Hierarchical Agent Memory (HAM)

Scoped memory system that gives AI coding agents a cheat sheet for each directory instead of re-reading your entire project every prompt. Root CLAUDE.md holds global context (~200 tokens), subdirectory CLAUDE.md files hold scoped context (~250 tokens each), and a .memory/ layer stores decisions, patterns, and an inbox for unconfirmed inferences.

When to Use This Skill

• Use when you want to reduce input token costs across Claude Code sessions
• Use when your project has 3+ directories and the agent keeps re-reading the same files
• Use when you want directory-scoped context instead of one monolithic CLAUDE.md
• Use when you want a dashboard to visualize token savings, session history, and context health
• Use when setting up a new project and want structured agent memory from day one

Availability and evidence

This tree contains the guide only; it does not bundle a HAM CLI, dashboard or tokenizer. go ham and ham ... are upstream workflow conventions; discover an actually installed reviewed implementation before invoking them or claiming files/dashboard/savings exist. Preserve existing project instructions when adding context, keep inferred items unconfirmed, and obtain scope before reading private session history. Report measured token usage separately from modeled savings/cost/carbon examples; do not compare unlike tasks as a proven improvement.

How It Works

Step 1: Setup ("go ham")