Tools / Memory
get_entity()
KeyA versioned entity dossier: summary, key facts, open questions — plus drill-down ids for the L2 reads behind each line.
get_entity(entity_id, as_of)→ DOSSIERCallable over MCP as get_entity(entity_id, as_of). REST mirror GET /v1/entities Planned — alpha is MCP-only
The L2 dossier when one entity is the subject: summary, key facts, open questions, and ids to drill further. The open-questions block is often the most useful part — it tells the agent what the workspace knows it doesn't know.
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_entity(
entity_id="ent_discount_tier",
as_of="2026-06-11T17:00:00Z",
)
| Param | Type | Description |
|---|---|---|
| entity_idREQUIRED | string | The entity to load. |
| as_of | timestamp | Dossier as of this moment. Default now. |
get_entity()
{
"entity": "discount_tier",
"summary": "15% closing discount, live since 2025-09",
"key_facts": ["fct_2231"],
"open_questions": ["effect on enterprise win rate unmeasured"],
"drill_down": ["mem_0871", "mem_0912"]
}
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_memory()The full evidence card, by id.keyget_context_pack()Everything knowable for a decision, stamped and typed.keylist_contradictions()Open conflicts waiting on a human.