RepoAlerts

anthropics/sandbox-runtime

CLI tool

Can I trust it?

No red flags in our checks.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A command-line tool and TypeScript library that runs arbitrary processes under OS-level filesystem and network restrictions without a container. It uses sandbox-exec on macOS, bubblewrap on Linux and a WFP-based setup on Windows, with proxy-based domain allowlisting for network…

Who it's for

Developers who need to restrict the filesystem and network access of AI agents, MCP servers or shell commands

How to use it

Install

npm install -g @anthropic-ai/sandbox-runtime

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up anthropics/sandbox-runtime in my project. Follow its README: https://github.com/anthropics/sandbox-runtime. Explain each step and check it is safe before running anything.

Star curve

6.6KFrom 5,271 to 6,551 stars between 20 Sept 2026 and 25 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

20,109 GitHub repos watched and ranked every hour. Figures as of 25 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![anthropics/sandbox-runtime on RepoAlerts](https://repoalerts.com/badge/anthropics/sandbox-runtime.svg)](https://repoalerts.com/repo/anthropics/sandbox-runtime?ref=badge)
Share on X

  • NVIDIA/OpenShell

    A runtime that runs autonomous AI agents in isolated sandboxes. Kernel-level controls limit the files, system calls and network connections each agent can use, enforced by a declared policy. Credentia

    AgentAI agentsRust · 19,678 stars · +3,117 this week · 242 days old · HN 499 pts

  • sandbox-quantum/switch

    Self-hosted platform that places AI agents into Slack, Microsoft Teams, Discord, Telegram and Mattermost channels. Agents from different harnesses and models can join shared rooms with role instructio

    AppAI agentsPython · 1,553 stars · +771 this week · 101 days old

  • perplexityai/SPACE

    A sandbox platform that runs code in isolated Firecracker microVMs. Applications use its HTTP API to create sandboxes from templates, run commands in sessions, collect output over a separate data-plan

    AppDev infrastructureRust · 1,945 stars · +496 this week · 24 days old

  • CarterT27/scion

    Rust implementation of a source control system inspired by Anthropic's described architecture: history and expensive operations stay on the server, immutable objects are fetched on demand, and clients

    Rust · 241 stars · +22 this week · 11 days old

  • anthropics/oss-scanner

    Repository for enrolling open-source projects in Anthropic's OSS Scanner, a service that scans critical open-source projects for security vulnerabilities. Enrolment is done by adding a projects/<name>

    Dockerfile · 1,501 stars · +389 this week · 17 days old

  • migasrias2/geckobox

    A command-line tool and SDK, openspaces, that runs coding agents such as Claude Code, Codex, Gemini and OpenCode on local machines, SSH hosts, Docker containers or Cua sandboxes. It runs jobs across s

    CLI toolAI agentsTypeScript · 69 stars · +69 this week · 5 days old