Getting started

Before you begin

Python 3.10+ if you use the Python client or install the CLI via pip.

A virtual environment (recommended):

python -m venv .venv
source .venv/bin/activate   # Windows: .venv\Scripts\activate

A Sudoiq account and an API key: create one at Sudoiq settings.

Install the Python client (for the Python tab below):

pip install agentserviceapi

The Python SDK on PyPI is agentserviceapi (pip install agentserviceapi); import it as agentsapi in code (from agentsapi import ...). The CLI wheel package name is agentservice.

Run one agent

Use the dropdown to switch between Python, Node.js, and CLI. After start, the client waits for the run to finish using a long-lived streaming connection when the API supports it (server-sent events, SSE), so you do not write your own polling loop.

Python

import asyncio
from agentsapi import AgentServiceAPIClient

async def main():
    client = AgentServiceAPIClient()
    client.set_api_key("sk_...")  # from https://sudoiq.com/settings

    result = await client.run_agent(
        agent_id="YOUR_AGENT_UUID",
        string_inputs={"1": "Hello"},
        environment="playground",
    )
    print(result.status)
    print(result.result)

asyncio.run(main())

After your first run

Add tools, validators, and tests so you can measure and improve behavior:

For alternative delivery models (for example very long-running jobs), see Running agents.

Introduction

Quickstart

Concepts

Clients

Backend

Agents

Tools

Validation

Tutorials

Reference

Before you begin

Run one agent

After your first run

Next steps

​Before you begin

​Run one agent

​After your first run

​Next steps

Before you begin

Run one agent

After your first run

Next steps