OpenAI

Memori supports all OpenAI Chat Completions and Responses APIs. Both sync and async clients are fully supported.

Quick Start

OpenAI Integration

from memori import Memori
from openai import OpenAI

client = OpenAI()

mem = Memori().llm.register(client)
mem.attribution(entity_id="user_123", process_id="my_agent")

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Supported Modes

Mode	Method
Sync	`client.chat.completions.create()`
Async	`await client.chat.completions.create()`
Streamed	`stream=True` parameter
Responses API	`client.responses.create()`

Multi-Turn Conversations

Memori automatically captures each interaction and links them within the same session.

from memori import Memori
from openai import OpenAI

client = OpenAI()

mem = Memori().llm.register(client)
mem.attribution(entity_id="user_123", process_id="my_agent")

messages = [
    {"role": "user", "content": "My name is Alice."}
]

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages
)
messages.append({
    "role": "assistant",
    "content": response.choices[0].message.content
})

messages.append({
    "role": "user",
    "content": "What's my name?"
})
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages
)
print(response.choices[0].message.content)