Orgo - Cloud computers for AI agents

This guide uses the raw HTTP API - the same surface the CLI wraps. Drop curl, requests, or fetch against https://www.orgo.ai/api and you’re done.

Prefer the terminal? The Orgo CLI wraps this same API with orgo commands and a live orgo ssh shell.

1. Get your API key

Create an account at orgo.ai/start, then copy your key from orgo.ai/workspaces.

export ORGO_API_KEY=sk_live_...

Every request takes this as a bearer token:

Authorization: Bearer $ORGO_API_KEY

2. Create a workspace

Workspaces group related computers.

curl -X POST https://www.orgo.ai/api/workspaces \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "quickstart"}'

import os, requests

r = requests.post(
    "https://www.orgo.ai/api/workspaces",
    headers={"Authorization": f"Bearer {os.environ['ORGO_API_KEY']}"},
    json={"name": "quickstart"},
)
workspace = r.json()
print(workspace["id"])

const r = await fetch("https://www.orgo.ai/api/workspaces", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ORGO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ name: "quickstart" }),
});
const workspace = await r.json();
console.log(workspace.id);

Response:

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "name": "quickstart",
  "status": "active",
  "created_at": "2026-04-22T10:00:00Z"
}

Save the id. You’ll pass it as workspace_id when creating a computer.

3. Create a computer

curl -X POST https://www.orgo.ai/api/computers \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workspace_id": "550e8400-e29b-41d4-a716-446655440000",
    "name": "agent-1",
    "ram": 4,
    "cpu": 1
  }'

r = requests.post(
    "https://www.orgo.ai/api/computers",
    headers={"Authorization": f"Bearer {os.environ['ORGO_API_KEY']}"},
    json={
        "workspace_id": workspace["id"],
        "name": "agent-1",
        "ram": 4,
        "cpu": 1,
    },
)
computer = r.json()
print(computer["id"], computer["status"])

const r = await fetch("https://www.orgo.ai/api/computers", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ORGO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    workspace_id: workspace.id,
    name: "agent-1",
    ram: 4,
    cpu: 1,
  }),
});
const computer = await r.json();
console.log(computer.id, computer.status);

Response (abridged):

{
  "id": "a3bb189e-8bf9-3888-9912-ace4e6543002",
  "name": "agent-1",
  "status": "running",
  "ram": 4,
  "cpu": 1,
  "resolution": "1280x720x24",
  "url": "https://orgo.ai/workspaces/550e8400-e29b-41d4-a716-446655440000/computers/a3bb189e-8bf9-3888-9912-ace4e6543002"
}

The computer boots in under 500ms and is ready to accept commands immediately.

4. Take a screenshot

curl https://www.orgo.ai/api/computers/$COMPUTER_ID/screenshot \
  -H "Authorization: Bearer $ORGO_API_KEY"

r = requests.get(
    f"https://www.orgo.ai/api/computers/{computer['id']}/screenshot",
    headers={"Authorization": f"Bearer {os.environ['ORGO_API_KEY']}"},
)
# `image` is a public URL to the PNG - fetch it to get the bytes.
image_url = r.json()["image"]
with open("screenshot.png", "wb") as f:
    f.write(requests.get(image_url).content)

const r = await fetch(
  `https://www.orgo.ai/api/computers/${computer.id}/screenshot`,
  { headers: { Authorization: `Bearer ${process.env.ORGO_API_KEY}` } },
);
const { image } = await r.json();
// `image` is a public URL to the PNG - fetch it to get the bytes.

