tractorjuice/arc-kit

The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants

What it solves

ArcKit is designed to move enterprise architecture governance from fragmented, static documents into a systematic, AI-assisted workflow. It helps enterprise architects manage the entire lifecycle of architecture—from strategic planning and stakeholder analysis to risk management, data modeling, and formal design reviews—while ensuring consistency and traceability across artifacts.

How it works

ArcKit operates as a set of plugins, extensions, or prompt files for various AI coding assistants and CLIs (such as Claude Code, Gemini CLI, GitHub Copilot, Mistral Vibe, and Kimi Code). It provides a library of over 75 official commands and specialized agents that automate the creation of draft architecture artifacts. It leverages Model Context Protocol (MCP) servers to pull authoritative documentation from sources like Microsoft Learn, AWS, and Google Developer Knowledge to power its research agents.

Who it’s for

It is primarily built for enterprise architects, particularly those working in highly regulated environments (such as the UK Government, NHS, or other federal jurisdictions) who need to produce structured governance documentation and maintain strict requirements traceability.

Highlights

  • Comprehensive Governance Toolkit: Supports a wide range of workflows including Wardley Mapping, ERD data modeling, GDPR compliance, and build-vs-buy analysis.
  • Multi-Platform Integration: Works across multiple AI interfaces including Claude Code, Gemini, Copilot, and Mistral Vibe.
  • Regional and Sector Overlays: Offers specialized plugins for different jurisdictions (e.g., UAE, EU, US, Canada) and sectors (e.g., NHS, Finance).
  • ** uma-AI Research**: Integrates with MCP servers for real-time, authoritative cloud provider research.
  • Interoperability: Supports the Open Knowledge Format (OKF) for exchanging Markdown knowledge bundles.

Related

  • Project
    vfarcic/dot-ai

    An AI-powered platform engineering toolkit that automates Kubernetes operations and troubleshooting through natural language interfaces and conversational workflows.

  • Project
    genkit-ai/genkit

    An open-source framework by Google for building full-stack AI applications with unified APIs for multiple model providers and integrated developer tools for testing and monitoring.

  • Project
    Arch1eSUN/Arcgentic

    A harness engineering layer for Codex and Claude Code that turns AI coding into a gated workflow with specialized roles for planning, development, and auditing.

  • Project
    soumatheusgomes/vibe-coding-toolkit

    A documented workflow and set of tools (plugins, prompts, lint rules, sub‑agent orchestration, memory handling) that let developers use Claude Code / Codex as a disciplined coding teammate. Includes a “Superpowers” discipline, parallel sub‑agents, quality‑gate ESLint config, and a full onboarding Playbook.

  • Project
    chujianyun/skills

    A library of reusable Agent Skills and workflows for AI agents, covering everything from prompt optimization and document interpretation to system operations and career coaching.