memory-import
Installation
SKILL.md
Memory Import — Bring External Memory Data Into deep-memory
Migrates memory data from three sources into deep-memory's existing hot/cold stores. Pure Python standard library — no .venv, no pip install, works from turn one.
Supported Sources
--source |
Input | Destination | Why |
|---|---|---|---|
chatgpt |
ChatGPT memory export (.json) |
Cold store (cold-notes/raw.jsonl) |
Flat, uncategorized facts — let the existing cold→hot refinement workflow (deep-memory/resources/cold-store-and-vectorization.md) promote the valuable ones later |
claude-local |
Claude Code local memory directory (~/.claude/projects/*/memory/) |
Hot store, new category knowledge-base/imported-claude-memory.md |
Already structured (frontmatter has name/description/type) — safe to go straight into the hot store |
autoskill |
A legacy auto-skill project's root directory | Hot store, direct safe merge into knowledge-base/ and experience/ |
Same schema as deep-memory's own hot store — this is a structural merge, not a transform |
Mem0 and MemGPT/Letta are not implemented yet — no real export files were available to validate the format against. The adapter dispatch in import.py is built so adding either later is a new parser function plus a new --source choice, nothing else changes.
Commands
Always preview first with --dry-run, then drop it once the list looks right: