Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.orgo.ai/llms.txt

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

Orgo Hero Light

​
Overview

Orgo is desktop infrastructure for AI agents. Launch headless cloud VMs that AI models can control and interact with.

Quick Start

Get started in under 5 minutes

Create an Account

Get your API key

​
What is computer use?

AI computer use enables AI models to directly control computers — viewing screens, clicking, typing, and running commands just like a human. Anthropic, OpenAI, and Google have all shipped computer use agents (CUAs) that can interact with desktop environments autonomously. Running these agents on your own machine works for experimentation but lacks security, scalability, and production-ready infrastructure. Orgo provides cloud desktops purpose-built for AI agents.

​
How it works

Orgo is a plain HTTP API. Any language with an HTTP client works — below is a two-step flow: create a computer, then hand it to a Claude agent over the OpenAI-compatible endpoint. 
# 1. Create a computer (one HTTP call, boots in <500ms)
curl -X POST https://www.orgo.ai/api/computers \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"workspace_id": "$WORKSPACE_ID", "name": "agent-1"}'

# 2. Let Claude drive it (OpenAI-compatible, any SDK works)
curl https://www.orgo.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.6",
    "computer_id": "$COMPUTER_ID",
    "messages": [
      {"role": "user", "content": "Find a funny cat image and save it to the desktop"}
    ]
  }'
The agent takes screenshots, clicks, types, and runs commands until the task is done. You can also call individual actions directly — see API Reference for every endpoint. Prefer a helper library? The Python and TypeScript SDKs wrap this exact surface.

​
Agent loop

Computer use agents typically operate in a loop:
  1. See - Capture a screenshot
  2. Decide - AI analyzes the screen and decides what to do
  3. Act - Perform mouse/keyboard actions
  4. Repeat - Continue until task is complete

​
Key features

Fast boot

Computers boot in under 500ms

Full control

Mouse, keyboard, and code execution

Templates

Pre-configure environments with installed software

Bring your own model

Claude, GPT-4, OpenAI-compatible API

​
Get started

Quickstart

Launch your first computer

Templates

Pre-configure environments

Use Any Model

Claude, GPT, Gemini, and more

API Reference

Explore the API