Skip to main content
The skyvern package wraps the Skyvern REST API in a typed, async Python client. 
pip install skyvern
Requires Python 3.11+. If you hit version errors, use pipx install skyvern to install in an isolated environment.

​
Initialize the client

The Skyvern class is async — all methods are coroutines. Wrap calls in an async function and use asyncio.run() as the entry point: 
import asyncio
from skyvern import Skyvern

async def main():
    client = Skyvern(api_key="YOUR_API_KEY")

    result = await client.run_task(
        prompt="Get the title of the top post on Hacker News",
        url="https://news.ycombinator.com",
        wait_for_completion=True,
    )
    print(result.output)

asyncio.run(main())
If you’re inside a framework that already runs an event loop (FastAPI, Django ASGI), await directly without asyncio.run().

​
Constructor parameters

ParameterTypeDefaultDescription
api_keystr—Required. Your Skyvern API key. Get one at app.skyvern.com/settings.
environmentSkyvernEnvironmentCLOUDTarget environment. Options: CLOUD, STAGING, LOCAL.
base_urlstr | NoneNoneOverride the API base URL. Use this for self-hosted deployments.
timeoutfloat | NoneNoneHTTP request timeout in seconds.
follow_redirectsboolTrueWhether to follow HTTP redirects.
httpx_clientAsyncClient | NoneNoneProvide your own httpx client for custom TLS, proxying, or connection pooling.

​
Environments

The SDK ships with three built-in environment URLs: 
from skyvern.client import SkyvernEnvironment
EnvironmentURLWhen to use
SkyvernEnvironment.CLOUDhttps://api.skyvern.comSkyvern Cloud (default)
SkyvernEnvironment.STAGINGhttps://api.staging.skyvern.comStaging environment for testing
SkyvernEnvironment.LOCALhttp://localhost:8000Local server started with skyvern run server
For a self-hosted instance at a custom URL, pass base_url instead: 
client = Skyvern(
    api_key="YOUR_API_KEY",
    base_url="https://skyvern.your-company.com",
)

​
Local mode

Run Skyvern entirely on your machine — no cloud, no network calls. Skyvern.local() reads your .env file, boots the engine in-process, and connects the client to it. Prerequisite: Run skyvern quickstart once to create the .env file with your database connection and LLM API keys. 
from skyvern import Skyvern

client = Skyvern.local()

result = await client.run_task(
    prompt="Get the title of the top post",
    url="https://news.ycombinator.com",
    wait_for_completion=True,
)
If you configured headful mode during skyvern quickstart, a Chromium window opens on your machine so you can watch the AI work.
ParameterTypeDefaultDescription
llm_configLLMConfig | LLMRouterConfig | NoneNoneOverride the LLM. If omitted, uses LLM_KEY from .env.
settingsdict | NoneNoneOverride .env settings at runtime. Example: {"MAX_STEPS_PER_RUN": 100}

​
wait_for_completion

By default, run_task and run_workflow return immediately after the run is queued — you get a run_id and need to poll get_run() yourself. Pass wait_for_completion=True to have the SDK poll automatically until the run reaches a terminal state (completed, failed, terminated, timed_out, or canceled): 
# Returns only after the task finishes (up to 30 min by default)
result = await client.run_task(
    prompt="Fill out the contact form",
    url="https://example.com/contact",
    wait_for_completion=True,
    timeout=600,  # give up after 10 minutes
)

# Without wait_for_completion — returns immediately
task = await client.run_task(
    prompt="Fill out the contact form",
    url="https://example.com/contact",
)
print(task.run_id)  # poll with client.get_run(task.run_id)
ParameterTypeDefaultDescription
wait_for_completionboolFalsePoll until the run finishes.
timeoutfloat1800Maximum wait time in seconds. Raises Python’s TimeoutError if exceeded.
Supported on run_task, run_workflow, and login.

​
Request options

Every method accepts an optional request_options parameter for per-request overrides of timeout, retries, and headers: 
from skyvern.client.core import RequestOptions

result = await client.run_task(
    prompt="Extract data",
    url="https://example.com",
    request_options=RequestOptions(
        timeout_in_seconds=120,
        max_retries=3,
        additional_headers={"x-custom-header": "value"},
    ),
)
These override the client-level defaults for that single call only.

​
Next steps

Tasks

Run browser automations with run_task

Workflows

Create and run multi-step automations

Browser Sessions

Maintain live browser state between calls

Error Handling

Handle errors and configure retries