Cua vs Orgo
Choose Cua for teams that want open-source computer-use sandboxes on their own Macs, servers or cloud accounts, including macOS VMs on Apple silicon; choose Orgo for agents that keep a persistent cloud desktop running around the clock with a browser, terminal and SSH. Cua uses gVisor container or VM isolation and is open source; Orgo uses Isolated VM (hypervisor not named) isolation.
Key differences between Cua and Orgo
- Type: Cua is an open-source project you run yourself; Orgo is a hosted platform.
- Isolation: Cua uses gVisor container or VM; Orgo uses Isolated VM (hypervisor not named).
- Open source: Cua is open source (MIT); Orgo is not.
- Session length: Until destroyed (Cua) versus Unlimited (paid) (Orgo).
- SDKs and interfaces: Only Cua lists Rust. Only Orgo lists REST API.
What they have in common
- Both companies are based in the United States.
- Both support snapshots.
- Both can pause and resume a sandbox.
- Both list Python, TypeScript, CLI and MCP server.
Cua vs Orgo at a glance
| Attribute | Cua | Orgo |
|---|---|---|
| What it is | Open-source computer-use infrastructure: Linux sandboxes as gVisor containers and macOS or Windows sandboxes as VMs, run locally, in your own cloud account or as shared "Spaces". | Always-on cloud Linux and Windows desktops for AI agents, each an isolated VM billed by the second, with a computer-use API, MCP server, SSH, clone and fork. |
| Type | Open-source project | Hosted platform |
| Isolation | Linux images run as gVisor containers by default (runc optional); macOS and Windows images run as VMs via Lume (Apple Virtualization.Framework on Apple silicon) or QEMU | Each Linux and Windows computer is "its own isolated virtual machine with its own disk"; the docs do not name the hypervisor (the API returns a per-computer hypervisor field) |
| Open source | Yes (MIT) | No |
| Self-host / BYOC | Yes / Yes | Not documented / Not documented |
| SDKs | Python, JavaScript/TypeScript, Rust, CLI, MCP server | Python, JavaScript/TypeScript, REST API, CLI, MCP server |
| Cold start (vendor claim) | Not documented | Docs say "a new computer is online in seconds"; no figure given |
| Max session | Persistent sandboxes live until you destroy them; ephemeral sandboxes are deleted when the async with block exits. Spaces plans meter "remote hours" per month (20 Free, 200 Pro) | Paid computers run until you stop or delete them (never auto-suspended); optional end times of 1 to 720 hours, extendable up to 2,160 hours ahead. Free-plan computers stop when credit runs out |
| Persistence | suspend, resume and restart keep state: containers are paused or checkpointed, QEMU VMs are snapshotted, Lume VMs are stopped with their disk kept | Files and installed software persist across stops; a stopped computer cold-boots from its saved disk (memory not kept). Sleep keeps memory. Clone and fork endpoints and reusable templates; free-plan files kept 7 days after credit runs out |
| Snapshots / pause | Yes / Yes | Yes / Yes |
| GPU | Not documented in the sandbox reference | Linux-only --gpu option with 2 GB (2q) or 4 GB (4q) slices; falls back to CPU if no GPU host is free |
| Networking | network="default" gives outbound access like a Docker container; network="none" removes egress but requires a local QEMU VM (unsupported for containers and Lume). Ports exposed via service(), public_url() (TTL 60 s to 24 h) and tunnels | Outbound internet; 1 Gbps network on paid plans; own HTTP CONNECT proxy via the egress API; residential IPs (US-only, Linux-only) with a monthly data allowance on paid plans; public URLs for ports on paid plans; direct SSH for Linux |
| Pricing | SDK, CLI, Driver and Lume are free (MIT). Cua Spaces: Free $0; Pro $18/month or $15/month billed yearly; Teams $30/seat/month or $25/seat/month billed yearly. Cua does not host compute; VMs in your AWS, Google Cloud or Modal account are billed by that provider | Per second, no hourly minimum: Small (0.5 vCPU, 4 GB) $0.023/h running, $0.0014/h stopped; Medium (2 vCPU, 8 GB, 40 GB) $0.055/h running, $0.0027/h stopped; Large (4 vCPU, 16 GB) $0.11/h; XL (6 vCPU, 32 GB) $0.202/h; 2XL (8 vCPU, 64 GB) $0.368/h. Plans: Pay as you go $0; Starter $29/month (1 Medium always on); Growth $99/month (4 Medium); Scale $399/month (16 Medium, Windows included); Enterprise custom. Windows is $15/month per computer on Starter/Growth |
| Free tier | Free to self-host; Spaces Free plan includes 2 computers in use at once and 20 remote hours per month | $5 starting credit for new accounts (about 90 running hours of one Medium computer); $2 for agent-created accounts; one computer at a time on Free |
| Compliance | Not documented | Not documented |
| Regions | Not documented | Not documented |
| Company headquarters | San Francisco, California, United States | San Francisco, California, United States |
| Good fit for | Teams that want open-source computer-use sandboxes on their own Macs, servers or cloud accounts, including macOS VMs on Apple silicon | Agents that keep a persistent cloud desktop running around the clock with a browser, terminal and SSH |
Verified November 14, 2026 from each provider’s documentation. Cold-start figures are vendor claims, not our measurements.
Which should you choose?
Reasons to choose Cua
- You want macOS, Linux and Windows computer-use sandboxes from one open-source SDK
- You need macOS VMs on Apple silicon for agents that must drive native Mac apps
- You run sandboxes on your own hardware or cloud account and want no vendor-hosted compute
- You are building computer-use benchmarks or training data with Cua Bench
Reasons to choose Orgo
- You want an agent to keep a persistent desktop that survives stops and restarts
- You need Windows as well as Linux desktops, and SSH access to the Linux ones
- You want to connect an MCP client such as Claude Code directly to a cloud computer
- You are watching cost: stopped computers cost fractions of a cent per hour
Trade-offs to check first
- Cua: No hosted compute: you provision and pay for machines yourself (Cua Cloud ended October 2026)
- Cua: Licensing differs by component: MIT for the core, FSL-1.1-MIT for Cua Spaces and Driver Bench, AGPL-3.0-or-later for the optional cua-som package
- Orgo: Hypervisor and hosting regions are not documented; the trust centre lists security controls but no named compliance attestation
- Orgo: Residential egress is US-only and Linux-only, with no data included on the Free plan
Both are worth piloting with your own image and region. See the full Cua profile and Orgo profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Cua or Orgo better for AI agents?
What is the difference between Cua and Orgo?
Which is open source, Cua or Orgo?
How do Cua and Orgo isolate code?
hypervisor field).How does Cua pricing compare with Orgo?
Do Cua and Orgo support GPUs?
--gpu option with 2 GB (2q) or 4 GB (4q) slices; falls back to CPU if no GPU host is free.Can you self-host Cua or Orgo?
How long can sessions run on Cua and Orgo?
async with block exits. Spaces plans meter "remote hours" per month (20 Free, 200 Pro). Orgo: Paid computers run until you stop or delete them (never auto-suspended); optional end times of 1 to 720 hours, extendable up to 2,160 hours ahead. Free-plan computers stop when credit runs out.Do Cua and Orgo support snapshots or pause and resume?
Sources
Check before you rely on it. Products change quickly, and this page reflects public documentation as of November 14, 2026. Confirm anything that matters in the provider’s own documentation.
Cite this page
Agent Sandboxes. (2026). Cua vs Orgo. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/cua-vs-orgo/