Skip to main content
The add method stores conversation messages into memory. Cognis automatically extracts key facts, preferences, and context from the messages and stores them as discrete, searchable memory records.

​
Basic Usage

from lyzr import Cognis

cog = Cognis(api_key="sk-your-api-key")

result = cog.add(
    messages=[
        {"role": "user", "content": "My name is Alice and I work at Acme Corp."},
        {"role": "assistant", "content": "Nice to meet you, Alice! What do you do at Acme Corp?"},
    ],
    owner_id="user_alice",
)

print(result)
# {"success": True, "session_id": "..."}

​
Method Signature

cog.add(
    messages: List[Dict[str, str] | CognisMessage],
    owner_id: str | None = None,
    agent_id: str | None = None,
    session_id: str | None = None,
) -> Dict[str, Any]

​
Parameters

ParameterTypeRequiredDescription
messagesList[Dict[str, str] | CognisMessage]YesList of conversation messages. Each message must have role and content keys.
owner_idstrNo*Owner/user identifier for scoping memories.
agent_idstrNo*Agent identifier for scoping memories.
session_idstrNo*Session identifier for scoping memories.
*At least one of owner_id, agent_id, or session_id must be provided.

​
Response

Returns a dictionary with operation results: 
{
  "success": true,
  "session_id": "sess_abc123",
  "memories_created": 2
}

​
Using CognisMessage Objects

Instead of plain dictionaries, you can use CognisMessage objects for type safety: 
from lyzr import Cognis, CognisMessage

cog = Cognis(api_key="sk-your-api-key")

result = cog.add(
    messages=[
        CognisMessage(role="user", content="I prefer dark mode in all apps."),
        CognisMessage(role="assistant", content="Noted! I'll keep that preference in mind."),
    ],
    owner_id="user_alice",
)

​
Multi-Turn Conversations

You can add longer conversations with multiple message pairs: 
result = cog.add(
    messages=[
        {"role": "user", "content": "I'm working on a Python project."},
        {"role": "assistant", "content": "What kind of project?"},
        {"role": "user", "content": "A REST API using FastAPI."},
        {"role": "assistant", "content": "FastAPI is a great choice!"},
        {"role": "user", "content": "I need help with authentication."},
        {"role": "assistant", "content": "I'd recommend using OAuth2 with JWT tokens."},
    ],
    owner_id="user_alice",
    session_id="project_session",
)

​
Scoping with Multiple Identifiers

Combine identifiers for fine-grained memory scoping: 
# User + agent scoped
cog.add(
    messages=messages,
    owner_id="user_alice",
    agent_id="support_bot",
)

# User + session scoped
cog.add(
    messages=messages,
    owner_id="user_alice",
    session_id="sess_001",
)

# All three identifiers
cog.add(
    messages=messages,
    owner_id="user_alice",
    agent_id="support_bot",
    session_id="sess_001",
)

​
Async Usage

import asyncio
from lyzr import Cognis

async def main():
    async with Cognis(api_key="sk-your-api-key") as cog:
        result = await cog.aadd(
            messages=[
                {"role": "user", "content": "I love hiking on weekends."},
                {"role": "assistant", "content": "That sounds fun!"},
            ],
            owner_id="user_alice",
        )
        print(result)

asyncio.run(main())
Send messages in natural conversation pairs (user/assistant) for best memory extraction. The service extracts facts from context, so richer conversations produce more useful memories.