codeaholicguy/ai-devkit

Registry 信息

项目简介

AI DevKit 是一个通用的 AI 代理技能 CLI 工具包，支持在 Cursor、Claude Code、Codex 等工具中实现结构化的 AI 辅助开发，提供统一的接口以简化工程工作流。

要点

• 跨多种工具的通用 AI 代理技能 CLI
• 结构化的 AI 辅助开发工作流
• 支持 Cursor、Claude Code、Codex 等工具
• 使用 TypeScript 构建，确保可靠性和性能

使用场景

• 使用 AI 代理自动化代码生成和审查
• 将 AI 辅助开发集成到现有 CLI 工作流中
• 跨不同开发工具标准化 AI 交互

README 摘要

# AI DevKit > English | [中文](./README-zh.md) **Your team of AI coding agents is fast, eager, and reckless. Make them work like senior engineers instead.**  AI DevKit turns one-off AI coding chats into a repeatable software delivery workflow: requirements, design, planning, implementation, tests, verification, memory, and review. - **Stops prompt-and-pray coding** — `/new-requirement` makes the agent clarify the problem before touching code - **Blocks fake "done" claims** — `verify` requires fresh test/build output before completion claims - **Keeps project knowledge alive** — `@ai-devkit/memory` stores decisions, conventions, and fixes across sessions - **Catches drift before push** — `/code-review` audits the diff against the design and requirements docs - **One console for all of them** — `agent console` is a live TUI dashboard for control all your running agents, no matter the provider One config. All coding agents: Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, opencode, Antigravity, Amp, Windsurf, Kilo Code, Roo Code. Run `npx ai-devkit@latest init` and your agent gets: | What you need | What AI DevKit installs | |---------------|-------------------------| | A plan before code | `/new-requirement`, `/review-design`, and `/execute-plan` | | Evidence before "done" | `verify` gates tied to fresh test/build output | | Memory across sessions | Local SQLite memory exposed through MCP and CLI | | Same behavior across agents | Generated config for the coding tools your team uses | [](https://www.npmjs.com/package/ai-devkit) [](https://www.npmjs.com/package/ai-devkit) [![GitHub stars](https://img.shields.

话题