the link is over here, somehow link changed on its own : https://vrn21.com/blog/rl-env

  Location: India
  Remote: Yes
  Willing to relocate: Yes
  Technologies: Rust, Python, Docker, Linux, Terraform, K8s, Sandboxes
  Résumé/CV: vrn21.com/resume
  Email: hello@vrn21.com

I'm KV, upcoming grad, previously interned at 3 startups [1x YC], where most of my work has revolved around Systems [Rust, Python, Docker, Linux]; You could see more info at my resume: [vrn21.com/resume]

And I've built some projects like: sandbox for agents with firecracker and rust [ https://github.com/vrn21/bouvet ] ; a key value store in rust[ https://github.com/hrefto/shorterdb ]; a serverless FaaS platform with WASM and rust [ https://github.com/orbit-serverless/server ]; a postgres extension with pgrx for full text search using tantivy, bm25, rust [ https://github.com/vrn21/pdb ]

so user gets all of the dependencies and apps in userspace to run as well? but each of the command runs in its own more secure shell of some sorts?

Correct, your PATH resolves to your local tools as if it was unprotected bash, but syscalls are filtered/virtualized

from a utilitarian perspective, can we swap this instead of a e2b or some other provider? since this doesnt require n number of micrvovm kernals and rootfs hanging round?

Exactly, that’d be the intention. For compute-heavy or long running jobs you’d still probably want a dedicated VM like on E2B but for quick stuff, bVisor

no on noticing it?

Location: India Remote: Yes Willing to relocate: Yes to anywhere (if provided with VISA) Technologies: Rust, Python, Docker, Terraform, Linux, Infra/Systems/Backend Résumé/CV: vrn21.com/resume Email: hello [at] vrn21 [dot] com

upcoming grad with 3 prior internships [1x yc]: rl envs, linux, filesystems. recently built a sandbox for agents with rust and firecracker as well btw: github.com/vrn21/bouvet

link not found btw

lol thanks for the compliments, generated both the testimonials after giving the mcp server to both opus and gemini and asked their feedback on it.

it is supposed to be directly used by agents, so they are kind of my end users, hence it made sense to get their testimonials :)

my ideal scenario is a cloud web model getting access to a sandbox to run commands and read/write to files. but yeah it could be used as an alternative to bash and read write tools.

I did not get your second question exactly, but yeah microvms can be considered one of the secure ways to run your agent

Basically, just thinking that it’s more ideal to have the tool call the micro VM versus the agent, doing it in the sense of its mandated by the tool call

every syscall on containers run on the kernal with full privelages, so if needed one can break out of the container and get access to the host

> with full privs

No that’s just a misconfigured container then.

Unless there is an exploit on an unpatched kernel bug, a properly configured container shouldn’t allow break out

Luis wrote an excellent blog about it btw: https://www.luiscardoso.dev/blog/sandboxes-for-ai