Engramory: A Portable Markdown Memory Protocol for DeepSeek Harness Agents

Engramory (tinqiao-oss/engramory) is a zero-infrastructure memory protocol designed for AI agents: Markdown-based single-file-per-fact structure, four types of typed notes, explicit curation discipline, and bounded indexing. It has 171 stars on GitHub and is categorized as a memory tool in SkillHub. This article introduces its core capabilities, official SkillHub installation command, the engramory_init initialization process, index guard configuration, and considerations like single-writer/experimental status, helping DSH users set up auditable long-term working memory.