Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Sandbox: Run untrusted AI code safely, fast

github.com

Post reply on HN
Print view View original

1–10 of 32 posts

Re: Sandbox: Run untrusted AI code safely, fast

#2

Post by mkagenius »

If you don't want to depend on cloud, have a mac, then you can run a sandbox locally on you mac. I have built an apple container (not docker) based sandbox to run arbitrary code - coderunner[1]. It is quite fast. And apple container provides one vm per container unlike docker on macos which shares the vm across all containers. Coderunner is good for processing sensitive docs locally in a secure sandbox.

1. coderunner - https://github.com/instavm/coderunner

Re: Sandbox: Run untrusted AI code safely, fast

#6

Post by zingar »

mkagenius wrote: post #2

If you don't want to depend on cloud, have a mac, then you can run a sandbox locally on you mac. I have built an apple container (not docker) based sandbox to run arbitrary code - coderunner[1]. It is quite fast. And apple container provides one vm per container unlike docker on macos which shares the vm across all containers. Coderunner is good for processing sensitive docs locally in a secure sandbox. 1. coderunner…

In the coderunner read me it talks about reading files without sending them to the cloud. Does that mean there is something agentic going on? That’s more than I expect from something called a sandbox.

Also if it is agentic, why is it less cloud based than eg Claude code? Are there LLMs running locally?

Re: Sandbox: Run untrusted AI code safely, fast

#9

Post by mijoharas »

This seemed quite interesting but it seems to run them on GCP rather than locally.

I had a brief glance at running firecracker VM's locally as that sounded interesting, but it doesn't seem too easy.

Does anyone know of any good solution that improve the UX of that (running some firecracker VM's locally)?

Re: Sandbox: Run untrusted AI code safely, fast

#10

Post by l9o »

mijoharas wrote: post #9

This seemed quite interesting but it seems to run them on GCP rather than locally. I had a brief glance at running firecracker VM's locally as that sounded interesting, but it doesn't seem too easy. Does anyone know of any good solution that improve the UX of that (running some firecracker VM's locally)?

Out of curiosity, what would be an ideal UX for you? I'm working on a Rust library for this exact problem (CLI and language bindings should be easy to add).

It uses KVM directly on Linux and Virtualization.framework on macOS, with a builder API for VM configuration. For AI sandboxing specifically, it has a higher-level "sandbox" mode with a guest agent for structured command execution and file I/O over vsock. You get proper exit codes and stdout/stderr without console scraping.

Also supports pre-warmed VM pools for fast startup and shared directories via virtio-fs.

I'm planning to support OCI images, but not sure if that's important to people. I typically just build my own root disks with Nix.

Post reply on HN