Cognis provides two methods for retrieving memories: get() lists all memories with pagination support, and get_memory() fetches a single memory by its ID.
List All Memories
from lyzr import Cognis
cog = Cognis(api_key="sk-your-api-key")
memories = cog.get(owner_id="user_alice")
for memory in memories:
print(f"{memory.id}: {memory.content}")
get() Method Signature
cog.get(
owner_id: str | None = None,
agent_id: str | None = None,
session_id: str | None = None,
limit: int | None = None,
offset: int | None = None,
include_historical: bool | None = None,
cross_session: bool | None = None,
) -> CognisMemoryList
get() Parameters
| Parameter | Type | Required | Description |
|---|
owner_id | str | No* | Filter by owner/user identifier. |
agent_id | str | No* | Filter by agent identifier. |
session_id | str | No* | Filter by session identifier. |
limit | int | No | Maximum number of memories to return. |
offset | int | No | Number of records to skip (for pagination). |
include_historical | bool | No | Include previous versions of updated memories. |
cross_session | bool | No | Retrieve memories across all sessions. |
*At least one of owner_id, agent_id, or session_id must be provided.
CognisMemoryList Response
get() returns a CognisMemoryList object that is iterable and supports len():
memories = cog.get(owner_id="user_alice")
print(len(memories)) # Number of memories
print(memories.total) # Total count
print(memories[0].content) # Access by index
for memory in memories:
print(memory.content)
CognisMemoryRecord Fields
Each memory in the list is a CognisMemoryRecord with the following fields:
| Field | Type | Description |
|---|
id | str | Memory record ID. |
content | str | The memory content. |
owner_id | str | None | Owner identifier. |
agent_id | str | None | Agent identifier. |
session_id | str | None | Session identifier. |
status | str | None | Memory status. |
is_current | bool | None | Whether this is the current version. |
version | int | None | Version number. |
salience_score | float | None | Importance score. |
decay_score | float | None | Temporal decay score. |
metadata | Dict | None | Additional metadata. |
created_at | str | None | Creation timestamp. |
updated_at | str | None | Last update timestamp. |
Get a Single Memory
Retrieve a specific memory by its ID:
memory = cog.get_memory(memory_id="mem_abc123")
print(memory.id)
print(memory.content)
print(memory.created_at)
get_memory() Method Signature
cog.get_memory(
memory_id: str,
owner_id: str | None = None,
) -> CognisMemoryRecord
get_memory() Parameters
| Parameter | Type | Required | Description |
|---|
memory_id | str | Yes | The ID of the memory to retrieve. |
owner_id | str | No | Owner identifier for additional scoping. |
limit and offset to paginate through large result sets:
# First page
page1 = cog.get(owner_id="user_alice", limit=10, offset=0)
# Second page
page2 = cog.get(owner_id="user_alice", limit=10, offset=10)
# Process all pages
offset = 0
page_size = 20
while True:
page = cog.get(owner_id="user_alice", limit=page_size, offset=offset)
if len(page) == 0:
break
for memory in page:
print(memory.content)
offset += page_size
Include Historical Versions
Retrieve previous versions of memories that have been updated:
memories = cog.get(
owner_id="user_alice",
include_historical=True,
)
for memory in memories:
print(f"v{memory.version}: {memory.content} (current: {memory.is_current})")
Cross-Session Retrieval
Retrieve memories from all sessions for an owner:
all_memories = cog.get(
owner_id="user_alice",
cross_session=True,
)
Async Usage
import asyncio
from lyzr import Cognis
async def main():
async with Cognis(api_key="sk-your-api-key") as cog:
# List all memories
memories = await cog.aget(owner_id="user_alice")
for memory in memories:
print(memory.content)
# Get a specific memory
memory = await cog.aget_memory(memory_id="mem_abc123")
print(memory.content)
asyncio.run(main())
