Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Agents/Microsandbox

Microsandbox

appcypher · Agent

Microsandbox gives Node.js and TypeScript applications virtual machine sandboxes for AI agents, tools, tests and untrusted code. The package binds to the microsandbox runtime through a native addon and creates microVM-backed sandboxes with a guest Linux kernel. From an async TypeScript API you run commands, use the guest filesystem, set network policies, DNS filtering and secrets, mount volumes, and take snapshots or fork a live sandbox. Local and cloud backends are supported.

Written by ooruby from the README of microsandbox 0.7.8.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

Code from AI agents and other untrusted sources gets its own virtual machine to run in, controlled from TypeScript.

What you could do with it

  1. 1Create a sandbox from an Alpine or Python image and run a command in it from your TypeScript code.
  2. 2Fork a running sandbox into an independent copy to try an experiment without touching the original.
  3. 3Set a network policy with DNS filtering on a sandbox before running untrusted code in it.

Written from its documentation: what it says it can do, not what our checks found.

MIagentInfrastructure

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Command execution is bounded
inventory
node child_process (native/index.cjs:56)
synchronous shell execution (native/index.cjs:56)
node child_process (bin/microsandbox.cjs:5)
synchronous shell execution (bin/microsandbox.cjs:112)
An inventory of where the code starts another program, not a verdict on this row: whether each one runs a fixed program or whatever it is handed takes a reading by hand.
Licence and provenance
finding
no LICENCE file at the root (.)

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

Lightweight VM sandboxes for Node.js and TypeScript applications that need hardware-level isolation for AI agents, tools, tests, and untrusted code.

Compare with

  • Instarside by side
  • Secretsside by side
  • Domainsside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.7.8, the file with digest sha512-bUll2JNeVhAdvtlemsD5rNkVpLU0KQSXVpuSjXFmkG6Z52Z2ZL9sP8hAdFT8pIGoEPLj+OB9ohgFEPsJgBVkFg==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y -p microsandbox@0.7.8 msb

Pinned to 0.7.8, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
microsandbox
Version read
0.7.8
Resolved
2026-10-10
Open the source(opens in a new tab)

Built from source, attested

npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.

Repository
github.com/superradcompany/microsandbox
Commit
7b7b9dc89e9a
Built by
github.com/actions/runner/github-hosted
Registry publish attestation
signed by npm · 2026-10-10
Checked
2026-10-10

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/microsandbox)](https://ooruby.com/market/microsandbox)

About this listing

Kind
Agent
Category
Infrastructure
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-10
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

Similar agents

All agents
LOagentInfrastructure
2 findingsStatic scanned
Workflow files hold shell commands, native pipeline steps and explicit approval or input gates, with retries, timeouts and error handling per step. A graph command shows a workflow's structure before it runs.

Lobster

clawdbot
Free

Runs agent workflows as deterministic pipelines that pause at approval gates for a person's decision.

3.1M installs/moMIT
AEagentInfrastructure
2 findingsStatic scanned
Compare models, documentation or MCP servers side by side, with token usage recorded for each run. A web playground shows results, and a status command runs only new or changed evals.

Agent Eval

vercel
Free

Tests AI coding agents against your framework in sandboxes and measures their pass rates.

408.7k installs/moMIT
ARagentInfrastructure
Clean scanStatic scanned
Detection checks known agent user agents, the Signature-Agent header and a browser-fingerprint heuristic. Adapters cover Next.js, SvelteKit, Nuxt and sites on Vercel.

Agent Readability

vercel
Free

Spots AI agents visiting your website and answers them with Markdown versions of your pages.

260.6k installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.