E2B logo

E2B

Secure cloud sandboxes that give AI agents isolated Linux machines to run code

Freemiume2b.devUpdated
Visit website

About E2B

E2B is an AI agent cloud that gives each agent session its own isolated Linux machine. Developers create a sandbox through a Python or JavaScript SDK, then run shell commands, execute code, read and write files, and expose ports over HTTPS from inside that environment. Each sandbox runs in a hardware-isolated Firecracker microVM rather than a shared-kernel container, so code written by a model can run without touching the host application.

Best for

  • Running untrusted LLM-generated code, building code interpreters, and giving coding or computer-use agents a disposable Linux environment
  • Coding Agents: Give an agent a disposable Linux machine to write, run and test code safely.
  • Code Interpreters: Execute model-generated Python or JavaScript and return charts, tables and files to the user.
  • Computer-Use and Browser Agents: Host the desktop or browser environment an agent controls.
  • Deep Research Agents: Let research agents fetch data and run analysis in an isolated environment.
  • RL and Evaluation Environments: Fork many parallel copies from a snapshot for reinforcement learning, evals and benchmarks.

Not ideal for

  • Workloads needing GPUs (sandboxes are CPU-only), non-developers, or teams wanting a no-code agent builder

Popular with

  • AI Engineers
  • Agent Developers
  • Backend Developers
  • AI Startups
  • Enterprise Platform Teams

Screenshots

Key features

  • Firecracker microVM Isolation
  • Code and Command Execution
  • Pause, Resume and Fork
  • Network and Secret Controls
  • Persistent Storage
  • Custom Templates
  • Observability
  • Self-Hosting and BYOC

Pros and cons

Pros

  • Hardware-level isolation through Firecracker microVMs rather than shared-kernel containers.
  • Model- and framework-agnostic, with Python and JavaScript SDKs.
  • Pause, resume and fork of sandboxes (up to 100 forks) suits parallel agent runs and evaluations.
  • Free Hobby tier with $100 in credits and no credit card.
  • Self-hosting and BYOC options for enterprises, plus SOC 2 Type II compliance.

Cons

  • Pro costs $150/month before usage, a large step up from the one-time Hobby credit.
  • No GPU support; sandboxes are limited to 8 vCPUs and 8 GiB RAM.
  • Hobby sessions are capped at 1 hour of continuous runtime.
  • Enterprise carries a stated $3,000/month minimum.

Pricing

Plans as listed by the vendor on . Check their site for current prices.

See e2b.dev

Hobby

$0

Free start with one-time usage credit, no credit card

  • $100 one-time usage credit
  • 20 concurrent sandboxes
  • up to 1 hour sessions
  • 10 GiB storage

Pro

Most popular

$150/month

Production usage with longer sessions and custom sizing

  • 100 concurrent sandboxes
  • up to 24 hour sessions
  • 20 GiB storage
  • custom CPU and RAM
  • plus usage

Enterprise

Custom/custom

Large deployments with negotiated terms

  • Custom concurrency and limits
  • negotiated credits
  • BYOC option
  • $3,000/month minimum

Our ratings

Scored out of 10 by the Finder Atlas editorial team.

8.2overall
Ease of Use
8.3
Feature Depth
8.6
Value for Money
7.6
Performance & Speed
8.4
Documentation & Support
8.2

Platforms and integrations

Available on

  • Web
  • API
  • CLI

Works with

  • Anthropic
  • OpenAI
  • LangChain
  • OpenAI Agents SDK
  • AWS
  • GCP
  • Azure

E2B alternatives

Other tools people compare with E2B.

All 8 alternatives
  • CodeRabbit logo
    CodeRabbitFree trial

    AI code review that checks, explains and prioritizes every pull request before merge

    Compare
  • Greptile logo
    GreptileFreemium

    AI code review that checks every pull request against your full codebase context

    Compare
  • fal logo
    falPaid

    Run image, video, audio and 3D generative models through one fast developer API

    Compare
  • OpenRouter logo
    OpenRouterRated4.5Freemium

    One API and one bill for hundreds of AI models across many providers

    Compare
  • Warp logo
    WarpFreemium

    Open-source terminal with built-in AI agents and cloud infrastructure for coding workflows

    Compare

Release history

  1. Reported $21 million Series A led by Insight Partners (per Preqin)

    Reported $21 million Series A led by Insight Partners (per Preqin).

Reviews

No reviews yet

Used E2B? Help others decide by sharing your experience.

Frequently asked questions

What is an E2B sandbox?

A sandbox is an isolated Linux machine, run as a Firecracker microVM, that an AI agent session can use to execute commands and code, manage files and expose ports.

Which languages and SDKs are supported?

E2B provides a Python SDK (Python 3.10+) and a JavaScript SDK (Node.js 20.18.1+ or 22+). Inside a sandbox you can run Python, JavaScript and any command available on the Linux machine.

Does E2B offer a free plan?

Yes. Hobby is free to start with no credit card and includes a one-time $100 usage credit, 20 concurrent sandboxes and sessions of up to 1 hour.

Are GPUs available?

No. The pricing page lists CPU and RAM only; sandboxes can have 1 to 8 vCPUs and 1 to 8 GiB of RAM.

Can I self-host E2B?

Enterprises can run the data plane in their own AWS, GCP or Azure account. E2B also publishes E2B Embed, an Apache-2.0 single-node package for Linux x86-64 machines with KVM.

Is E2B tied to a specific AI model?

No. E2B provides the machine and the user brings their own model, prompts and orchestration, including Anthropic, OpenAI and open-weight models.

More Developer Tools tools

View all