OpenAI SDK

1. Install the CLI

npm install -g swytchcode

irm https://cli.swytchcode.com/install.ps1 | iex

curl -fsSL https://cli.swytchcode.com/install.sh | sh

Use swy as a shorter alias for swytchcode.

2. Install the packages

JavaScript
Python

npm install @swytchcode/runtime @openai/agents dotenv

pip install swytchcode-runtime openai-agents python-dotenv

3. Initialize Swytchcode and fetch a toolkit

swy init
swy get github

swy init creates .swytchcode/ and tooling.json for the project. swy get github downloads the GitHub integration bundle - the schemas that tools.get reads from in a later step.

4. List available methods

swy list methods

This lists every method from the integrations you’ve downloaded, so you can see what the GitHub bundle exposes before you load tools in the SDK.

5. Enable a tool and connect GitHub

swy add <canonical_id>
swy auth connect github

Copy a canonical ID from swy list methods. For example:

swy add github.issues.create

swy add writes that method into tooling.json so the SDK can execute it. swy auth connect github opens a browser so you can authorize GitHub.

import 'dotenv/config';
import { Swytchcode } from '@swytchcode/runtime';
import { OpenAIAgentsProvider } from '@swytchcode/runtime/providers/openai-agents';

const swx = new Swytchcode(new OpenAIAgentsProvider());

const tools = await swx.tools.get({ toolkits: ['github'] });

import os
from dotenv import load_dotenv
from swytchcode_runtime import Swytchcode
from swytchcode_runtime.providers.openai_agents import OpenAIAgentsProvider

load_dotenv()

swx = Swytchcode(provider=OpenAIAgentsProvider())
tools = swx.tools.get(toolkits=["github"])

print(f"Loaded {len(tools)} tools")

7. Run the agent

JavaScript
Python

import { Agent, run } from '@openai/agents';

const agent = new Agent({
  name: 'Assistant',
  instructions: 'You are a helpful assistant.',
  tools,
});

const result = await run(agent, 'List my open GitHub issues and summarize them.');

console.log(result.finalOutput);

from agents import Agent, Runner

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant.",
    tools=tools,
)

result = Runner.run_sync(agent, "List my open GitHub issues and summarize them.")

print(result.final_output)

8. Run the file

Save the example as main.js or main.py, then run the matching command:

JavaScript
Python

node main.js

python main.py

The runtime maps the agent’s tool calls to the Swytchcode execution layer.

Example projects

Browse all examples

Star Repo Agent

Minimal OpenAI Agents SDK example that stars a GitHub repo through Swytchcode-brokered OAuth.