# modu-ai/moai-adk

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.

Repository: https://github.com/modu-ai/moai-adk
Canonical: https://ross.abutalabs.com/products/moai-adk
Homepage: https://adk.mo.ai.kr
Language: Go
License: Apache-2.0
License Family: permissive
Topics: agentic-ai, agentic-workflow, claude, vibe-coding, agentic-coding, ai-agent, ai-coding, anthropic, claude-code, cli-tool, code-quality, ddd, developer-tools, multi-agent, spec-driven-development, tdd, code-generation, go, golang, llm
Last push: 2026-09-03T00:31:00+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 86, longevity 25
- inputs: {"age_days": 351, "days_push": 0, "days_rel": 12, "gap_med": 0, "n_releases_24m": 110}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1195, forks 222 (observed 2026-09-03T02:15:15.186790+00:00)

## What it is
MoAI-ADK is an agentic development harness for Claude Code that enforces SPEC-driven plan/run/sync workflows, TRUST 5 quality gates, and multi-LLM (Claude×GLM) cost control. It ships as a single dependency-free Go binary supporting 16 languages.

## Use cases
- orchestrate claude code agents with spec-driven workflows
- enforce quality gates on ai-generated code
- reduce llm api costs with model routing
- split long coding tasks across multiple agent sessions
- add tdd and verification to vibe coding
- run multi-agent coding pipelines from the terminal

## When to choose
- you use Claude Code daily and want structured, verifiable agent workflows
- you need cost control across multiple LLM providers
- you want a zero-dependency single-binary tool with broad language support

## When to avoid
- you don't use Claude Code or compatible LLM coding agents
- you prefer lightweight ad-hoc prompting over enforced SPEC/TDD process
- you need a GUI-based agent orchestration tool

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools, code-review, testing, workflow-automation
- domain: developer-tools, large-language-models
- platform: cli, go, cross-platform, windows
- tags: claude-code, spec-driven-development, agentic-coding, multi-llm, tdd, quality-gates, vibe-coding, harness, kanban-mode, cost-control, ai-agents, command-line, automation, macos, linux

## Member repositories
- modu-ai/moai-adk (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.186790+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:23:19.403050+00:00, confidence not recorded.
  - readme: https://github.com/modu-ai/moai-adk (fetched 2026-09-03T02:15:15.186790+00:00, sha 01eee5b3bfe1)
  - homepage: https://adk.mo.ai.kr (fetched 2026-08-29T12:30:21.405560+00:00, sha 4a5a63ca9095)
- Data as of 2026-08-30T08:39:29.467469+00:00.