Orgo for AI agents
Orgo provides cloud computers that agents can create, control, and automate through an API, including screenshots and keyboard input. Developers use it to give agents a sandboxed desktop to operate. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Orgo.
Create a cloud computer
Spin up a new cloud desktop from a template so an agent has an environment to work in.
Take a screenshot of the desktop
Capture the current screen state read-only to confirm what the agent is looking at.
Delete a computer with approval
Tear down a cloud computer only after confirming its session work is complete.
11 Orgo actions, graded by risk.
Every Orgo action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- orgo.get_computerGet Computer
- orgo.get_screenshotGet Screenshot
- orgo.list_templatesList Templates
- orgo.list_workspacesList Workspaces
write
6Create and change things. Allow, or ask the user first.
- orgo.create_computerCreate Computer
- orgo.send_keyboard_inputSend Keyboard Input
- orgo.execute_codeExecute Code
- orgo.control_pointerControl Pointer
- orgo.run_computer_agentRun Computer Agent
- orgo.set_computer_power_stateSet Computer Power State
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- orgo.delete_computerDelete Computer
Orgo in three steps.
- 01Your users connect OrgoThey add their Orgo api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Computer” can wait for the user, and “delete Computer” can be denied outright.
- 03Any agent can actYour agent calls Orgo through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('orgo', { read: 'allow', write: 'ask', // create_computer destructive: 'deny', // delete_computer }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Orgo connects.
Users add their Orgo api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Orgo connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Orgo from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Orgo and Arc0, answered.
Can I use Orgo with Claude, ChatGPT or Cursor?
Yes. Connect Orgo to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Orgo actions you allow.
How do users connect Orgo?
Users add their Orgo api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Orgo actions can my agent take?
11 in total: 4 read, 6 write and 1 destructive, such as “create Computer”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Orgo?
Yes. Actions like “delete Computer” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Orgo too?
Yes. The same Orgo connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Orgo into your agent.
Your users connect Orgo once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan