migrate

A command that imports records from another memory plugin into mneme's Markdown vault, a folder of stored notes. It currently supports importing from claude-mem.

In plain words
What is it for?
Reading the source store, converting records into vault documents, rebuilding the search index, reporting skipped records, and safely resuming an interrupted migration.
Why use it?
It lets existing memory records become searchable in the new vault without changing the original source data.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/onourimpram/mneme/migrate
Clone the repo
git clone --depth 1 https://github.com/OnourImpram/mneme
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00286
Opus 5 $0.00000 $0.00143
Sonnet 5 $0.00000 $0.00057
Haiku 4.5 $0.00000 $0.00029

Measured 2d ago against content hash 3bf79406e972, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

migrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/mneme-cc-plugin/commands/migrate.md · 42 lines

What it actually says

/mneme:migrate

Import existing memory data from another memory plugin into the vault.

Usage

/mneme:migrate from=claude-mem [path=<custom path>]

What it does

Invokes mneme migrate-from-<source> under the hood. The migration:

  1. Reads the source memory store at the default or supplied path.
  2. Maps each record into a markdown document with frontmatter that matches the vault contract.
  3. Writes the converted documents under vault/migrated/<source>/.
  4. Rebuilds the FTS5 index incrementally so the imported documents are searchable immediately.
  5. Reports per-record success and any skipped or malformed entries.

The original source store is not modified. If the migration is interrupted, re-running is safe: existing destination files are detected by content hash and not overwritten.

Supported sources at v1.0

  • claude-mem (SQLite observation database).

Future sources (mem0, supermemory, episodic-memory, letta, zep) ship in v1.1 and later.

Verification

After migration, run /mneme:search <known fact> to confirm the imported records are indexed. Or use the standalone CLI:

mneme doctor --vault <your-vault>
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 42 lines · 0 tokens per session scan A 3bf79406e972

Subscribe to this mod's changes

migrate is a command published in the GitHub repository OnourImpram/mneme (2 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 286 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.