AI-Assisted Development,
Disciplined

A methodology and tooling layer for Claude Code that turns AI sessions into traceable, domain-aware software — not just generated code.

See Pricing

The Problem

AI coding assistants are powerful. But without structure, every session starts from scratch.

// context loss

Each session forgets the last. Architectural decisions vanish. The agent rewrites what it wrote yesterday because nobody told it not to.

// session drift

What started as "fix the login bug" becomes a refactor of the auth system, a new middleware, and a half-finished migration. No guardrails, no checkpoints.

// no domain memory

The AI doesn't know your business language. It calls things by generic names, misses bounded contexts, and produces code that technically works but doesn't speak your domain.

What DevArch Does

Methodology + notation + agents. Conversation is the interface.

Methodology

DDD principles adapted for AI-assisted workflows. Start with guardrails. Add domain modeling only when complexity demands it.

Notation

A structured format that gives your conversations persistent state. You never touch it — the agents read and write it behind the scenes.

Agents

Specialized behaviors for Claude Code: session audits, mutation verification, domain discovery, code scaffolding. They run automatically.

Conversation

You describe your domain. The tooling listens and produces structured output. "Show me the model" gives you a summary, not a YAML dump.

What's Inside

Every license includes all three tiers. Use what you need — start with guardrails, add domain modeling when the problem earns it.

Tier 1

Guardrails

For every developer, every project

  • Pre-session audits surface blockers from prior work
  • Mutation verification catches side-effect mistakes
  • Session checkpoints prevent scope drift
  • Work summaries enable clean handoffs
  • Structured, traceable commits
Tier 3

Full DDD

For multi-context systems

  • Everything in DDD-Lite
  • All 24 notation element types
  • Code scaffolding from your domain model
  • Cross-context maps and integration boundaries
  • Progressive validation that tightens with maturity

How It Works

Three commands. No build tools. No dependencies.

01

Install

One command installs agents and hooks into your Claude Code environment. Everything is included.

$ devarch install # Copies agents to ~/.claude/agents/ # Configures hooks in settings.json # Writes manifest for safe updates
02

Init

Initialize any project. DevArch creates the directory structure and drops in a tier-appropriate CLAUDE.md.

$ cd your-project $ devarch init # Creates docs/context/, docs/ddd/ # Writes CLAUDE.md with tier rules # Marks project with .devarch
03

Work

Open Claude Code and start talking. The agents handle audits, checkpoints, and domain capture automatically.

$ claude # Pre-session audit runs automatically # Mutation verification on side-effects # Session checkpoint every ~60 min # Work summary on session end

Pricing

All tiers included. Annual license with repo access, updates, and all future agents.

Individual

Solo Developer

$999
per developer / year

Full access to the DevArch repo — all agents, hooks, notation schema, methodology docs, and templates. One seat.

Get Started
Enterprise

Unlimited Developers

$9,999
per year · 21+ developers

Unlimited seats for your organization. The same repo access, the same tooling — no per-developer math.

Contact Us

All plans are annual. Licensed users get read access to the private GitHub repo — pull updates anytime. No runtime dependencies, no API keys, no usage metering.

Get in Touch

Interested in DevArch for your team? Want to discuss licensing or have questions? Drop us a line.