@basicmachines-co

memory-ingest converts unstructured external input (transcripts, documents, logs) into structured knowledge graph entities. parses content, extracts and deduplicates entities, gathers user approval, creates linked source notes and entity records with observations and relations.

memory-tasks enables structured task management within basic memory's schema system. tasks persist as queryable notes through context compaction, supporting multi-step work tracking, resumption after memory loss, and explicit blocker/context capture.

memory-defrag consolidates agent knowledge by splitting oversized files, merging duplicates, removing stale entries, and restructuring directory hierarchies. targets bloat reduction and reference clarity via periodic or on-demand audit and reorganization.

Analyze a complete literary work into a structured Basic Memory knowledge graph. Covers schema design, entity seeding, chapter-by-chapter processing,…

Research an external subject using web search, synthesize findings into a structured Basic Memory entity. Use when asked to research a company, person,…

How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building…

Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory. Use when triggered by cron,…

Manage entity status transitions in Basic Memory: archive completed work, move notes between status folders, update frontmatter, and handle edge cases. Use…

Structured metadata search for Basic Memory: query notes by custom frontmatter fields using equality, range, array, and nested filters. Use when finding notes…

Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift.…