Introduction

• No code. Sign in at orgo.ai and launch an agent or a computer from the dashboard. See Start in the dashboard.
• With code. Create and drive computers from the API, the CLI, or an MCP client. See the Quickstart.

​

What Orgo is

• Give an agent its own computer. Install Hermes Agent, OpenClaw, or any other agent there, so it has a home that stays on instead of a laptop.
• Run coding agents continuously. Run Claude Code, Codex, or similar CLIs on an Orgo computer so they stay online across sessions and can be reached from any device.
• Drive a computer with a model. Wire an Anthropic, OpenAI, Google, or any OpenAI-compatible model to an Orgo computer and let it screenshot, click, type, and run commands. Useful for software that doesn’t expose an API.

​

From one agent to a fleet

• Isolated. Each computer is its own virtual machine with its own disk.
• No limit on how many run at once. Paid plans include 50 computers per account. Past that, more run by the hour from credit, up to 999 per account. For a larger fleet, contact us.
• Everything from code. The API, SDKs, CLI, and MCP create, fork, clone, start, stop, and resize computers live, and can give one an end time after which it is deleted.
• Built to repeat. Templates launch the same setup again and again. Workspaces group computers, and an API key can be scoped to one workspace or one computer, as described in Key scopes and computer keys.
• Predictable limits. API rate limits are set by plan and counted per account, as described in Rate limits.

​

What Orgo is not

​

How it works

• API. A plain HTTP API. Any language with an HTTP client works, and the Python and TypeScript SDKs wrap it.
• CLI. orgo from your terminal, for creating computers and driving them by hand.
• MCP. An MCP server, so any MCP client controls your computers directly.

# 1. Create a computer (one HTTP call). Set $WORKSPACE_ID to your workspace ID.
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 an agent drive it (OpenAI-compatible, any SDK works).
#    Set $COMPUTER_ID to the "id" returned by step 1.
curl https://www.orgo.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "computer_id": "'"$COMPUTER_ID"'",
    "messages": [
      {"role": "user", "content": "Find a funny cat image and save it to the desktop"}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.orgo.ai/api/v1", api_key=os.environ["ORGO_API_KEY"])

response = client.chat.completions.create(
    model="orgo-agent",
    messages=[{"role": "user", "content": "Find a funny cat image and save it to the desktop"}],
    extra_body={"computer_id": os.environ["COMPUTER_ID"]},
)
print(response.choices[0].message.content)

import OpenAI from "openai";
import type { ChatCompletionCreateParamsNonStreaming } from "openai/resources/chat/completions";

const client = new OpenAI({
  baseURL: "https://www.orgo.ai/api/v1",
  apiKey: process.env.ORGO_API_KEY,
});

// computer_id is an Orgo field. The SDK sends it as-is; add it to the type.
const params: ChatCompletionCreateParamsNonStreaming & { computer_id: string } = {
  model: "orgo-agent",
  messages: [{ role: "user", content: "Find a funny cat image and save it to the desktop" }],
  computer_id: process.env.COMPUTER_ID!,
};

const response = await client.chat.completions.create(params);

console.log(response.choices[0].message.content);

​

Agent loop

1. See. Capture a screenshot.
2. Decide. The model analyzes the screen and chooses an action.
3. Act. Perform a mouse, keyboard, or shell action.
4. Repeat. Continue until the task is complete.

​

Key capabilities

​

Get started