Arch1eSUN/Arcgentic

258 stars · Last commit 2026-08-12

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

PluginWorkflow & Automation TDD & Testing Documentation Design & UI DevOps & Infra Productivity AI & Prompting Security

README preview

# Arcgentic

<p align="center">
  <img src="./assets/arcgentic-logo.png" alt="Arcgentic logo" width="168">
</p>

> **Arcgentic is a harness engineering layer for AI coding agents. It turns
> ad-hoc prompting into a gated engineering workflow.**

**中文文档 -> [README.zh-CN.md](./README.zh-CN.md)**

[![status](https://img.shields.io/badge/status-stable-brightgreen.svg)](#status)
[![license](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE)
[![version](https://img.shields.io/badge/version-v2.2.0-blueviolet.svg)](#status)
[![PyPI](https://img.shields.io/pypi/v/arcgentic.svg)](https://pypi.org/project/arcgentic/)
[![npm](https://img.shields.io/npm/v/arcgentic.svg)](https://www.npmjs.com/package/arcgentic)

Arcgentic helps Codex and Claude Code run software work as a disciplined
sequence: clarify the idea, plan the work, build it, self-audit it, optionally
run a realistic user test, audit it independently, then close only when the

View full repository on GitHub →