#189189th of 324 in Skills, plugins and prompts
moai-adk
Go CLI harness that wraps Claude Code with SPEC workflow and verified completion claims
- Stars
- 1.3k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Aug 2026
- Language
- Go
875 on 3 Apr 20261,251 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
MoAI-ADK is a Go CLI that wraps Claude Code with a plan, run, sync SPEC lifecycle and binds completion claims to the command actually run and its output. Factory Mode (v3.2) splits work across one leader session and numbered lane sessions, each carrying a card through its stages in its own worktree. It also offers a local web console, a SQLite-backed task queue, and launchers for GLM and Codex backends.
Who it is for: Claude Code users running multi-session, SPEC-driven development workflows
Strengths
- Completion claims must cite the command run and its output
- Per-SPEC git worktrees and a branch guard keep parallel agents from colliding
- Factory Mode spreads cards across lanes on Claude, GLM or Codex backends
- Progress files and memory let work survive /clear
Weaknesses
- Lanes must be launched by hand, one terminal each
- Built around Claude Code; Codex can only join as a lane
- MOAI_HOME is read only by Go processes, so shell hooks and statusline can split state
- Large command and concept surface (SPEC tiers, cards, lanes, runs) to learn
What it needs
- no GPU
- Needs Claude Code, SQLite
- Models: Claude, GLM, Codex
Quick answers
Is moai-adk open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |