AgentToolDrop

3 sandboxes

Isolated environments where agents can run generated code without touching your machine.

2 of 3 are open source, 2 pushed to GitHub in the last 30 days, 1 has no public repo. Numbers on the left are ranks in the full ledger of all tools. Filter this category in the directory.

  1. Rank 23

    E2B

    Sandbox

    Runs AI-generated code in isolated cloud sandboxes you start and control from Python or JavaScript

    • score 63
    • 14.4k stars
    • pushed
    • @e2b/code-interpreter-python@2.11.0 on
    • Apache-2.0

    Install the JavaScript SDK

    npm i e2b
    Use it when, skip it if, stats for E2B

    Why you'd want it

    E2B gives agent tasks their own isolated sandbox in the cloud, started with Sandbox.create() from the JavaScript or Python SDK, where code can run shell commands and programs. The Code Interpreter SDK adds runCode/run_code for executing snippets, and the Desktop SDK adds mouse, keyboard, screenshot and desktop streaming APIs for computer-use agents. The runtime is open source and can be self-hosted with Terraform on AWS, Google Cloud, Azure or a general Linux machine.

    Best for

    • Running untrusted model-generated code
    • Code interpreter and data analysis features
    • Computer-use agents that need a desktop

    Use it when

    Your agent writes code or shell commands that must run somewhere isolated from your own machines and data.

    Skip it if

    You do not want to sign up for an E2B API key or operate the Terraform-based self-hosted runtime.

    Stats

    Stars
    14,355
    Last push
    Release
    @e2b/code-interpreter-python@2.11.0,
    License
    Apache-2.0
    Pricing
    Open source
    Drop score
    63 of 100

    Full stat block for E2B

  2. Rank 57

    Daytona

    Sandbox

    Runs AI-generated code in hosted sandboxes with their own kernel, filesystem and network stack

    • score 43
    • No public repo
    • Hosted service

    Install the Python SDK

    pip install daytona
    Use it when, skip it if, stats for Daytona

    Why you'd want it

    Daytona sandboxes are full computers with a dedicated kernel, filesystem, network stack and allocated vCPU, RAM and disk, which agents create and control through SDKs for TypeScript, Python, Ruby, Go and Java, an API and a CLI. Operations cover sandbox lifecycle, file system, process and code execution and git, and stateful snapshots let agent work persist across sessions. The docs also cover computer use, an MCP server, and SSH, VNC and web terminal access, and the pricing page lists GPU options.

    Best for

    • Agents that need sandboxes that persist across sessions
    • SDK users in Ruby, Go or Java as well as Python and TypeScript
    • Sandboxed workloads that need GPUs

    Use it when

    You want hosted, isolated machines for agent code execution and prefer usage-based billing to running the infrastructure yourself.

    Skip it if

    You need to self-host or audit the platform source: core development moved to a private codebase and the public repo is archived. Billing is pay as you go per vCPU, memory and storage hour.

    Stats

    GitHub
    no public repo
    License
    Hosted service
    Pricing
    Paid
    Drop score
    43 of 100

    Full stat block for Daytona

  3. Rank 71

    Container Use

    Sandbox

    Gives each coding agent its own container and git branch so several can work in parallel without conflicts

    • score 18
    • 4.1k stars
    • pushed
    • v0.4.2 on
    • Apache-2.0

    Install with Homebrew and add to Claude Code

    brew install dagger/tap/container-use
cd /path/to/repository
claude mcp add container-use -- container-use stdio
    Use it when, skip it if, stats for Container Use

    Why you'd want it

    Container Use is an MCP server, run from a CLI and built on Dagger, that gives each agent a fresh container on its own git branch, so you can run several agents at once and discard failed attempts. You can see the full command history and logs of what an agent did, drop into its terminal to take over, and review its work with a normal git checkout of its branch. Setup is the same for any MCP-compatible agent, adding container-use stdio as an MCP server, and the docs have guides for Claude Code, Cursor, Windsurf, Zed, Codex, Gemini CLI and others.

    Best for

    • Running several coding agents in parallel
    • Keeping agent changes off your working tree until reviewed
    • Claude Code, Cursor and other MCP agents

    Use it when

    You want coding agents to work in isolated, reviewable environments on your own machine instead of directly in your checkout.

    Skip it if

    You do not have Docker and Git installed, which the quickstart requires. The project describes itself as experimental and in early development.

    Stats

    Stars
    4,069
    Last push
    Release
    v0.4.2,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Cursor, Windsurf, Zed, Codex, Gemini CLI, VS Code, Any MCP client
    Drop score
    18 of 100

    Full stat block for Container Use

Other categories