm two gates (plan, ship). Everything else is automatic.

🟡 gate:plan   ←  you decide here (architecture + tasks + cost)
   ↓
🤖 senior-dev → 12-angle review → qa-engineer → security-officer → devops
   ↓
🟢 gate:ship   ←  you decide here (PR ready, security signed off)

Architects, planners, reviewers, QA, security, DevOps run automatically between those two human checkpoints. Memory persists between sessions: every gate verdict appends to ~/.great_cto/decisions.md, every retrospective appends to per-project lessons.md, and /crystallize promotes high-impact patterns to a global library agents query before re-solving.

great_cto is not another coding-agent loop — it's the orchestration layer above the coding agent you already use. Think "specialist team that reviews and gates the work" rather than "another assistant that types code."

npx great-cto init

The CLI scans your repo, picks the right archetype, wires compliance gates automatically. Works on new or existing projects. Restart Claude Code afterwards.

Requires: Claude Code · Node 18.17+ · Beads · Superpowers

great-cto board opens an admin UI at http://localhost:3141 — Kanban with realtime SSE updates, per-agent cost tile, pipeline status across 8 stages, and a 30-day cost history that pairs LLM spend with the human-equivalent baseline.

Metrics — LLM cost, human-equivalent baseline, savings_x ratio	Inbox — pending gates, P0 incidents, blocked tasks, stale in-progress
Agents — 50 specialists with last-used + run counts	Memory — 11 layers + crystallized incident patterns

Full API surface: docs/BOARD-API.md.

/start "build a refund endpoint with PCI-DSS scoping"
# → architect → enterprise-saas-reviewer (PCI-DSS auto-loaded)
# → pm → 5 Beads tasks → gate:plan (you approve)
# → senior-dev → 12-angle review → qa → security-officer
# → gate:ship (you approve) → devops → deployed

/inbox
# Pending gates · P0 incidents · blocked tasks · stale in-progress

/digest
# Weekly DORA + delta vs last week + cost-per-feature roll-up

Plus: /audit (existing-codebase scan), /cost (LLM router savings), /sec (security umbrella), /oncall, /release, /rfc. Full list: ~/.claude/commands/ after install.

~$34/month for a typical solo-CTO project — 20 pipeline runs/month, indicative.

Pay your own Anthropic API tokens. No per-seat fee. No SaaS lock-in. Routine triage auto-routes to Kimi K2 (Sonnet-equivalent at ~5× lower cost) → 60–80% reduction on log clustering.

Each archetype activates its own specialist agents and compliance checklists. Top 7:

Full table (25 archetypes) + how detection works: docs/ARCHETYPES.md.

Domain packs ride on top of archetypes. Auto-attached when CLI detects pack-specific signals (deps, README terms). Each pack adds its own reviewer(s), threat-model template, EVAL suite, and human gates — independent of base archetype.

→ 22 human-gate types + 50+ reference EVAL suites + 19 TM templates. Browse all 15 packs with 4-layer journey visualization (archetype → pack → reviewer → gate): greatcto.systems/packs.html.

A Python CLI feature shipped through the full pipeline: $2.39 LLM spend vs ~$5,460 human-equivalent. Security caught two real defects QA had passed (list(stream_csv()) defeated streaming → 14.5 MB peak RSS on 13 MB input). Multi-reviewer model catching what single agents miss, before merge.

Full trace + artefacts: greatcto.systems/proof · raw: docs/qa/runs/2026-05-09/E2E-CLI-PIPELINE.md.

Drop into any GitHub Actions workflow:

- run: npx great-cto@latest ci ./ --sarif results.sarif
- uses: github/codeql-action/upload-sarif@v3
  if: always()
  with: { sarif_file: results.sarif }

great-cto ci auto-detects $GITHUB_ACTIONS and emits ::error file=...,line=N:: annotations inline on PR diffs. Exit codes: 0 clean / 1 findings / 2 setup error.

Layered test suite — structural + state-machine tier runs in <2 min for $0 (node --test tests/*.test.mjs); real-LLM tier (25 archetypes × 4-8 stages + 15 packs + 9 reviewers) runs on-demand via OpenRouter for ~$5–10. Full breakdown: docs/testing/.

Native MCP server — call great_cto's tools (scan, list_rules, detect_archetype, estimate_cost, query_decisions) from Claude Desktop or any MCP host:

{ "mcpServers": { "great-cto": { "command": "npx", "args": ["-y", "great-cto@latest", "mcp"] } } }

Full setup + internal MCPs (Grafana, LLM router, Beads): docs/MCP.md.

Five things that need you to act in <2h get emailed automatically — even when you're away from the board:

Setup: board → Notifications tab → enter email → enter the 6-digit code we send → pick triggers. No Resend signup, no API keys — delivery routed through greatcto.systems/notify (free, 100 emails/24h per verified email).

• Not for teams — solo-CTO is the product. 2+ engineers? You've outgrown it.
• Not a replacement for senior engineers — codifies process; doesn't make architectural judgement calls without one.
• Not a CI/CD system — gates run locally / in-session. You still need GitHub Actions for actual merge.
• Not certification-audited — PCI/HIPAA/SOC2 archetype scaffolds are starting points, not certifications.
• Not deterministic — LLM-generated outputs. Every gate verdict should be sanity-checked.

Is my source code used to train models? No. Claude API zero-retention by default for paying customers. great_cto adds nothing.

How do you keep token costs down? Haiku-by-default + Kimi K2 router for triage (60–80% savings) + cost-guard hook.

Can I disable hooks? Every hook honors GREAT_CTO_DISABLE_<NAME>=1. Per-file opt-out: // agentshield:ignore.

What if I'm not solo? great_cto is built for the one-person engineering org. If you have 2+ engineers and need shared boards / multi-seat auth, you've outgrown it.

Full FAQ: docs/FAQ.md.

The plugin runs inside Claude Code (or any MCP-capable host); 50 agents are markdown specs; tasks live in Beads (dolt, git-native); memory is plain markdown (no vector store). Diagram + stack table: docs/ARCHITECTURE.md.

v2.9.1 (May 2026) — zero-setup email alerts (5 trigger types · 100/24h free via greatcto.systems/notify relay · no Resend signup) · session-start auto-attach reviewers (scans recent diff → flags the right specialist subagent_type so the 24 reviewers stop sitting idle) · subagent_type routing table in CLAUDE.md / AGENTS.md.

v2.8.6 — Claude Code-only release · 15 domain packs (added edtech / gov / gaming / enterprise / insurance) · 4-layer journey visualization on /packs.html · 50 specialist agents.

Full changelog →

• v2.9 — lesson-quality tracking (which lessons agents cite vs ignore)
• v2.10 — auto-promotion: high-impact decisions → reusable skills
• v3.0 — Claude Agent SDK headless mode (CI / scheduled / webhook-triggered pipelines)

Vote on the next feature →

avelikiy — CTO building AI-native trading and fintech platforms (0→1, 1→N). great_cto is the result of automating my own loops, one agent at a time. Every rule appeared in response to a real problem in a real production system.

Pull requests welcome — see CONTRIBUTING.md. Good first issues: good-first-issue.

MIT — see LICENSE.

If great_cto saved you time, please star the repo — it helps other solo CTOs find it.