The Cloud for AI Agents

Spin up secure sandboxes in ~100 ms

184 followers

Spin up secure sandboxes in ~100 ms

184 followers

Hopx lets you spin up fully isolated Linux micro-VMs in ~100 ms — perfect for running AI agents, notebooks, or untrusted code safely at scale. Each sandbox runs in its own Firecracker microVM, with full state persistence, SDKs for Python, JS, Go, and more. No cold-start lag. No runtime limits. Just raw performance and security.

Free

Launch tags:Software Engineering•Artificial Intelligence•SDK

Launch Team / Built With

Wispr Flow: Dictation That Works Everywhere — Stop typing. Start speaking. 4x faster.

Stop typing. Start speaking. 4x faster.

Promoted

It Works On My Computer Podcast

Maker

📌

Hey everyone 👋 I’m Alin, founder of Hopx (and Bunnyshell). Over the past year, we’ve rebuilt the idea of “ephemeral environments” from the ground up — this time for AI agents and developers who need instant, isolated sandboxes. Hopx sandboxes launch in ~100 ms, run for hours or days, and give you full Linux access — safely. We’re giving $200 in free compute credits to early users — your feedback will directly shape how Hopx evolves. 👉 Try it out, run an agent, or launch your first sandbox: hopx.ai Excited to hear what you’ll build ⚡

Report

3mo ago

@alin_dobra Great job!

Report

3mo ago

It Works On My Computer Podcast

Maker

@cristianducu thanks Cristi!

Report

3mo ago

The Cloud for AI Agents

Maker

🚀 Big milestone for our team.

Over the past months, we’ve been focused on one goal — making it effortless and safe to run untrusted code at scale. Traditional containers couldn’t deliver the speed or isolation modern AI systems need, so we built something new.

Hopx Sandboxes launch in around 150 ms, run as full microVMs, and provide true isolation — the security of VMs with the speed and simplicity developers expect.

They’re built for developers and AI workloads alike — from code interpreters and agent frameworks to automated testing and data pipelines. With SDKs in six languages, clean APIs, and detailed documentation, you can go from install to execution in minutes.

No complex setup. No DevOps overhead, just a pip/npm install and you are good to go!

Couldn’t be prouder of what the team has built — and excited to see how developers use it next.

Report

3mo ago

It Works On My Computer Podcast

Maker

@a4d 🚀

Report

3mo ago

Swytchcode

This is awesome! How many programming languages do you support today?
Congrats on the launch!

Report

3mo ago

It Works On My Computer Podcast

Maker

@chilarai Thanks so much! 🙌
Right now, we have official SDKs for JavaScript and Python, and we’re beta testing .NET, Java, Go, and PHP — coming soon.

The default code-interpreter template already includes Python, Go, Bun, and Node.js as runtimes.
You can also create custom templates to run anything else — from Rust to C++ — fully isolated inside a Hopx sandbox.

Report

3mo ago

Swytchcode

@alin_dobra We have a use case. Can you connect me over linkedin? Would love to understand your product

Report

3mo ago

It Works On My Computer Podcast

Maker

@chilarai added you. looking forward to chat!

Report

3mo ago

It Works On My Computer Podcast

Maker

@chilarai added on linkedin. looking forward to chat!

Report

3mo ago

The Cloud for AI Agents

Maker

Hey everyone 👋

I’m really excited to share what our team has been building.

For the last few months, we’ve been heads-down rethinking how developers spin up fast, safe execution environments for AI workflows. Most existing solutions were either too slow, too heavy, or too fragile for real agent-driven systems — so we built a platform that gives you instant, fully isolated compute on demand.

Environments boot in ~100ms and come with full Linux access. No infra wrangling, no DevOps detours — just install the SDK and start running code.

👉 Give it a try, launch your first environment, and let us know what you think.

Can’t wait to see what you build ⚡

Report

3mo ago

It Works On My Computer Podcast

Maker

@chiticmihai 🚀🚀🚀

Report

3mo ago

Congrats on the launch! A couple of things I was curious about:
Is the main value prop the speed of spinning up new environments?
And how would this fit into an existing cloud setup - does it run alongside AWS/GCP, or replace part of it?

Report

3mo ago

It Works On My Computer Podcast

Maker

The main prop is the combination between the speed, vm-level isolation and easy of use.

Here a quick example how to spin-up a sandbox in ms, run your code, kill the sandbox. Very useful when developing AI Agents, to run untrusted code in isolation. But you can really spin up anything, from self-hosted LLMs, to ETL jobs, mcp servers, full APIs, apps etc.

import { Sandbox } from '@hopx-ai/sdk';

const sandbox = await Sandbox.create({
  template: 'code-interpreter',
  apiKey: process.env.HOPX_API_KEY
});

// Execute Python code
const result = await sandbox.runCode(`
import sys
print(f"Python {sys.version}")
print("Hello from HopX!")
`);

console.log(result.stdout);
// Output: Python 3.11...
//         Hello from HopX!

await sandbox.kill();

Report

3mo ago

The Cloud for AI Agents

Maker


from bunnyshell import Sandbox

# Create sandbox with code-interpreter template
sandbox = Sandbox.create(template="code-interpreter")

print(f"✅ Sandbox created: {sandbox.sandbox_id}")

# Get sandbox info
info = sandbox.get_info()
print(f"Status: {info.status}")
print(f"Info: {info}")


result = sandbox.commands.run('ls / && rm -rf / ')
print(result.stdout)
print(f"Exit code: {result.exit_code}")


print(f"Output: {result.stdout}")

# Cleanup
sandbox.kill()

Always wanted to run `rm -rf /`, now I can :)

Report

3mo ago

It Works On My Computer Podcast

Maker

@alexo_bunnyshell 🚀🚀🚀

Report

3mo ago

Blindspot

Big fan of the makers, know then since they started Bunnyshell.

Report

3mo ago

It Works On My Computer Podcast

Maker

@matei_psatta Big fan of what you’re building as well. And I still remember to thank you for that viral DigitalOcean campaign!

Report

3mo ago

1 2

🚀 Big milestone for our team.

Hopx Sandboxes launch in around 150 ms, run as full microVMs, and provide true isolation — the security of VMs with the speed and simplicity developers expect.

No complex setup. No DevOps overhead, just a pip/npm install and you are good to go!

Couldn’t be prouder of what the team has built — and excited to see how developers use it next.

import { Sandbox } from '@hopx-ai/sdk'; const sandbox = await Sandbox.create({ template: 'code-interpreter', apiKey: process.env.HOPX_API_KEY }); // Execute Python code const result = await sandbox.runCode(` import sys print(f"Python {sys.version}") print("Hello from HopX!") `); console.log(result.stdout); // Output: Python 3.11... // Hello from HopX! await sandbox.kill();

from bunnyshell import Sandbox # Create sandbox with code-interpreter template sandbox = Sandbox.create(template="code-interpreter") print(f"✅ Sandbox created: {sandbox.sandbox_id}") # Get sandbox info info = sandbox.get_info() print(f"Status: {info.status}") print(f"Info: {info}") result = sandbox.commands.run('ls / && rm -rf / ') print(result.stdout) print(f"Exit code: {result.exit_code}") print(f"Output: {result.stdout}") # Cleanup sandbox.kill()