The Cloud for AI Agents

What it does

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.

Execute untrusted code securely with isolated sandboxes for AI agents. Spin up Linux micro-VMs in milliseconds. Run Python, JavaScript, Go code in secure, disposable environments. Perfect for AI code execution, autonomous agents, and dynamic workloads.

Execute any code — scripts, tests, jobs, agents — securely in isolated sandboxes. ~100ms startup, filesystem access, no host exposure. Scale to thousands, pay only when running. 1 from hopx_ai import Sandbox 2 3 # Create sandbox 4 sandbox = Sandbox . create ( 5 template = "code-interpreter" 6 ) 7 8 # Execute code 9 result = sandbox . run_code ( 10 "print('Hello, World!')" 11 ) 12 print ( result . stdout ) 13 14 # Cleanup 15 sandbox . kill ( ) SPEED Startup in ~100ms Sandboxes launch from prebuilt snapshots, allowing near-instant cold starts instead of seconds or minutes. Firecracker microVMs provide hardware-level security and kernel isolation — far beyond containers or serverless…from hopx.ai

• 
  I put an AI agent on a $7/month VPS with IRC as its transport layerMar 2026 · georgelarson.me · ▲340

  The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…

• 
  InstaVMMay 2026 · instavm.io · ▲109

  Teaching AI agents to find security vulnerabilities by distilling 4,000 paid HackerOne bug bounty reports — from PDF cracking to API hacking with CLI tools.

• 
  Sub-millisecond VM sandboxes using CoW memory forkingMar 2026 · github.com · ▲311

  I wanted to see how fast an isolated code sandbox could start if I never had to boot a fresh VM. So instead of launching a new microVM per execution, I boot Firecracker once with Python and numpy already loaded, then snapshot the full VM state. Every execution after that creates a new KVM VM backed by a `MAP_PRIVATE` mapping of the snapshot memory, so Linux gives me copy-on-write pages automatically. That means each sandbox starts from an already-running Python process inside a real VM, runs the code, and exits. These are real KVM VMs, not containers: separate guest kernel, separate guest…

• 
  BudaMay 2026 · buda.im · ▲197

  Run a full AI agent team in the cloud — no hardware, no setup. Persistent memory, browser automation, parallel agents. The OpenClaw alternative built for teams. Start free.

• 
  Skill that lets Claude Code/Codex spin up VMs and GPUsFeb 2026 · cloudrouter.dev · ▲138

  I've been working on CloudRouter, a skill + CLI that gives coding agents like Claude Code and Codex the ability to start cloud VMs and GPUs. When an agent writes code, it usually needs to start a dev server, run tests, open a browser to verify its work. Today that all happens on your local machine. This works fine for a single task, but the agent is sharing your computer: your ports, RAM, screen. If you run multiple agents in parallel, it gets a bit chaotic. Docker helps with isolation, but it still uses your machine's resources, and doesn't give the agent a browser, a desktop, or a GPU to…

• 
  Fly – A global load balancer with middleware2017 · fly.io · ▲112

  Sandboxes aren't enough. Give your agent a real computer and get back to building.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 16d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 18d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  Onepin▲384

  AI voiceover with every name, price and date said right

  AI · 30d ago · onepin.ai

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 28d ago · world.pixverse.video

• 
  Guideflow▲1,338

  Create interactive product demos and step-by-step guides in seconds with Guideflow, the leading AI-powered demo automation tool.

  AI · Nov 2025 · guideflow.com

• 
  I built a synth for my daughter▲1,278

  Hardware and software projects by Ali Roberts

  Life & fun · Nov 2025 · bitsnpieces.dev

• 
  Welltory▲1,028

  Measure your wellness. Use data to feel great every day.

  Work · Nov 2025 · welltory.com

• 
  Gemini 3▲1,016

  Bring any idea to life with multimodal capabilities

  AI · Nov 2025 · blog.google

• 
  TrustMRR▲833

  LLM Gateway is a b2b artificial intelligence based in United States, founded in 2025. $259,539/month in verified Stripe revenue. $78,764 MRR. Ahrefs Domain Rating 52/100. growing 55% month-over-month. Track LLM Gateway's verified metrics on TrustMRR.

  Growth · Nov 2025 · trustmrr.com

• 
  Boing▲782

  Life & fun · Nov 2025 · boing.greg.technology