HAM — Hierarchical Agent Memory

Fewer tokens. Greener AI.

HAM is a memory system for AI coding agents that reduces token consumption by up to 80%. Instead of loading your entire project context on every request, HAM scopes memory to the directory you're actually working in.

Less tokens. Faster agents. Lower costs. Greener AI.

Claude Code only — HAM is a skill for Claude Code and only works with Claude coding agents. It is not compatible with Cursor, Copilot, Windsurf, or other AI coding tools.

---

The Problem

Every time your AI agent starts a session, it re-reads everything. Your full project structure. Conventions it already learned. Decisions you already made. Context that has nothing to do with the current task.

A single bloated CLAUDE.md can eat 47% of your context window before the agent writes a single line of code.

That's wasted tokens. Wasted money. Wasted energy.

The Solution

HAM replaces one massive context file with small, scoped memory files at each directory level. Your agent reads only what it needs for the directory it's touching.

project-root/
├── CLAUDE.md                  # Global: stack, conventions (under 250 tokens)
├── src/
│   ├── CLAUDE.md              # Shared src patterns
│   ├── api/
│   │   └── CLAUDE.md          # API auth, rate limits, endpoint patterns
│   ├── components/
│   │   └── CLAUDE.md          # Component conventions, styling rules
│   └── db/
│       └── CLAUDE.md          # Schema context, query patterns
└── .memory/
    ├── decisions.md           # Architecture decisions with rationale
    └── patterns.md            # Implementation patterns

The agent reads 2-3 small files instead of one massive context dump. Your starting context drops from thousands of tokens to hundreds.

---

Before & After

	Before HAM	After HAM
Context per prompt	4,000 - 12,000 tokens	800 - 2,400 tokens
50-prompt session	200K - 600K tokens	40K - 120K tokens
Context window used at start	Up to 47%	Under 10%
Token reduction	—	Up to 80%

---

Why This Matters

For Your Wallet

Fewer tokens = lower API bills. Teams running agents at scale see the savings immediately.

For Your Speed

Smaller context = faster responses. Your agent spends less time processing irrelevant information and more time writing code.

For The Planet

AI inference accounts for over 80% of AI electricity consumption. Every token generated requires compute, energy, and cooling. Reducing token waste isn't just efficient — it's a sustainability decision.

Data centers are projected to consume 945 TWh of electricity by 2030 — more than Japan's total consumption. AI is the primary driver of this growth. — International Energy Agency

HAM makes your AI usage greener by eliminating the tokens that never needed to exist.

---

Installation

git clone https://github.com/kromahlusenii-ops/ham.git ~/.claude/skills/ham

This installs HAM globally — it's available in every project you open with Claude Code.

Add to a specific project only

If you prefer to scope HAM to a single project instead of installing it globally:

cd your-project
mkdir -p .claude/skills
git clone https://github.com/kromahlusenii-ops/ham.git .claude/skills/ham

Project-level skills live in .claude/skills/ and are only active in that project.

Quick Start