agents-sandbox vs nono
Choose agents-sandbox for developers who want each coding agent confined to a per-project microVM on their own Linux or Apple Silicon machine; 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. agents-sandbox uses microsandbox microVM isolation and is open source; nono uses Landlock / Seatbelt isolation and is open source.
Key differences between agents-sandbox and nono
- Isolation: agents-sandbox uses microsandbox microVM; nono uses Landlock / Seatbelt.
- Licence: agents-sandbox is GPL-3.0; nono is Apache-2.0.
- 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 are open source.
- Both list CLI.
agents-sandbox vs nono at a glance
| Attribute | agents-sandbox | nono |
|---|---|---|
| What it is | GPL-3.0 launcher that gives each project and coding agent its own microsandbox microVM on Linux/KVM or Apple Silicon macOS, with secrets kept on the host. | 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 | Dedicated microsandbox microVM per project and agent with a "separate microVM and Linux kernel"; the README does not name the hypervisor | 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 (GPL-3.0) | 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 | VM is built or reused per project; agent state persists in a /home/dev volume; the project directory is mounted read-write at /workspace, or an isolated VM-internal worktree for some agents | 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 | Egress profiles: public (default), private and host extend it, none is allowlist-only "deny-by-default egress, not a complete air gap"; links can open in the host browser for allowlisted schemes | 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 (GPL-3.0) | Free (Apache-2.0); a "nolabs Enterprise" offering is mentioned without pricing |
| Free tier | Free | Free |
| Compliance | Not documented | Not documented |
| Regions | Not documented | Not documented |
| Company headquarters | Hamburg, Germany | Not documented |
| Good fit for | Developers who want each coding agent confined to a per-project microVM on their own Linux or Apple Silicon machine | 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 agents-sandbox
- You want one microVM per project rather than one shared sandbox
- You need secrets kept off the guest while the agent still works
- You want configurable egress without a full air gap
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
- agents-sandbox: Five of the seven agent profiles are marked experimental
- agents-sandbox: Hypervisor and boot behaviour are inherited from microsandbox and not documented here
- 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 agents-sandbox profile and nono profile, or the complete comparison.
More comparisons
Frequently asked questions
Is agents-sandbox or nono better for AI agents?
What is the difference between agents-sandbox and nono?
Which is open source, agents-sandbox or nono?
How do agents-sandbox and nono isolate code?
How does agents-sandbox pricing compare with nono?
Can you self-host agents-sandbox or nono?
Do agents-sandbox 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). agents-sandbox vs nono. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/agents-sandbox-vs-nono/