Skip to main content
Get your first agent live and start calling it from your app. Configure via UI for quick results, or deploy custom code for full control — either way, you’ll have a working agent in minutes.

​
1. Get Your API Key

  1. Sign in to the Reminix Dashboard
  2. Navigate to your project settings
  3. Copy your Project API Key
Your API key looks like: reminix_sk_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

​
2. Install the SDK

pip install reminix

​
3. Invoke a Task Agent

Invoke a stateless operation with a task-oriented agent: 
import os
from reminix import Reminix

client = Reminix(api_key=os.environ.get("REMINIX_API_KEY"))

response = client.agents.invoke(
    "my-agent",
    prompt="Analyze this data and provide insights",
    data={"sales": [100, 200, 150, 300]}
)

print(response["content"])

​
4. Chat with an Agent

Have a conversation with a chat agent: 
response = client.agents.invoke(
    "chat-assistant",
    messages=[
        {"role": "user", "content": "Hello! What can you do?"}
    ]
)

# Chat agents return 'message' with the assistant's response
print(response["message"]["content"])

​
5. Stream Responses

Get real-time streaming responses: 
# Streaming task agent
for chunk in client.agents.invoke(
    "my-agent",
    prompt="Generate a story about AI",
    stream=True
):
    print(chunk, end="", flush=True)

# Streaming chat agent
for chunk in client.agents.invoke(
    "chat-assistant",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
):
    print(chunk, end="", flush=True)

​
Next Steps

Agents

Learn about agent types

Streaming

Real-time responses

Python SDK

Full Python documentation

TypeScript SDK

Full TypeScript documentation