by modu-ai
SPEC-First Agentic Development Kit for Claude Code — 24 AI agents + 52 skills with TDD/DDD quality gates, 16-language projects, 4-language docs. Go CLI, zero deps.
# Add to your Claude Code skills
git clone https://github.com/modu-ai/moai-adk"The purpose of vibe coding is not rapid productivity but code quality."
MoAI-ADK is a high-performance AI development environment for Claude Code. 24 specialized AI agents and 52 skills collaborate to produce quality code. It automatically applies TDD (default) for new projects and feature development, or DDD for existing projects with minimal test coverage, and supports dual execution modes with Sub-Agent and Agent Teams.
A single binary written in Go -- runs instantly on any platform with zero dependencies.
MoAI-ADK v2.12.0 introduces major upgrades to the design system, Claude Code native integration, and Opus 4.7 support.
| Version | Highlights |
|---------|-----------|
| v2.9.0 | Claude Code v2.1.89-90 native skill integration (Opus 4.6) |
| v2.10.x | LSP suite expansion, SPEC-CC297-001 permissionMode attribute support, Opus 4.7 preview |
| v2.11.x | Self-Research System integration, multi-source documentation loading, enhanced memory management |
| v2.12.0 | [SPEC-AGENCY-ABSORB-001] /agency → /moai design absorption, full Opus 4.7 support, Adaptive Thinking native integration |
Design System Absorption (SPEC-AGENCY-ABSORB-001)
The legacy /agency command has been fully absorbed into /moai design. Existing /agency/ projects migrate automatically via:
moai migrate agency
No comments yet. Be the first to share your thoughts!
Benefits:
/moai + /agency commandsOpus 4.7 Native Support
MoAI-ADK now targets Claude Opus 4.7 with native Adaptive Thinking:
Self-Research & Memory Evolution
v2.11+ self-research system now integrated with agent learnings:
.claude/agent-memory/)We completely rewrote the Python-based MoAI-ADK (~73,000 lines) in Go.
| Aspect | Python Edition | Go Edition | |--------|---------------|------------| | Distribution | pip + venv + dependencies | Single binary, zero dependencies | | Startup time | ~800ms interpreter boot | ~5ms native execution | | Concurrency | asyncio / threading | Native goroutines | | Type safety | Runtime (mypy optional) | Compile-time enforced | | Cross-platform | Python runtime required | Prebuilt binaries (macOS, Linux, Windows) | | Hook execution | Shell wrapper + Python | Compiled binary, JSON protocol |
MoAI-ADK implements the Harness Engineering paradigm — designing the environment for AI agents rather than writing code directly.
| Component | Description | Command |
|-----------|-------------|---------|
| Self-Verify Loop | Agents write code → test → fail → fix → pass cycle autonomously | /moai loop |
| Context Map | Codebase architecture maps and documentation always available to agents | /moai codemaps |
| Session Persistence | progress.md tracks completed phases across sessions; interrupted runs resume automatically | /moai run SPEC-XXX |
| Failing Checklist | All acceptance criteria registered as pending tasks at run start; marked complete as implemented | /moai run SPEC-XXX |
| Language-Agnostic | 16 languages supported: auto-detects language, selects correct LSP/linter/test/coverage tools | All workflows |
| Garbage Collection | Periodic scan and removal of dead code, AI Slop, and unused imports | /moai clean |
| Scaffolding First | Empty file stubs created before implementation to prevent entropy | /moai run SPEC-XXX |
"Human steers, agents execute." — The engineer's role shifts from writing code to designing the harness: SPECs, quality gates, and feedback loops.
| Platform | Supported Environments | Notes | |----------|----------------------|-------| | macOS | Terminal, iTerm2 | Fully supported | | Linux | Bash, Zsh | Fully supported | | Windows | WSL (recommended), PowerShell 7.x+ | Native cmd.exe is not supported |
Prerequisites:
curl -fsSL https://raw.githubusercontent.com/modu-ai/moai-adk/main/install.sh | bash
Recommended: Use WSL with the Linux installation command above for the best experience.
irm https://raw.githubusercontent.com/modu-ai/moai-adk/main/install.ps1 | iex
Requires Git for Windows to be installed first.
git clone https://github.com/modu-ai/moai-adk.git
cd moai-adk && make build
Prebuilt binaries are available on the Releases page.
If your Windows username contains non-ASCII characters (Korean, Chinese, etc.),
you may encounter EINVAL errors due to Windows 8.3 short filename conversion.
Workaround 1: Set an alternative temp directory:
# Command Prompt
set MOAI_TEMP_DIR=C:\temp
mkdir C:\temp 2>nul
# PowerShell
$env:MOAI_TEMP_DIR="C:\temp"
New-Item -ItemType Directory -Path "C:\temp" -Force
Workaround 2: Disable 8.3 filename generation (requires admin):
fsutil 8dot3name set 1
Workaround 3: Create a new Windows user account with ASCII-only username.
moai init my-project
An interactive wizard auto-detects your language, framework, and methodology, then generates Claude Code integration files.
# After launching Claude Code
/moai project # Generate project docs (product.md, structure.md, tech.md)
/moai plan "Add user authentication" # Create a SPEC document
/moai run SPEC-AUTH-001 # DDD/TDD implementation
/moai sync SPEC-AUTH-001 # Sync docs & create PR
/moai github issues # Fix GitHub issues with Agent Teams
/moai github pr 123 # Review PR with multi-perspective analysis
graph LR
A["🔍 /moai project"] --> B["📋 /moai plan"]
B -->|"SPEC Document"| C["🔨 /moai run"]
C -->|"Implementation Complete"| D["📄 /moai sync"]
D -->|"PR Created"| E["✅ Done"]
MoAI-ADK automatically selects the optimal development methodology based on your project's state.
flowchart TD
A["🔍 Project Analysis"] --> B{"New Project or<br/>10%+ Test Coverage?"}
B -->|"Yes"| C["TDD (default)"]
B -->|"No"| D{"Existing Project<br/>< 10% Coverage?"}
D -->|"Yes"| E["DDD"]
C --> F["RED → GREEN → REFACTOR"]
E --> G["ANALYZE → PRESERVE → IMPROVE"]
style C fill:#4CAF50,color:#fff
style E fill:#2196F3,color:#fff
The default methodology for new projects and feature development. Write tests first, then implement.
| Phase | Description |
|-------|-------------|
| RED | Write a failing test that defines expected behavior |
| GREEN | Write minimal code to make the test pass |
| REFACTOR | Improve code quality while keeping tests green. /simplify runs automatically after REFACTOR completes. |
For brownfield projects (existing codebases), TDD is enhanced with a pre-RED analysis step: read existing code to understand current behavior before writing tests.
A methodology