Codex CLI sandboxing vs nono
Choose Codex CLI sandboxing for confining Codex CLI command execution on macOS, Linux or Windows without containers; choose nono for running Claude Code, Codex and other coding agents on your own machine with kernel-enforced file and network allow-lists and brokered credentials. Codex CLI sandboxing uses Seatbelt / bubblewrap / Windows isolation and is open source; nono uses Landlock / Seatbelt isolation and is open source.
Key differences between Codex CLI sandboxing and nono
- Isolation: Codex CLI sandboxing uses Seatbelt / bubblewrap / Windows; nono uses Landlock / Seatbelt.
- SDKs and interfaces: Only nono lists Rust, Python, JavaScript/TypeScript and Go.
What they have in common
- Both are tools that run on your own machine.
- Both use OS-level sandboxing.
- Both are open source.
- Both list CLI.
Codex CLI sandboxing vs nono at a glance
| Attribute | Codex CLI sandboxing | nono |
|---|---|---|
| What it is | Codex CLI's built-in sandbox: Seatbelt on macOS, bubblewrap on Linux/WSL2 and a native Windows sandbox, with read-only, workspace-write and full-access modes. | Kernel-enforced OS-native sandbox for coding agents that runs each tool call in its own ephemeral sandbox, brokers credentials and keeps a tamper-evident audit chain. |
| Type | Local / OS-level | Local / OS-level |
| Isolation | macOS: built-in Seatbelt framework; Linux and WSL2: bubblewrap (bwrap) from PATH or a bundled helper that needs unprivileged user namespaces; Windows: native sandbox with mxc process isolation (recommended), elevated lower-privilege sandbox users, or an unelevated restricted token | OS-level sandboxing via Landlock on Linux and Seatbelt on macOS, with opt-in user, network, IPC and UTS namespaces on Linux; a supervisor launches each tool call in a short-lived sandbox with only the capabilities it needs |
| Open source | Yes (Apache-2.0) | Yes (Apache-2.0) |
| Self-host / BYOC | No / No | No / No |
| SDKs | CLI | CLI, Rust, Python, JavaScript/TypeScript, Go |
| Cold start (vendor claim) | Not documented | Website: "zero setup and zero latency" (claim); no figures given |
| Max session | Not documented | Not documented |
| Persistence | Works directly on the host workspace; workspace-write confines edits to the workspace, read-only requires approval to edit or run commands | Runs on the host filesystem within allow-listed paths; rollback restores tracked files from verified snapshots |
| Snapshots / pause | Not documented / Not documented | Yes / Not documented |
| GPU | Not documented | Not documented |
| Networking | The sandbox controls "whether commands can use the network"; approval policy can "Always ask to edit external files and use the internet"; in ChatGPT Work, commands reach only required hostnames from a managed allowlist unless "Allow public internet access" is turned on | Domain filtering and API rules by HTTP method and path through a proxy that injects credentials at the boundary; the real credential "never enters the child"; block_network() in the SDKs |
| Pricing | Free, open-source CLI; use requires a ChatGPT plan or API key | Free (Apache-2.0); a "nolabs Enterprise" offering is mentioned without pricing |
| Free tier | Not documented | Free |
| Compliance | Not documented | Not documented |
| Regions | Not documented | Not documented |
| Company headquarters | San Francisco, California, United States | Not documented |
| Good fit for | Confining Codex CLI command execution on macOS, Linux or Windows without containers | Running Claude Code, Codex and other coding agents on your own machine with kernel-enforced file and network allow-lists and brokered credentials |
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 Codex CLI sandboxing
- You use Codex CLI and want default confinement with no containers
- You need a native Windows sandbox, not just WSL2
- You want network use gated by approvals or an allowlist
Reasons to choose nono
- You want kernel-enforced allow-lists around an existing coding agent without containers or VMs
- You need credentials kept out of the agent process and injected per request
- You want a tamper-evident audit trail and file rollback for agent sessions
- You are on macOS or Linux and want zero-setup enforcement
Trade-offs to check first
- Codex CLI sandboxing: OS-level sandboxing on the host rather than a VM; danger-full-access removes the filesystem and network boundaries
- Codex CLI sandboxing: Linux requires bubblewrap and user-namespace support; Windows mxc needs specific recent builds
- nono: OS-level sandboxing (Landlock, Seatbelt) on the host kernel rather than a VM
- nono: Pre-1.0 with APIs still stabilising
Both are worth piloting with your own image and region. See the full Codex CLI sandboxing profile and nono profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Codex CLI sandboxing or nono better for AI agents?
What is the difference between Codex CLI sandboxing and nono?
Which is open source, Codex CLI sandboxing or nono?
How do Codex CLI sandboxing and nono isolate code?
How does Codex CLI sandboxing pricing compare with nono?
Can you self-host Codex CLI sandboxing or nono?
Do Codex CLI sandboxing and nono 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). Codex CLI sandboxing vs nono. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/codex-cli-sandbox-vs-nono/