Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/modu-ai/moai-adk && cp moai-adk/*.md ~/.claude/agents/24 items in this repository
Claude Code upstream change tracker -> moai-adk update plan + docs sync workflow (dev-only). Tracks new CC release notes, classifies changes by impact tier, cross-references official docs, generates update plan at .moai/research/ or .moai/specs/, and synchronizes docs-site 4-locale + README. NOT distributed to user projects.
GitHub Workflow - Manage issues and review PRs with Agent Teams (dev-only). NOT distributed to user projects.
MoAI-ADK production release via Enhanced GitHub Flow (CLAUDE.local.md §18). Creates release/vX.Y.Z branch, version bump, CHANGELOG (bilingual), PR to main, merge commit (NOT squash), then scripts/release.sh for tag + GoReleaser. Hotfix support via --hotfix flag. All git operations delegated to manager-git. Quality failures escalate to expert-debug. NOT distributed to user projects (dev-only).
Run the 7-phase /moai brain ideation workflow to convert ideas into validated proposals
Hybrid design workflow — Claude Design import (path A) or code-based brand design (path B)
Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains
Manage harness learning subsystem (status/apply/rollback/disable) OR create a harness via natural-language analysis (Context-First Discovery + name derivation + approval gate)
Generate project documentation (product.md, structure.md, tech.md, codemaps/)
Subagents overview
What people ask about moai-adk
What is modu-ai/moai-adk?
+
modu-ai/moai-adk is subagents for the Claude AI ecosystem. Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps. It has 1.2k GitHub stars and its last recorded update is dated 2026-09-12.
How do I install moai-adk?
+
You can install moai-adk by cloning the repository (https://github.com/modu-ai/moai-adk) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is modu-ai/moai-adk safe to use?
+
Our security agent has analyzed modu-ai/moai-adk and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains modu-ai/moai-adk?
+
modu-ai/moai-adk is maintained by modu-ai. The last recorded GitHub activity is dated 2026-09-12, with 26 open issues.
Are there alternatives to moai-adk?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy moai-adk to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/modu-ai-moai-adk)<a href="https://claudewave.com/repo/modu-ai-moai-adk"><img src="https://claudewave.com/api/badge/modu-ai-moai-adk" alt="Featured on ClaudeWave: modu-ai/moai-adk" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.