Re:Green Eggs and HAM (Hierarchical Agent Memory)
by Luseniik on Thursday February 26, 2026 @11:31PM
(#47176538)
I do not like them in my code.
I do not like them, token load.
I do not like re-reading files.
I do not like re-learning styles.
So I built HAM (Hierarchical Agent Memory).
Every Claude Code session, your agent burns 5,000–15,000 tokens just getting oriented. Re-reading your project. Re-discovering conventions. Re-proposing decisions you already rejected. One dev had 76K in a single CLAUDE.md eating 47% of his context window. Every request.
HAM replaces one bloated file with scoped memory.
Before: 5,000–15,000 tokens/request. After: 300–800.
The system is self-maintaining. Agent creates memory files as you build.
Zero dependencies. Open source. For token-poor builders and small teams.
Would you eat them in a box? Would you eat them with a fox?
Every Claude Code session, your agent burns 5,000–15,000 tokens just getting oriented. Re-reading your project. Re-discovering conventions. Re-proposing decisions you already rejected. One dev had 76K in a single CLAUDE.md eating 47% of his context window. Every request.
HAM replaces one bloated file with scoped memory.
Before: 5,000–15,000 tokens/request. After: 300–800. The system is self-maintaining. Agent creates memory files as you build.
Zero dependencies. Open source. For token-poor builders and small teams. Would you eat them in a box? Would you eat them with a fox?
No. You'd go HAM.