Amla Sandbox

Infrastructure

sandboxing for ai agents

SHOW HN2026

146points
73comments
#446of 4,366 in 2026
Top 11%of 2026 by points

How HN took it

MixedNo clear lean

6 positive, 8 neutral or asking, 2 mixed, 11 critical, out of 27 comments about the project. Thread score -0.15.

Idea: 4 for, 6 againstPrivacy: 1 for, 2 againstExecution: 0 for, 1 againstDocs: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Capability-based tool constraint model is useful

    From 2 comments
    • I really like the capability enforcement model, it's a great concept. One thing this discussion is missing though is the ecosystem layer. Sandboxing solves execution safety, but…
      rellfy on HN
    • This is really awesome. I want to give my agent access to basic coding tools to do text manipulation, add up numbers, etc, but I want to keep a tight lid on it. This seems like a…
      turnsout on HN
  • Lightweight compared to full VM sandboxes

    From 1 comment
    • agentvm looks very cool! They are taking a different approach - full Linux VM emulated in WASM. It's very impressive technically. We differentiate from agentvm by being…
      souvik1997 on HN

Objections

  • Split license with proprietary WASM binary blocks redistribution

    From 2 comments
    • This project looks very cool - I've been trying to build something similar in a few different ways (https://github.com/simonw/denobox is my most recent attempt) but this is way…
      simonw on HN
    • That's great to hear. The split license is a blocker for me because I build open source tools for other people to use, so I need to be sure that all of my dependencies are things…
      simonw on HN
  • Containers or VMs are safer and already work

    From 2 comments
    • We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra. The pitch is appealing until you realize the tradeoff: you either accept a limited…
      ai-christianson on HN
    • Why not just put the agent in a VM?
      poly2it on HN
  • Limited runtime lacks sockets and common Python packages

    From 1 comment
    • > For agent tool calling, you don't really need NumPy and Pandas. That's true, but you'll likely need sockets, pydantic or SQLAlchemy (all of of them require heavy support on the…
      syrusakbary on HN

Requests

  • Open source the WASM binary

    From 2 comments
    • Thanks Simon! Denobox looks very cool: Deno's permissions model is a natural fit for this. On the licensing: totally fair point. Our intention is to open source the WASM too. The…
      souvik1997 on HN
    • Makes total sense. We'll prioritize getting the WASM source out. This is good signal that it matters. Will ping you when it's up!
      souvik1997 on HN
  • Add SQLite support

    From 1 comment
    • That's really cool. Any chance you could add SQLite? ``` % uv run --with pyeryx python Installed 1 package in 1ms Python 3.14.0 (main, Oct 7 2025, 16:07:00) [Clang 20.1.4 ] on…
      simonw on HN
  • Add curl and more coreutils

    From 2 comments
    • Cool to see more projects in this space! I think Wasm is a great way to do secure sandboxing here. How does Amla handle commands like grep/jq/curl etc which make AI agents so…
      sd2k on HN
    • Great question. We cheated a bit; we didn't compile the GNU coreutils to wasm. Instead, we have Rust reimplementations of common shell commands. It allows us to focus on the use…
      souvik1997 on HN

Questions

  • How does it compare to pyodide or containers

    From 2 comments
  • Is it affiliated with AlmaLinux

    From 1 comment

Alternatives named

  • eryx

    From 1 comment
    • I posted this elsewhere in the thread, and don't want to spam it everywhere (or take away from Amla!), but you might be interested in eryx [1] - the Python bindings [2] get you a…
      sd2k on HN
  • agentvm

    From 2 comments
    • From "Show HN: NPM install a WASM based Linux VM for your agents" re: https://github.com/deepclause/agentvm .. https://news.ycombinator.com/item?id=46686346 : >> How to run…
      westurner on HN
    • agentvm looks very cool! They are taking a different approach - full Linux VM emulated in WASM. It's very impressive technically. We differentiate from agentvm by being…
      souvik1997 on HN
  • Pyodide

    From 2 comments
    • How does this all compare to using pyodide?
      manojlds on HN
    • A lot of it IS using Pyodide, but wrapping it in a way that's convenient to use not-in-a-browser.
      simonw on HN
  • gVisor and Firecracker

    From 1 comment
    • We went down the WASM sandboxing rabbit hole at Gobii when building our agent infra. The pitch is appealing until you realize the tradeoff: you either accept a limited…
      ai-christianson on HN
  • bubblewrap

    From 1 comment
    • Docker and vms are not the only options though... you can use bubblewrap and other equivalents for mac
      messh on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/46824877)