AccrueDev

Developer Infrastructure Platform

The system behind 46 projects, 2,400+ memories, and zero lost context.

Persistent memory, hierarchical agents, self-extending skills. A complete AI development methodology, packaged for your CLI.

The Problem

Sound familiar?

Lost Context

Every new session starts from scratch. Claude has no memory of what you built yesterday.

Brittle Agents

Your AI workflow is copy-paste prompts. No hierarchy, no quality gates, no learning.

No Methodology

You are fast at prompting but slow at shipping. Random walks through code, no compounding knowledge.

Solo Scaling Wall

50+ projects, one person. Without a system, context switching destroys your velocity.

The System

Four layers that compound.

Each one makes the others stronger.

01

Persistent Memory

pgvector-powered knowledge graph. Every decision, bug fix, and pattern survives across sessions. Your AI gets smarter the longer you use it.

02

Agent Hierarchy

10+ specialized agents (code-writer, logic-auditor, security-auditor, devil-advocate) orchestrated by an Opus architect. Each agent has defined tools, scope, and quality contracts.

03

Self-Extending Skills

30+ production-tested skills that grow automatically. When a pattern appears 3+ times, the system crystallizes it into a reusable playbook.

04

Quality Gates

Mandatory planning gates for structural changes. Logic auditor catches regressions. Devil's advocate stress-tests decisions before they ship.

Battle-Tested

Numbers that matter.

46+
projects managed
2,400+
persistent memories
30+
production skills
14+
specialized agents
8
course modules

Curriculum

8 modules.

From foundation to production ops.

01 Foundation: Memory System FREE

Set up pgvector-powered persistent memory. Install memory-mcp, configure recall/remember patterns, establish session protocols.

02 Memory Architecture

Design your knowledge graph. Memory types, cross-project search, skill pattern extraction, deduplication strategies.

03 Agent Hierarchy

Build a multi-level agent system. Code-writer, test-writer, file-analyzer at L1-2. Logic-auditor, security-auditor at L4. Devil's advocate, plan-enforcer at L5.

04 Skill System

Create self-extending skills. Pattern detection, maturity tracking, automatic SKILL.md generation, slash command integration.

05 Quality Gates

Mandatory planning gates. Pre-implementation audit chains. Plan-enforcer for drift detection. Checkpoint-based phase management.

06 Content Pipeline

Automate knowledge extraction. n8n workflows for memory-to-content transformation. Claude API for pedagogical structuring.

07 Multi-Project Ops

Scale to 50+ projects. Cross-project memory, portfolio management, context switching without context loss.

08 Production Operations

Deploy, monitor, maintain. Docker orchestration, VPS deployment, security audits, compliance tracking.

Pricing

Choose your plan.

Course

$997 one-time

The complete AI development methodology

  • 8 structured modules with exercises
  • CLAUDE.md templates and starter configs
  • Agent and skill starter library
  • 30-day money-back guarantee
Get Early Access ($697)

Agent Store

$29 /mo

Stay current with production-tested tools

  • 30+ skills updated 2 to 4x/month
  • 14+ specialized agents
  • 10+ slash commands
  • New tools as they ship
Subscribe

Bundle

$99 /mo

Everything, always updated

  • Full course access
  • Agent Store subscription
  • Memory Cloud (coming soon)
  • Priority support
Get Bundle

FAQ

Common questions.

What exactly do I get?

A complete AI development methodology delivered via CLI. Course buyers get 8 structured modules with exercises. Agent Store subscribers get 30+ production skills, 14+ agents, and 10+ slash commands, all updated 2 to 4 times per month.

Do I need Claude Code?

Yes. The system is built for Claude Code (Anthropic's CLI). It works with your existing Claude Pro or Team subscription.

Is this just a collection of prompts?

No. This is a full development infrastructure: persistent memory (pgvector), hierarchical agent orchestration, self-extending skill system, and quality gates. Prompts are maybe 5% of it.

How is this different from cursor rules or .cursorrules?

Cursor rules are static text files. This is a living system with persistent memory across sessions, agents that audit each other, skills that grow automatically, and quality gates that prevent regressions.

Can I get a refund?

Yes. 30-day money-back guarantee on the course, no questions asked.

What if Claude Code changes its file structure?

The CLI detects structure changes at runtime and adapts. Course content is always delivered to a stable location regardless of Claude Code updates.

Early Access

Join the Waitlist

Get early access pricing and be first to know when we launch.

No spam. Unsubscribe anytime.