GL

glacius-labs/markitect

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

0 stars 质量 57 趋势 20Apache-2.0

AI工作流程的类型化工程知识:明确的所有权、依赖关系、上下文及变更影响。

概览

Markitect 是以模型为先的开发,实现委托。你维护一个典型的 YAML 模型,定义项目的预期世界:其概念、规则、边界、责任、检查和依赖。源代码、测试、配置和散文在采纳项目中仍是普通文件;它们实现了模型。 你更改模型,通常与编码代理对话,Markitect 会应用该变更。它编译模型,推导受影响的管理器和文件,并允许递归管理器通过独立审查、集成、固定候选验证和受保护的应用实现变更。Markitect 报告已执行检查的证据;项目所有者保留关于语义接受和释放的决策权。Markitect 简要说明了原因以及如何判断。 模型优先的 markitect 工作流程可在此开发源验证中获得;但它未包含在发布的 v0.14.1 二进制文件中。

概述(AI 翻译)

别追随代码。让代码追着你。

以模型为先的软件工程,配备编译器检查的规范模型和AI团队,源自你的架构。

想法 ·工作原理 ·一个具体示例 ·试试看 ·当前状态 ·文档


这个想法

AI可以写代码。让整个项目都符合它应该做的事就难了。

关于行为或架构的决策很少只停留在一个地方。其后果体现在源代码、测试、文档、配置、依赖关系,有时甚至是给编码代理的指令中。随着这些表示的演变,代理可能完成当前任务,却在其他地方遗漏规则,导致矛盾,或导致之前正确的行为被破坏。

Markitect 的出发点是不同的:

定义一次预期系统。将代码、测试、配置、文档和代理指导视为该意图的实现。

你维护一个规范的项目模型。

本页由 AI 翻译,技术细节请以原文为准。

README

以下为原文 README 节选,完整内容请查看原文。

Markitect keeps one canonical model of your project in Markdown, checks it like code, and has a team of AI agents derived from its architecture realize and check every change.

Why · How it works · Quick start · Example · Status · Documentation

[!IMPORTANT] Markitect is in active development and runs from source; there is no release yet. Every command on this page exists on main. Whether its Runs keep a project at least as consistent as one strong agent with ordinary documentation, with fewer defects left for people to repair, is the question its evaluation answers; a pilot has run, and the counted series follows (status).

Why Markitect

When AI agents build most of a project, its design, rules, documentation, code, tests and configuration drift apart. A decision about behavior reaches the code, the tests, the documentation and the agents’ own instructions. An agent finishes its task and misses a rule two folders away. Consistency passes take hours and find more each time, and a pull request that one AI wrote, another reviewed and a person approved on trust carries the gap to main.

Markitect moves the knowledge of what belongs together out of the agents’ memory and into one place you own: the canonical model. You describe the project once, as typed documentation in Markdown. Code, tests, configuration and documentation are its realizations. When intent changes, you change the model; Markitect works out what the change reaches, has the responsible agents bring the repository in line, checks every step independently and lands the result with a record of every verdict.

Features

  • Typed documentation. One Markdown file per Definition, its Kind in the front matter, links by path such as [[members/member]]. Projects define their own Kinds; the standard Libraries std, rest and cli ship in the binary.
在 GitHub 查看完整 README

推荐工具

换一个关键词,或者移除筛选条件。

安装

npx skillfish add glacius-labs/markitect
新手?先看 mcpskill.org 教程 →