Use this file to discover all available pages before exploring further.
This guide uses the raw HTTP API — the same surface every Orgo SDK wraps.
Drop curl, requests, or fetch against https://www.orgo.ai/api and
you’re done. No SDK required.
Prefer a helper library? Skip to Use the SDK after you’ve
seen the raw calls. The SDK is a thin wrapper around the exact same
endpoints.
Orgo exposes an OpenAI-compatible endpoint at /api/v1/chat/completions.
Point any OpenAI SDK at https://www.orgo.ai/api/v1, pass
computer_id, and the model will screenshot, click, and type on its own
until your instruction is done.
Stream the agent’s progress token-by-token with "stream": true — see
Create chat completion for the full
spec including thread continuation, custom Anthropic key, and error
handling.
If you’d rather not wire HTTP calls by hand, the official SDKs wrap this
exact surface. They give you typed helpers, connection pooling for VNC,
and one-line computer.prompt("do X") for the AI agent loop.
pip install orgo
from orgo import Computercomputer = Computer(workspace="quickstart")# Each of these is a direct wrapper over a single HTTP call.computer.left_click(100, 200)computer.type("Hello, world!")computer.key("Enter")output = computer.bash("ls -la")# One-liner for the AI agent loopcomputer.prompt("Open Chrome and search for AI news")computer.destroy()
Both SDKs read ORGO_API_KEY from the environment and default to the
same base URL you’d call directly.