Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.plato.so/llms.txt

Use this file to discover all available pages before exploring further.

​
PlatoClient

The PlatoClient is your main entry point for interacting with the Plato platform. It handles authentication, environment creation, task management, and simulator operations.

​
Initialization

from plato import Plato

# Initialize with environment variables
client = Plato()

# Or specify API key directly
client = Plato(api_key="your_api_key")

# Custom configuration
client = Plato(
    api_key="your_api_key",
    base_url="https://plato.so/api",  # Optional: API endpoint
)

​
Environment Management

​
Create Environment

Create a new Plato environment for testing and automation: 
# Basic environment creation
env = await client.make_environment(env_id="doordash")

# Advanced environment creation with custom settings
env = await client.make_environment(
    env_id="doordash",
    open_page_on_start=True,
    viewport_width=1920,
    viewport_height=1080,
    interface_type="browser",
    record_network_requests=True,
    record_actions=True,
    env_config={"custom_setting": "value"},
    keepalive=True,
    alias="my-test-environment"
)

# Use as context manager for automatic cleanup
async with client.make_environment("doordash") as env:
    # Your automation code here
    pass
Parameters:
  • env_id (str): Environment identifier (e.g., “doordash”, “espocrm”)
  • open_page_on_start (bool): Whether to open the page immediately
  • viewport_width/height (int): Browser viewport dimensions
  • interface_type (str): Interface type (“browser” or “noop”)
  • record_network_requests (bool): Enable network request recording
  • record_actions (bool): Enable action recording
  • env_config (dict): Custom environment configuration
  • keepalive (bool): Prevent job termination due to heartbeat failures
  • alias (str): Optional alias for the job group

​
Close Client

Properly close the client and clean up resources: 
# Close the client session
await client.close()

​
Simulator Management

​
List Simulators

Get all available simulators: 
simulators = await client.list_simulators()

for simulator in simulators:
    print(f"Name: {simulator['name']}")
    print(f"Description: {simulator['description']}")
    print(f"Enabled: {simulator['enabled']}")
Returns a list of enabled simulators with their metadata.

​
Task Management

​
Load Tasks by Simulator Name

Load all tasks from a specific simulator: 
# Load tasks from a simulator
tasks = await client.load_tasks("doordash")

for task in tasks:
    print(f"Task: {task.name}")
    print(f"ID: {task.public_id}")
    print(f"Prompt: {task.prompt}")
    print(f"Start URL: {task.start_url}")
    print(f"Average Time: {task.average_time}s")
    print(f"Average Steps: {task.average_steps}")

​
List Tasks by Simulator ID

Get tasks using the simulator’s internal ID: 
# Get tasks by simulator ID
tasks = await client.list_simulator_tasks_by_id("simulator_id_123")

for task in tasks:
    print(f"Name: {task['name']}")
    print(f"Public ID: {task['publicId']}")
    print(f"Prompt: {task['prompt']}")

​
Complete Example

Here’s a complete example showing typical usage: 
import asyncio
from plato import Plato

async def main():
    # Initialize client
    client = Plato(api_key="your-api-key")

    # List available simulators
    simulators = await client.list_simulators()
    print(f"Available simulators: {[s['name'] for s in simulators]}")

    # Load tasks for a specific simulator
    tasks = await client.load_tasks("doordash")
    print(f"Found {len(tasks)} tasks")

    # Create environment
    env = await client.make_environment("doordash")

    # Start interaction
    await env.reset()
    cdp_url = await env.get_cdp_url()

    # Take actions with your agent
    your_agent = await YourAgent(cdp_url).start()

    # Get final state mutations
    state_changes = await env.get_state()

    # Clean up
    await env.close()
    await client.close()

asyncio.run(main())

​
Environment Variables

The client looks for these environment variables: 
# Required
PLATO_API_KEY=your_api_key
PLATO_BASE_URL=https://plato.so/api

​
Error Handling

from plato.exceptions import PlatoClientError

try:
    env = await client.make_environment("invalid_env_id")
except PlatoClientError as e:
    print(f"Plato error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")
Always properly close the client and its environments when done to free up resources. Use context managers (async with) for automatic cleanup.