Use Archcore your way

Archcore turns your repository into structured, machine-readable context. Typed documents — decisions, rules, guides, plans — that every AI coding agent discovers automatically through MCP.

There are two ways to use it. Both read and write the same .archcore/ directory.

Best for most teams

Plugin

Use Archcore through a higher-level plugin in Claude Code or Cursor. Skills, tracks, built-in agents, and guardrails out of the box.

Plugin quick start →

Best for direct integrations

CLI

Use Archcore as a core context layer through the CLI, MCP server, and session hooks. Works with 8 coding agents.

CLI quick start →

Understand the model

Concepts

Document types, relations, layout, and why Archcore exists. The shared mental model that both paths build on.

Read concepts →

What changes when you install it

Without Archcore, asking an AI for “a new service” means the agent:

• guesses the folder structure
• ignores conventions it has never been told about
• produces code that drifts from decisions buried in docs
• rediscovers patterns you’ve already written down

With Archcore, the same ask and the agent:

• places files where your architecture says they belong
• follows rules defined in .archcore/
• respects ADRs and existing specs
• reuses patterns (cpat) you’ve already captured

Explore

• What is Archcore? — the problem, the solution, and the shape of the system.
• Mental Model — CLI as compiler, plugin as runtime.
• Document Types — the 18 types your agent will create.
• Use Cases — how teams use Archcore in practice.
• Changelog — recent releases.