Tools / Memory
get_memory()
KeyThe L2 drill-down: the full evidence card for one memory item — content, type, status, linked entities, evidence, and its available_at stamp.
get_memory(memory_id)→ EVIDENCE CARDCallable over MCP as get_memory(memory_id). REST mirror GET /v1/memories Planned — alpha is MCP-only
The drill-down. Search and packs return summaries plus ids; when an item is load-bearing for a recommendation, the agent pulls the full evidence card — content, status, linked entities, evidence, timestamps — before leaning on it.
Over MCP, your agent invokes it on its own when the moment calls for it — just describe the situation. A Python SDK for headless runtimes is planned; this is what the call will look like.
agent · python sdk
from cascadian import Cascadian
cx = Cascadian(api_key=os.environ["CASCADIAN_API_KEY"])
result = cx.get_memory(
memory_id="mem_0871",
)
| Param | Type | Description |
|---|---|---|
| memory_idREQUIRED | string | The memory item to load in full. |
get_memory()
{
"id": "mem_0871", "type": "belief", "status": "approved",
"content": "Discount pulls deals forward; net win-rate lift unclear.",
"entities": ["discount_tier", "win_rate"],
"evidence": ["src_0307"],
"available_at": "2026-04-02T09:12:00Z"
}
keybootstrap()The ~200-token session card your agent reads first.keyingest_source()Store a raw source — chunked, embedded, indexed.keyassert_fact()Write a temporal fact with an honest available_at.keypropose_memory()Propose a memory item — contradiction-checked on write.keylink_memories()A typed relationship edge, with rationale.keysupersede_memory()Revise without erasing — new row, old row closed.keysearch_memory()Hybrid retrieval with an honest empty result.keyget_facts()What was true, as of any moment.keyget_entity()The versioned dossier for one entity.keyget_context_pack()Everything knowable for a decision, stamped and typed.keylist_contradictions()Open conflicts waiting on a human.