Skip to content
Get started

Update

projects.memory.update(strproject_id, MemoryUpdateParams**kwargs) -> MemoryUpdateResponse
PUT/projects/{projectId}/memory

Set the caller’s assistant memory scoped to this project (markdown, max 30KB). Set content to null to clear.

ParametersExpand Collapse
project_id: str
content: Optional[str]

Markdown content of the memory. Set to null to clear. Max size depends on the scope (20-50 KB).

ReturnsExpand Collapse
class MemoryUpdateResponse: …
memory: Optional[Memory]

Public JSON shape returned by GET endpoints

id: str

The memory ID — deterministic from scope + parent IDs (example: “mem_team_team_abc”)

content: str

Markdown content of the memory

created_at: str

ISO 8601 timestamp when the memory was first written

size_bytes: float

UTF-8 byte length of the content — used for quota enforcement

updated_at: str

ISO 8601 timestamp when the memory was last updated

updated_by: str

The userId of the last writer — useful for audit/UI

Update

import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),  # This is the default and can be omitted
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),  # This is the default and can be omitted
)
memory = client.projects.memory.update(
    project_id="projectId",
)
print(memory.memory)
{
  "memory": {
    "id": "id",
    "content": "content",
    "createdAt": "createdAt",
    "sizeBytes": 0,
    "updatedAt": "updatedAt",
    "updatedBy": "updatedBy"
  }
}
Returns Examples
{
  "memory": {
    "id": "id",
    "content": "content",
    "createdAt": "createdAt",
    "sizeBytes": 0,
    "updatedAt": "updatedAt",
    "updatedBy": "updatedBy"
  }
}