What is Archcore?

Shared

Archcore turns your repository into structured, machine-readable context — so AI agents understand your architecture, rules, and decisions. It takes scattered project knowledge — decisions, rules, patterns, plans — and stores it as typed, git-native documents that agents discover, read, and follow automatically.

The problem

AI coding agents start every session from scratch. They don’t remember yesterday’s decisions, last week’s architecture review, or the coding standards your team agreed on months ago.

Teams work around this with flat instruction files:

• CLAUDE.md — grows into a wall of text that’s hard to maintain
• .cursorrules — locked to one tool, not reusable across agents
• docs/ folder — unstructured markdown, agents don’t know what’s relevant
• Team knowledge — lives in people’s heads, Slack threads, and wikis

These workarounds stop scaling as projects grow.

How Archcore solves this

Archcore adds a .archcore/ directory to your repository. Inside it, every piece of project knowledge becomes a typed document — an architecture decision, a coding rule, a how-to guide, an implementation plan.

your-project/
├── .archcore/
│   ├── auth/
│   │   ├── jwt-strategy.adr.md        ← decision
│   │   └── auth-redesign.prd.md       ← requirements
│   ├── payments/
│   │   └── stripe-integration.guide.md ← how-to
│   └── onboarding-flow.task-type.md   ← proven pattern
└── src/
    └── ...

Each file suffix (.adr.md, .guide.md, .task-type.md) indicates its document type.

When an agent starts a session, Archcore’s MCP server makes all documents available. The agent can query, read, create, and link documents without leaving the conversation.

Why not just flat instruction files?

Feature	Flat files	Archcore
Structure	Free-form text	Typed documents with templates
Scale	Gets unwieldy past ~50 lines	Separate documents, free-form directory structure
Reusability	Copy-paste between tools	One setup works with all agents
Findability	Agent reads the whole file	Agent queries by type, status, or topic
Lifecycle	No versioning beyond git diff	Draft → accepted → rejected status
Connections	No links between concepts	Explicit relations between documents

Read the full comparison →

What you get after setup

After running archcore init, your agents can:

• Find relevant context — query decisions, rules, and patterns by type or topic
• Follow team standards — read coding rules and how-to guides automatically
• Create new knowledge — record decisions and patterns as structured documents
• Link related concepts — connect a plan to the PRD it implements, or a rule to the decision that produced it
• Work consistently — the same knowledge base works across Claude Code, Cursor, Copilot, Gemini CLI, and more

Two ways to use Archcore

• The Plugin gives you the highest-level experience in Claude Code and Cursor — skills like /archcore:adr, multi-step tracks, built-in agents, and guardrails.
• The CLI is the core — one binary, eight MCP tools, and session hooks that work with all eight supported agents.

Both paths use the same .archcore/ directory. See Mental Model for how they fit together.

Next steps

• Mental Model — CLI as compiler, plugin as runtime.
• Document Types — the 18 types you can create.
• Use Cases — the most common starting points for teams.