e2b-dev/code-interpreter

Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

What it solves

It provides a secure way to execute AI-generated code in the cloud. By using isolated sandboxes, it prevents the risks associated with running untrusted code generated by LLMs on a local machine or a main server.

How it works

E2B offers a cloud-based infrastructure that creates secure, isolated sandboxes. Developers can use the provided JavaScript or Python SDKs to start, control, and execute code within these sandboxes remotely.

Who it’s for

Developers building AI agents or applications that need to run code generated by LLMs to perform calculations, data analysis, or other programmatic tasks.

Highlights

  • Secure, isolated cloud sandboxes for AI-generated code.
  • Dedicated SDKs for both JavaScript/TypeScript and Python.
  • Support for custom sandbox templates to include specific packages or runtimes.

Related

  • 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/desktop

    An open-source secure virtual desktop designed for AI agents to perform 'Computer Use' tasks via programmatic GUI control and screen streaming.

  • 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
    opensandbox-group/OpenSandbox

    A general-purpose sandbox platform for AI applications that provides secure, isolated environments for code execution, agent evaluation, and RL training.

  • Project
    tastyeffectco/sandboxd

    An open-source, self-hosted AI app builder engine that uses coding agents to create and host real applications in isolated Docker sandboxes on your own server.