# Runloop

> Micro-VM sandboxes called Devboxes for building, evaluating and running AI coding agents at scale

Source: https://dontaskagain.com/runloop
Website: https://www.runloop.ai/?utm_source=dontaskagain
Pricing: Paid
Categories: [Sandboxes](https://dontaskagain.com/categories/sandboxes.md)
Listed: 2026-10-18
Updated: 2026-10-18

Runloop is infrastructure for building and running AI coding agents on secure sandboxes called Devboxes. Each Devbox is an isolated micro-VM where an agent can write and run code, use tools and work with repositories, with evaluation tooling to refine agents before shipping.

**Key features:**

- Start Devboxes fast on a custom bare-metal hypervisor with arm64 and x86 support.
- Infer build environments automatically from Git repositories in any language.
- Snapshot and branch sandbox disk state, and suspend and resume Devboxes.
- Share tools, files and keys through Agent, Object and Secret stores.
- Connect to MCP servers, SSH, websockets and browser or computer use.
- Run more than 10,000 parallel sandboxes with autoscaling and monitoring.

Runloop offers Python and TypeScript SDKs, with VPC deployment and reinforcement fine-tuning on Enterprise. Compute is billed by usage ($0.108 per CPU-hour), the Basic plan has no platform fee, and Pro is $250/month plus usage, with a free trial that includes $50 in credits.

## More sandboxes

- [Browserbase](https://dontaskagain.com/browserbase.md): Cloud browser platform that lets AI agents log in, navigate, fill forms and extract data from any website at scale
- [Hyperbrowser](https://dontaskagain.com/hyperbrowser.md): Cloud browsers, sandboxes and web data APIs for AI agents, plus managed agents that run browser tasks from a prompt
- [Steel](https://dontaskagain.com/steel.md): Open-source browser API that spins up fleets of cloud browsers for agents to research, scrape, shop and fill forms
- [Anchor Browser](https://dontaskagain.com/anchor-browser.md): Cloud browser infrastructure that runs fleets of managed Chromium agents to automate authenticated web tasks at scale
- [Cua](https://dontaskagain.com/cua.md): Shared virtual desktops where you and computer-use agents like Claude Code or Codex work side by side
- [E2B](https://dontaskagain.com/e2b.md): Cloud sandboxes that give each AI agent an isolated microVM with a shell, filesystem, browser and network
- [Daytona](https://dontaskagain.com/daytona.md): Sandbox infrastructure for running AI-generated code in isolated, stateful environments that start in under 90 ms
- [Modal](https://dontaskagain.com/modal.md): Serverless AI cloud for inference, training, batch jobs and scalable sandboxes that give agents their own computers