Microsandbox vs Pullrun
Choose Microsandbox for self-hosted microVM isolation on developer machines or your own servers; choose Pullrun for running agent workloads from OCI images as microVMs on your own Linux hosts or Apple Silicon Macs. Microsandbox uses MicroVM (libkrun) isolation and is open source; Pullrun uses Firecracker / Apple VM / runc isolation and is open source.
Key differences between Microsandbox and Pullrun
- Isolation: Microsandbox uses MicroVM (libkrun); Pullrun uses Firecracker / Apple VM / runc.
- SDKs and interfaces: Only Microsandbox lists TypeScript, Python, Rust, Go and Ruby.
What they have in common
- Both are open-source projects you run yourself.
- Both are open source.
- Both can be self-hosted.
- Both support snapshots.
- Both list CLI and MCP server.
Microsandbox vs Pullrun at a glance
| Attribute | Microsandbox | Pullrun |
|---|---|---|
| What it is | Open-source, local-first microVM runtime that gives each sandbox its own Linux kernel, with an optional managed cloud. | Apache-2.0 sandbox runtime that runs the same OCI image as a runc container, a Firecracker microVM on Linux or an Apple Virtualization VM on macOS, with a CLI and MCP server. |
| Type | Open-source project | Open-source project |
| Isolation | Hardware-virtualized microVMs built on libkrun; requires KVM on Linux, Apple Silicon on macOS or Windows Hypervisor Platform | Firecracker microVM with a per-VM kernel on KVM (Linux), Apple Virtualization.framework VM (macOS) or runc container, chosen per workload |
| Open source | Yes (Apache-2.0) | Yes (Apache-2.0) |
| Self-host / BYOC | Yes / Yes | Yes / No |
| SDKs | TypeScript, Python, Rust, Go, Ruby, CLI, MCP server | CLI, MCP server |
| Cold start (vendor claim) | README: average boot under 100 ms (measured on an M1 machine) | README (vendor benchmark on an Apple M3, cold cache): Firecracker cold boot ~500 ms, warm ~200 ms; Apple Virtualization VM boot ~160 ms; container run ~400 ms |
| Max session | Not documented | Not documented |
| Persistence | Volumes, snapshots and forking; detached sandboxes | commit writes a running workload's filesystem to a new image layer; stopped VMs retain state (Firecracker and Apple VM rootfs persist, container rootfs is ephemeral); save/load export tarballs |
| Snapshots / pause | Yes / Not documented | Yes / Not documented |
| GPU | Not documented | Not documented |
| Networking | Network policy with hostname allowlists, port rules and private-network/metadata blocking; secrets substituted via placeholders so keys never enter the VM | Five --net modes: isolated, bridge, slirp, host and none, with IPAM, DNS and iptables integration; per-pod bridge subnets with NAT under the Kubernetes CRI shim |
| Pricing | Free to self-host. Managed cloud (private beta, access by request): free trial with a $10 one-time credit; Builder $20/month and Teams $200/month, each including the same amount of usage credit; usage billed at $0.048 per vCPU-hour and $0.003 per GiB-hour of memory; Enterprise custom | Free to self-host under Apache-2.0. The website describes enterprise "per-node pricing" and a planned hosted API "billed per active sandbox-second", with no figures published |
| Free tier | Self-hosting is free; cloud free trial with a $10 one-time credit (1 sandbox at a time, 1-hour sessions) | Free to self-host |
| Compliance | Not documented | Not documented |
| Regions | Not documented | Not documented |
| Company headquarters | Not documented | Not documented |
| Good fit for | Self-hosted microVM isolation on developer machines or your own servers | Running agent workloads from OCI images as microVMs on your own Linux hosts or Apple Silicon Macs |
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 Microsandbox
- You want microVM isolation on your own laptop or servers
- You want secrets kept out of the VM via placeholder substitution
- You want SDKs beyond Python and TypeScript
Reasons to choose Pullrun
- You want one runtime that boots the same OCI image as a container or a microVM on Linux and on Apple Silicon.
- You need an Apache-2.0 sandbox layer you can self-host with no central daemon.
- You run agents through MCP clients and want a built-in MCP server rather than an SDK.
- You want image-level commits and air-gapped save/load of sandbox state.
Trade-offs to check first
- Microsandbox: Beta software
- Microsandbox: GPU support is not documented
- Pullrun: No hosted service yet; the managed API is only "planned".
- Pullrun: Language SDKs are not documented; interaction is through the CLI, Compose files or MCP.
Both are worth piloting with your own image and region. See the full Microsandbox profile and Pullrun profile, or the complete comparison.
More comparisons
Frequently asked questions
Is Microsandbox or Pullrun better for AI agents?
What is the difference between Microsandbox and Pullrun?
Which is open source, Microsandbox or Pullrun?
How do Microsandbox and Pullrun isolate code?
How does Microsandbox pricing compare with Pullrun?
Can you self-host Microsandbox or Pullrun?
Do Microsandbox and Pullrun 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). Microsandbox vs Pullrun. agentsandboxes.org. Last reviewed November 14, 2026. https://agentsandboxes.org/compare/microsandbox-vs-pullrun/