langgenius/dify-sandbox

A lightweight, fast, and secure code execution environment that supports multiple programming languages

What it solves

It provides a secure way to execute untrusted code submitted by users in a multi-tenant environment, preventing malicious or resource-heavy code from compromising the system.

How it works

The project uses a sandboxed environment that restricts system calls and resource access. It is designed to run within Docker containers on Linux systems, leveraging tools like libseccomp to enforce security boundaries.

Who it’s for

Developers building multi-tenant applications (such as AI platforms) that need to allow users to run custom code snippets safely.

Highlights

  • Secure execution of untrusted code.
  • Designed for multi-tenant environments.
  • Resource and system call restriction.
  • Linux and Docker compatible.

Related

  • Project
    opensandbox-group/OpenSandbox

    OpenSandbox is an open‑source sandbox platform for AI agents and other code‑execution workloads. It offers multi‑language SDKs, a CLI, and a server that can run sandboxes on Docker locally or on Kubernetes at scale, with strong isolation (gVisor, Kata, Firecracker), network policies, and a credential vault. Use cases include coding agents, browser/desktop automation, RL training, and secure code‑execution services.

  • Project
    cloudflare/sandbox-sdk

    A SDK for Cloudflare Workers to run untrusted code in secure, isolated containers at the edge, ideal for AI code interpreters and interactive development environments.

  • Project
    e2b-dev/E2B

    An open-source infrastructure that provides secure, isolated cloud sandboxes for running AI-generated code and interacting with virtual desktops.

  • Project
    finbarr/yolobox

    A containerized sandbox for AI coding agents that allows them to run commands without permission prompts while protecting the host home directory from accidental destruction.

  • Project
    e2b-dev/code-interpreter

    An open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes via JavaScript and Python SDKs.