E2B

Machines for AI agents | Hiring! 👉

[E2B @e2b]

3 years to 1B sandboxes.
5 months to 2B.
Wanna guess when we hit 3B?

[E2B @e2b]

Two new integrations landed in the E2B Cookbook this week: @veris_ai and @nottecore.

1. Veris

Use Veris with E2B to simulate any system your agent needs to work with, so it can test its work in a stateful and consistent twin of your production environment.

Agents can claim they did things they didn’t. In the cookbook example, the agent creates a Stripe customer in the simulation, and Veris’s receipt confirms the API call actually happened.

Cookbook: https://t.co/CMMI9xGSpW

2. Notte

Use Notte with E2B to give your agents a real browser that can get past bot checks, while the sandbox stays lightweight.

Real sites check for bots, ask for captchas, and want you signed in. Notte handles all three with stealth, residential proxies, captcha solving, and saved logins, so your sandbox stays focused on the agent's code.

Your agent drives the browser from its E2B sandbox with a few CLI commands, and you can watch every session live or step in when it gets stuck.

In the cookbook example, an agent serves an app from its E2B sandbox, then a Notte browser opens it, adds a to-do, and confirms the result.

Cookbook: https://t.co/qbtTFSobTV

Docs: https://t.co/jK3uERZLVK

[E2B @e2b]

Isolation for security. Zero compromises on speed. ⚡ Hear from our lead platform engineer Jakub how we uses a custom KVM hypervisor to achieve VM-level security while letting you pre-configure complex workloads like Docker and Kubernetes.
https://t.co/eIU8cq5a6H

[E2B @e2b]

Use @pydantic AI and E2B to build coding agents that can pick up where they left off, even after a worker crashes.

Check out the new cookbook example: a Temporal workflow hands the task to a new worker, which resumes the fix in the same E2B sandbox with the files and diagnosis intact.

Cookbook example: https://t.co/WIgUKZJ8XI

Docs: https://t.co/BXfzZxIVwM

[Pydantic @pydantic]

@E2B is now a native sandbox provider in Pydantic AI. One capability in the list, and the agent's shell runs in a microVM instead of on your laptop.

Pause it between runs. Kill the worker and recover in the same sandbox.

https://t.co/AH8CBFvnQb

[E2B @e2b]

Hear from Wei-Lu, our head of enterprise solutions, how BYOC at E2B works, and why you should be on it!
https://t.co/l3xyLoplxT

[E2B @e2b]

Use @CopilotKit's OpenMuse with E2B to give your agent a full desktop computer for last-minute meeting prep.

Have it do the legwork: write Python to pull five years of revenue and net income from SEC EDGAR, save the data as a CSV, and open the charts in a browser.

[CopilotKit🪁 @CopilotKit]

New in OpenMuse: @E2B computers

Your agent gets its own proper desktop.

More below 👇

[E2B @e2b]

Use @OpenAI's computer-use and browser-use helpers with E2B to give your agent a private desktop in the cloud that you can watch live while the model clicks and types.

Use it to help you complete tedious tasks in an application or test user flows: https://t.co/OC9eGMOq6j

[Kevin Whinnery @kevinwhinnery]

Browser and computer use got waaaay easier in the latest @OpenAIDevs Python and Node.js SDKs 🧵

[Vasek Mlejnsky @mlejva]

https://t.co/Nt8vpqjQjK

[E2B @e2b]

@mlejva Do it

[Vasek Mlejnsky @mlejva]

Should we start a Polymarket bet on when we hit 3B?

[Connor O'Brien @connorado]

Orbin' ain't easy.

Courtesy of our friends @e2b

[E2B @e2b]

Build the world agents learn in with @scale_AI AgentEnv and E2B.

Package your environment as an E2B template, and every task run boots a fresh microVM with the same world inside.

Docs: https://t.co/2lp6TlKu6m

[Scale @scale_AI]

Every RL environment we build runs on AgentEnv.

Today we’re open-sourcing it, so more people can build the worlds agents learn in.

[Vasek Mlejnsky @mlejva]

Ever wondered how @co_valenta and I started @e2b?

A quick founding story how we got started by @co_valenta

[Jake Mor @jakemor]

@SebastianSzturo @e2b @mlejva best product ever

[Box @Box]

Box Mount lets developers mount Box as a filesystem directly in any agent sandbox, so agents can work with files and data just like a person would.

In this article, we show how it works with @DigitalOcean, @E2B, @OpenAI, and @vercel. https://t.co/JXeN5xhNb7

[Wayne Sutton @waynesutton]

Wake up agents, there's a new @e2b @convex sandbox component.

A tableless Convex component that provides a V8-compatible E2B client for managing persistent cloud sandboxes inside Convex actions.

Details:
https://t.co/SebFC9lQLv

[Mish Ushakov @mishushakov]

if you have been laid off at Deno or unhappy at Cloudflare - my DMs are waiting for you!

we’re hiring @e2b - as we’ve been hitting record usage every day with growth chart going vertically towards the moon.

my exclusive offer: same/next day interview (no leetcode), an offer within <1 week and 100% remote in EU or UK (for the right candidate).

[Vasek Mlejnsky @mlejva]

You’d think I’d be the last person to say “sandboxes are dead.”

But I’ll be the first to tell you that sandboxes aren’t the whole story for agentic infrastructure.

A lot of the loudest takes here come from people who haven’t built agents that operate at scale. The reality is less convenient: there’s no single tool that fits every task. What matters is knowing what to use, when to use it, and which tradeoffs you’re making.

Everyone feels like they need a strong take. It has to be A or B. In the real world at real scale, it’s usually some combination of both.

The real world is messy. Infrastructure at scale is full of constraints you don’t see in a demo. If you haven’t dealt with them, it’s easy to mistake what worked for your agent for what should work for everyone.

At @e2b, we believe agents will increasingly make these infrastructure decisions themselves. They’ll choose the resources and environments they need for the task, with the underlying infrastructure handling orchestration, isolation, and control.

The only way to survive in AI is to keep building for where things are going. By the time you’ve built for what agents can do today, they’re already capable of more. And the easiest and fastest way to be wrong is to think your solution is the one.

Sandboxes are part of that future. There’s a lot more to build around and alongside them.

That’s what we’re building at @e2b

[Vasek Mlejnsky @mlejva]

We're all wrong. Agents are the only one who are right.

We should let agents pick what infra they want to use.

[E2B @e2b]

Hear @mlejva's take on AI security and why sandboxes are so essential: https://t.co/PAyNkVRo3v