Memory Ingest

Turns messy external input into structured Basic Memory entities. You paste meeting transcripts, email threads, or conversation logs, and it extracts people, organizations, and topics, then searches for existing entities before proposing new ones. The workflow preserves the original content verbatim while adding structured observations in categories like opportunity, decision, or sentiment. It creates wiki-linked relations between entities and pulls out action items. Optional web research fills in context for new entities like company backgrounds or technical concepts. Useful when you need to move information from the wild into your knowledge graph without losing the source material or doing manual cross-referencing.

skills.sh installs: 546
GitHub stars: 23
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add basicmachines-co/basic-memory-skills --skill memory-ingest --agent claude-code

Installs into .claude/skills of the current project.

Files

Memory Ingest

Turn raw, unstructured input into structured Basic Memory entities. Meeting transcripts, conversation logs, pasted documents, email threads — anything with information worth preserving gets parsed, cross-referenced against existing knowledge, and written as proper notes.

When to Use

User pastes a meeting transcript or conversation log
User says "process these notes" or "add this to Basic Memory"
User pastes a document, article, or email for knowledge extraction
Any time raw external text needs to become structured knowledge

Workflow Overview

1. Parse raw input           → identify structure, extract key info
2. Extract entities          → people, orgs, topics, action items
3. Search existing entities  → multi-variation queries
4. Research new entities     → optional web research (see memory-research)
5. Present entity proposal   → get approval before creating
6. Create source note        → verbatim content + observations + relations
7. Create approved entities  → structured notes for each new entity
8. Extract action items      → follow-ups and commitments