5. Click, type, and run shell commands

# Click at (100, 200)
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/click \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"x": 100, "y": 200}'

# Type text
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/type \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, world!"}'

# Press Enter
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/key \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"key": "Enter"}'

# Run a shell command
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/bash \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"command": "ls -la"}'

cid = computer["id"]
base = f"https://www.orgo.ai/api/computers/{cid}"
hdr = {"Authorization": f"Bearer {os.environ['ORGO_API_KEY']}"}

requests.post(f"{base}/click", headers=hdr, json={"x": 100, "y": 200})
requests.post(f"{base}/type",  headers=hdr, json={"text": "Hello, world!"})
requests.post(f"{base}/key",   headers=hdr, json={"key": "Enter"})

r = requests.post(f"{base}/bash", headers=hdr, json={"command": "ls -la"})
print(r.json()["output"])

const cid = computer.id;
const base = `https://www.orgo.ai/api/computers/${cid}`;
const hdr = {
  Authorization: `Bearer ${process.env.ORGO_API_KEY}`,
  "Content-Type": "application/json",
};

await fetch(`${base}/click`, { method: "POST", headers: hdr, body: JSON.stringify({ x: 100, y: 200 }) });
await fetch(`${base}/type`,  { method: "POST", headers: hdr, body: JSON.stringify({ text: "Hello, world!" }) });
await fetch(`${base}/key`,   { method: "POST", headers: hdr, body: JSON.stringify({ key: "Enter" }) });

const bash = await fetch(`${base}/bash`, {
  method: "POST",
  headers: hdr,
  body: JSON.stringify({ command: "ls -la" }),
}).then((x) => x.json());
console.log(bash.output);

Full list of actions: Mouse · Keyboard · Scroll · Bash · Python exec · Wait · Drag.

6. Let an AI drive it

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.

curl https://www.orgo.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "computer_id": "a3bb189e-8bf9-3888-9912-ace4e6543002",
    "messages": [
      {"role": "user", "content": "Open Chrome and search for AI news"}
    ]
  }'

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="claude-sonnet-5",
    messages=[{"role": "user", "content": "Open Chrome and search for AI news"}],
    extra_body={"computer_id": computer["id"]},
)
print(response.choices[0].message.content)

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "Open Chrome and search for AI news" }],
  computer_id: computer.id,
} as any);

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

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.

7. Lifecycle

# Stop
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/stop \
  -H "Authorization: Bearer $ORGO_API_KEY"

# Start a stopped computer
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/start \
  -H "Authorization: Bearer $ORGO_API_KEY"

# Restart (reboot)
curl -X POST https://www.orgo.ai/api/computers/$COMPUTER_ID/restart \
  -H "Authorization: Bearer $ORGO_API_KEY"

# Delete permanently
curl -X DELETE https://www.orgo.ai/api/computers/$COMPUTER_ID \
  -H "Authorization: Bearer $ORGO_API_KEY"

Stopped computers cold-boot from their saved disk on the next start - in-memory state is not preserved and they come back with a new IP.

Use the CLI

Prefer a terminal workflow? The Orgo CLI wraps this same API - create and manage computers, run bash and exec, open a live shell with orgo ssh, and drive agent runs, all from your shell.

npm install -g orgo

See the CLI guide for the full command set.

Next steps

API Reference

Every endpoint, every field.

Use any model

Claude, GPT, Gemini, Hermes. Any OpenAI-compatible model.

Embed computers

Drop a live VM into your own app via VNC.

Get Started

Guides

Migrations

Templates

Model integrations

Quickstart

1. Get your API key

2. Create a workspace

3. Create a computer

4. Take a screenshot

5. Click, type, and run shell commands

6. Let an AI drive it

7. Lifecycle

Use the CLI

Next steps

API Reference

Use any model

Embed computers

​1. Get your API key

​2. Create a workspace

​3. Create a computer

​4. Take a screenshot

​5. Click, type, and run shell commands

​6. Let an AI drive it

​7. Lifecycle

​Use the CLI

​Next steps

API Reference

Use any model

Embed computers

1. Get your API key

2. Create a workspace

3. Create a computer

4. Take a screenshot

5. Click, type, and run shell commands

6. Let an AI drive it

7. Lifecycle

Use the CLI

Next steps