Skip to main content
The Orgo API lets you provision virtual computers and control them programmatically. Build AI agent fleets, automation workflows, or browser testing at scale.

​
Base URL

https://www.orgo.ai/api

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer sk_live_...
Get your API key at orgo.ai/start.

​
Quick start

​
1. Create a workspace

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

​
2. 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",
    "os": "linux",
    "ram": 4,
    "cpu": 1
  }'

​
3. Control the computer

# Take a screenshot
curl https://www.orgo.ai/api/computers/a3bb189e-8bf9-3888-9912-ace4e6543002/screenshot \
  -H "Authorization: Bearer $ORGO_API_KEY"

# Click at coordinates
curl -X POST https://www.orgo.ai/api/computers/a3bb189e-8bf9-3888-9912-ace4e6543002/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/a3bb189e-8bf9-3888-9912-ace4e6543002/type \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, world!"}'

# Run bash command
curl -X POST https://www.orgo.ai/api/computers/a3bb189e-8bf9-3888-9912-ace4e6543002/bash \
  -H "Authorization: Bearer $ORGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"command": "ls -la"}'

​
Resource hierarchy

User
└── Workspaces
    └── Computers
Workspaces group related computers together. Use them to separate environments (production, staging) or projects.

​
Computer specs

ParameterOptionsDefault
oslinuxlinux
cpu1, 2, 4, 8, 16 cores1
ram4, 8, 16, 32, 64 GB4
disk_size_gbup to plan limit8
resolutionWIDTHxHEIGHTxDEPTH (e.g., 1024x768x24, 1920x1080x24)1280x720x24
Maximum CPU/RAM/disk per computer is capped by your plan. See https://orgo.ai/pricing.
RAMCPUBest for
4 GB1 coreStandard workflows (default)
8 GB2 coresHeavier automation
16 GB4 coresDevelopment
32 GB8 coresLarge-scale processing

​
Available actions

​
Mouse

  • Click (left, right, double)
  • Drag
  • Scroll

​
Keyboard

  • Type text
  • Press keys (Enter, Tab, ctrl+c, etc.)

​
Execution

  • Bash commands
  • Python code

​
Real-time (WebSocket)

  • Terminal - interactive PTY shell
  • Audio - live PCM audio stream from the VM’s virtual speaker
  • Events - subscribe to window, clipboard, file, process, and idle events

​
Lifecycle

  • Start, stop, restart
  • Auto-stop (optional, opt-in per computer)
  • Clone (copy a computer with full disk state)
  • Resize (live CPU/RAM/disk hot-resize)
  • Move (transfer between workspaces)

​
Other

  • Screenshots
  • Wait/delays
  • RTMP streaming

​
Templates

Templates are reproducible computers defined in a single orgo.ai/v1 file — hardware, installed apps, long-running services, secrets, and lifecycle hooks. Orgo builds the file once into a golden snapshot, and every launch restores from it in seconds.

​
Resource IDs

Every Orgo resource is identified by a UUID. Pass the UUID in the URL path wherever you see {id} - e.g., /computers/a3bb189e-8bf9-3888-9912-ace4e6543002/click. Workspace and computer UUIDs are returned in the id field of every create / get / list response.

​
Error responses

All errors return a JSON object with an error field: 
{
  "error": "Invalid API key"
}
StatusMeaning
200Success
207Partial success (resize only - some dimensions applied, others rejected)
400Invalid request - bad JSON, missing required field, out-of-range value
401Missing or invalid API key
403Authenticated, but not allowed - plan limit exceeded or no access to the resource
404Resource not found, or you don’t have access to it
405Method not allowed - check the verb for the endpoint
409Conflict - resource is in a state that blocks this operation (e.g. stopping a stopped computer)
422Validation failed - all dimensions of a resize were rejected
429Rate limited - back off and retry
500Unexpected server error

​
Rate limits

API requests are rate limited per API key. If you hit 429, back off with exponential retry (start at 1s, double each retry, max 60s). Email spencer@orgo.ai if you need higher limits.

​
Next steps

Create Workspace

Organize computers

Create Computer

Provision a VM

Templates

Reproducible computers

Authentication

API key setup

Use Any Model

Claude, GPT, Gemini, and more