Skip to main content

Installation

pip install reminix-google
This installs google-genai as a dependency.

Chat Agent

Use GoogleChatAgent for conversational agents with streaming support.
from google import genai
from reminix_google import GoogleChatAgent
from reminix_runtime import serve

client = genai.Client()

chatbot = GoogleChatAgent(client, name="chatbot", instructions="You are a helpful assistant.")

serve(agents=[chatbot])
The default model is gemini-2.5-flash. Override it with the model parameter:
chatbot = GoogleChatAgent(
    client,
    name="chatbot",
    model="gemini-2.5-pro",
    instructions="You are a helpful assistant.",
)

Streaming

Chat agents support streaming out of the box:
from reminix import Reminix

client = Reminix()

stream = client.agents.chat(
    "chatbot",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for event in stream:
    if event.type == "text_delta":
        print(event.delta, end="", flush=True)

Task Agent

Use GoogleTaskAgent for structured output with a defined schema.
from google import genai
from reminix_google import GoogleTaskAgent
from reminix_runtime import serve

client = genai.Client()

analyzer = GoogleTaskAgent(
    client,
    name="analyzer",
    instructions="Analyze the sentiment of the given text.",
    output_schema={
        "type": "object",
        "properties": {
            "sentiment": {"type": "string", "enum": ["positive", "negative", "neutral"]},
            "confidence": {"type": "number"},
        },
        "required": ["sentiment", "confidence"],
    },
)

serve(agents=[analyzer])

Options

The first argument to all Google AI agent constructors is a genai.Client instance.
name
str
required
Agent name. Used as the endpoint identifier.
model
str
Google AI model to use. Defaults to gemini-2.5-flash.
max_tokens
int
Maximum number of tokens to generate.
instructions
str
System prompt for the model.
description
str
Agent description for discovery and documentation.
output_schema
dict
Output schema for task agents. Defines the structured output format.
tags
list[str]
Tags for filtering and organizing agents.
metadata
dict
Additional metadata attached to the agent.

Next steps

Deploying

Ship your Google AI agent to production.

Configuration & Secrets

Where to put your GOOGLE_API_KEY.

OpenAI

Same flow with the OpenAI SDK.

TypeScript: Google AI

The same integration in TypeScript.