plato-sdk
Plato SDK
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you need an SDK to orchestrate AI agents against web applications and have access to the Plato backend service. The high dependency count (15 packages) and unclear license status are friction points. No known vulnerabilities as of 2026-08-14. Verify license terms and backend availability before committing to production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires PLATO_API_KEY environment variable set; requires Python 3.10+; depends on system libraries for psycopg2-binary and pymysql if database connectivity is used.
- High install friction: 15 runtime dependencies including aiohttp, openai, playwright, streamlit, boto3, psycopg2-binary, and pymysql.
- Requires Python 3.10+.
License · maintenance · safety
(unclear) — License status is unclear—no SPDX identifier or raw license text provided. Before deploying to production, verify the actual license terms with the package maintainer or documentation.
last release 2026-05-14 (92 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 490,435 downloads/mo, #6,370 on PyPI
Alternatives
Verify before relying
pip install plato-sdk
import asyncio
import os
from plato import Plato, PlatoTask
async def main():
client = Plato(api_key=os.environ.get("PLATO_API_KEY"))
env = await client.make_environment(task_env_id, open_page_on_start=False)
await env.wait_for_ready()
cdp_url = await env.get_cdp_url()
# Connect your agent via cdp_url
await env.close()
asyncio.run(main())- Whether the package is open-source and under what license terms it is distributed.
- Availability of official documentation and examples beyond the excerpt provided.
- Support status and maintenance roadmap for the 15 runtime dependencies.
- Whether the Plato backend service is a managed cloud offering or self-hosted.
- Performance and cost implications of remote environment provisioning.
What it is and what it does
Plato SDK is a client library for orchestrating automated browser agents that perform complex web tasks. It connects to a remote Plato environment backend, provisions isolated browser instances via Chrome DevTools Protocol (CDP), and provides state mutation tracking to monitor changes in web page elements as your agent interacts with them. The SDK handles environment lifecycle management, live monitoring URLs, and task evaluation.
You define a prompt and task, connect an agent to the CDP URL, and let it navigate and interact with web applications autonomously. The SDK tracks state changes (added, removed, modified fields) as JSON diffs, letting you verify task completion. It's designed for scenarios like automated form filling, e-commerce interactions, and web scraping where you need both browser control and structured state observation.
Use it for
- Automate multi-step e-commerce workflows like adding items to cart and proceeding through checkout with AI agents.
- Build web scraping agents that navigate complex sites and extract structured data while tracking page state changes.
- Create testing agents that interact with web applications and report on state mutations to verify expected behavior.
- Develop autonomous assistants that handle form submission, data entry, and navigation on behalf of users.
- Monitor and interact with dynamic web content in real time via live view URLs while agents execute tasks.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you need an SDK to orchestrate AI agents against web applications and have access to the Plato backend service. The high dependency count (15 packages) and unclear license status are friction points. No known vulnerabilities as of 2026-08-14. Verify license terms and backend availability before committing to production use.
Install
plato-sdk on PyPI
Before you install
High install friction: 15 runtime dependencies including aiohttp, openai, playwright, streamlit, boto3, psycopg2-binary, and pymysql. Requires Python 3.10+. Active maintenance (latest release 2026-05-14), but no public repository or documentation links available to verify ongoing support.
Requires PLATO_API_KEY environment variable set; requires Python 3.10+; depends on system libraries for psycopg2-binary and pymysql if database connectivity is used.
License in practice
License status is unclear—no SPDX identifier or raw license text provided. Before deploying to production, verify the actual license terms with the package maintainer or documentation.
Quickstart
pip install plato-sdk
import asyncio
import os
from plato import Plato, PlatoTask
async def main():
client = Plato(api_key=os.environ.get("PLATO_API_KEY"))
env = await client.make_environment(task_env_id, open_page_on_start=False)
await env.wait_for_ready()
cdp_url = await env.get_cdp_url()
# Connect your agent via cdp_url
await env.close()
asyncio.run(main())Verify before relying
- Whether the package is open-source and under what license terms it is distributed.
- Availability of official documentation and examples beyond the excerpt provided.
- Support status and maintenance roadmap for the 15 runtime dependencies.
- Whether the Plato backend service is a managed cloud offering or self-hosted.
- Performance and cost implications of remote environment provisioning.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | High. Source build required |
| Runtime dependencies | 15 packagesaiohttpopenaipydanticpydantic-settingsclickpython-dotenvaioboto3pyyamlrequestsboto3typerplaywrightstreamlitpsycopg2-binarypymysql |
| Maintenance | Actively maintained 92 days since the last release |
| First released | |
| Downloads | 490,435 / month, #6,370 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: plato_sdk-1.11.0.tar.gz
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “web task automation SDK”
- plato-sdkPlato SDK is a Python client library for building and running…
- browser-use-sdkPython SDK for controlling browsers programmatically through the…
- nova-actA Python SDK for building and running AI agents that automate…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also cursor-sdk · plato-sdk-v2 · agentql · browser-use-core · cdp-sdk · google-cloud-aiplatform · pydantic-deep · agentevals · cua-agent · vertexai