A portable memory protocol for artificial intelligence agents

Key features

• An opinionated, zero-infrastructure memory protocol for small-scale, local, file-based agent memory — a strict curation discipline plus a validator (tools/engramory_doctor.py), loaded as standing rules (CLAUDE.md / AGENTS.md / your host's rules file).
• Claude Code native auto-memory — the same markdown-MEMORY.md-index + lazy detail-file pattern
• The goal is the same discipline on any agent — by riding the real cross-agent rails, not by inventing a new standard.
• Never write a secret's value into memory — keys, tokens, passwords, cookies, recovery codes.
• It is not a database, a framework, or a relevance-loaded skill.