Ask HN: Secure wrapper for coding agents?

I believe someone recently posted sort of a secure harness/wrapper for running coding agents in a secure sandbox. I can't find the project.

Of course I can make my own wrapper with systemd-nspawn, kata or bspawn, but I believe I saw a decently well-maintained project just a while back. Does anyone have a suggestion or link? It's become extremely hard to find things on GitHub with all the generated projects.

19 points | by rjzzleep 2 days ago

15 comments

  • pixdamix 2 days ago
    If you're on a mac, lookup https://bromure.io/en/agentic-coding

    (Lookup the browser too: https://bromure.io/en/secure-web)

    Everything you see is made by Claude (and Renaud Deraison :-)) and working quite well jugding from the demos)

    See here for more details (in french but English subs available (and more)): https://www.sstic.org/2026/presentation/cloture_2026/

    [-]
    • j-conn 2 days ago
      The “fusion” mode looks really cool. Also loved the logo grid under “for the paranoid” — looks like a customer list but except it’s a wall of shame (“they did not run bromure”). Thanks for sharing!
  • sanju3026 2 days ago
    I believe you're looking for Era. It uses libkrun for local microVM isolation and was built specifically to solve the "LLM hallucinated a destructive bash command" problem without the overhead of a massive VM.

    Another one that handles this gracefully is Yolobox, which uses rootless Podman. Both are actively maintained and cut through the noise of the thousands of generic wrapper repos out there right now.

    [-]
  • theaniketmaurya 12 hours ago
    Celesto has an unified interface for sandboxes based on QEMU, Firecracker and Libkrun.

    https://docs.celesto.ai/smolvm

  • clusterhacks 1 day ago
    This may be too naive, but I created a user on my linux box who doesn't have very many permissions. Then I sudo to that user, use firejail to start pi in a dev project directory, and let it have at it.

    My projects are usually very limited with respect to external dependencies and that is part of prompts or markdown files describing various project goals, plans, and current state.

    My operating theory is that this probably won't get my systems borked. I wasn't patient enough to dig deeper.

  • ca_tech 2 days ago
    If you are running MacOS, I would recommend Agent Safehouse. Well maintained and is built on existing sandbox-exec so you are not locked in and can always build your own rules independent of the CLI tool.

    https://github.com/eugene1g/agent-safehouse/ https://agent-safehouse.dev/

    Originally posted on HN https://news.ycombinator.com/item?id=47301085

    [-]
    • atombender 2 days ago
      Seconding this. I've been running Safehouse for months and love that it can wrap any process (it's just a wrapper around the native macOS sandbox API, after all). The only thing I miss is the ability to limit network access, which isn't supported by the API.
      [-]
      • e1g 10 hours ago
        Safehouse author here - glad you found it helpful. It didn't even occur to me to add --offline mode because my mental model is anchored in agents which often require network access. Until we add this, the easiest option is to create a custom policy and then reference it with Safehouse (I usually setup shell aliases/funciton for this)

          ;; in ~/.config/agent-safehouse/no-network.sb
  (deny network*)

  safehouse --append-profile="$HOME/.config/agent-safehouse/no-network.sb" -- <command>
        [-]
        • atombender 8 hours ago
          Hello! I was definitely not looking to block all network access. I would want to maintain a whitelist of hosts and IPs. I don't know if that's possible?
          [-]
          • e1g 4 hours ago
            Unfortunately, no, MacOS sandboxing does not allow that type of blocking. Only broad categories like "local" vs "remote", but no selective targeting based on domain names or IPs.
  • binsquare 1 day ago
    I build a local, cross platform virtual machine for this purpose: https://github.com/smol-machines/smolvm
  • sakuraiben 1 day ago
    Take a look at https://github.com/Tako-Research/TakoVM!
  • aborsy 2 days ago
    Docker has introduced sandboxes for this purpose.
  • Jeremy1026 1 day ago
    agent-pd was posted as a Show HN fairly recently, might be what you are remembering? https://github.com/varmabudharaju/agent-pd/
  • felixlu2026 1 day ago
    for coding agents, i care less about sandbox branding and more about boring audit logs. what did it read, what did it write, and what was blocked?
  • rohityin 2 days ago
    Have you thought About docker?
  • sosojustdo 19 hours ago
    [flagged]
  • denn-gubsky 1 day ago
    [dead]
  • henryagi 1 day ago
    [flagged]
  • 512colors 1 day ago
    [dead]