memo_offload
Offload large tool outputs, logs, or dumps into a content-addressed reference tier, freeing the context window while returning an ID and deduplication status for later retrieval.
Instructions
Offload a bulky payload (tool output, log, dump) out of the context
window: memo stores it content-addressed as a reference-tier memory
and returns {id, sha256, kind, synopsis, deduplicated, drill_down}.
Use memo_offload for bulk working-context dumps; use memo_save for
curated durable facts meant to be recalled. Idempotent per payload:
re-offloading identical content returns the existing id with
deduplicated: true instead of writing a new memory.
The synopsis is deterministic (no LLM): JSON keys, CSV headers, code
symbols, or compressed text. Reference tier is excluded from
auto-recall, so offloaded blobs never appear in the recall hook.
Fetch the full payload later with memo_get(id).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional label used as the stored memory's title and markdown heading; None auto-generates 'offload:<kind> <sha256[:12]>'. | |
| content | Yes | Raw payload to store verbatim. Rejected when empty/whitespace-only or longer than the configured max_content_chars (MEMO_MAX_CONTENT_CHARS); identical content deduplicates by sha256 to the existing memory id. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||