judge0/judge0

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

What it solves

Judge0 provides a secure, scalable way to execute untrusted code online. It eliminates the need for developers to build their own sandboxed environments from scratch when creating applications that require code compilation and execution, such as AI agents, competitive programming sites, or e-learning platforms.

How it works

Judge0 is a modular online code execution system that exposes a simple HTTP JSON API and an official Python SDK. It allows users to submit source code, standard input, and configuration options (like time and memory limits) to be executed in a sandboxed environment. The system supports over 90 languages and can handle both single-file programs and multi-file projects.

Who it’s for

It is designed for developers building AI agents, online IDEs, recruitment platforms for candidate assessment, and educational tools for teaching programming.

Highlights

  • Extensive Language Support: Supports over 90 programming languages and frameworks.
  • Sandboxed Execution: Ensures the safe execution of untrusted code.
  • Flexible Deployment: Available as a self-hostable open-source project or a fully managed SaaS.
  • Developer Friendly: Features a simple JSON API, a Python SDK, and detailed execution results via webhooks.

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
    e2b-dev/E2B

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

  • Project
    e2b-dev/code-interpreter

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

  • 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
    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.