membrain-client 0.1.0

Python client for Membrain AI Safety Gateway — drop-in replacement for OpenAI SDK

membrain-client

Python client for the Membrain AI Safety Gateway. Drop-in replacement for the OpenAI Python SDK that routes requests through Membrain for PII detection, policy enforcement, cost tracking, and audit logging.

Installation

pip install membrain-client

Quick Start

Synchronous

from membrain_client import MembrainClient

client = MembrainClient(
    base_url="http://localhost:8001",
    api_key="mb-your-api-key",
)

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

Async

import asyncio
from membrain_client import AsyncMembrainClient

async def main():
    client = AsyncMembrainClient(
        base_url="http://localhost:8001",
        api_key="mb-your-api-key",
    )
    response = await client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}],
    )
    print(response.choices[0].message.content)
    await client.aclose()

asyncio.run(main())

Streaming

from membrain_client import MembrainClient

client = MembrainClient(base_url="http://localhost:8001", api_key="mb-your-api-key")

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a joke."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Configuration

Parameter	Default	Description
base_url	http://localhost:8001	Membrain gateway URL
api_key	None	Membrain API key
user_id	None	User identifier for audit trails
project	None	Project scope for multi-tenant setups
timeout	120.0	Request timeout in seconds
max_retries	3	Retry count for 429/5xx errors

Requirements

• Python 3.10+
• httpx >= 0.27

License

Apache-2.0