---
title: Runloop
slug: runloop
url: "https://toolweight.com/options/runloop"
homepage: "https://runloop.ai"
categories: sandbox-providers
last_verified: 2026-01-15
license: CC-BY-4.0
---

# Runloop

> Devboxes, blueprints and eval harnesses aimed at teams training coding agents.

Runloop sells persistent devboxes plus the scaffolding around them: blueprints for reproducible environments, snapshots, and public benchmark harnesses for agent evaluation. The framing is narrower than E2B's, it is built for teams running SWE-bench-style evaluation loops and generating training data rather than general untrusted-code execution. If that is your workload, the surrounding tooling is worth more than the boot time.

## Identity

|  |  |
| --- | --- |
| Name | Runloop |
| Company | Runloop |
| One-liner | Devboxes, blueprints and eval harnesses aimed at teams training coding agents. |
| Site | https://runloop.ai |
| Docs | https://docs.runloop.ai |
| Founded | 2023 |
| Funding | Seed |
| Brand | https://toolweight.com/vendors/Runloop |
| Compared in | 1 |

## Where it is compared

### [Sandbox providers](https://toolweight.com/compare/sandbox-providers)
Ranked **#4 of 20** on default weights.
| Field | Value | Confidence | Verified | Source | Note |
| --- | --- | --- | --- | --- | --- |
| Cold start | 800 ms | Inferred | - | - | Estimate for a devbox created from an existing blueprint or snapshot. |
| Cold start (claimed) | 1 s | Vendor-claimed | 2026-01-15 | https://docs.runloop.ai | Marketed as sub-second devbox boot from a snapshot. Recorded at 1000 ms, the literal ceiling of "sub-second", which is this page's convention for an unquantified claim of that shape, the same reading Modal's identical phrasing gets. It was previously recorded as 500, a favourable mid-reading no other vendor received. |
| Isolation | microvm | Inferred | - | - | - |
| Root in guest | ● | Inferred | - | - | - |
| Egress control | open | Inferred | - | - | No documented per-devbox allowlist. |
| Max runtime | 1440 min | Inferred | - | - | Devboxes are long-lived with a configurable idle shutdown. |
| Persistent FS | ● | Inferred | - | - | Devboxes persist across suspend and resume. |
| Snapshot & fork | ● | Vendor-claimed | 2026-01-15 | https://docs.runloop.ai | Snapshots and blueprints are the core primitive. |
| Custom images | ● | Vendor-claimed | 2026-01-15 | https://docs.runloop.ai | Blueprints build from a Dockerfile or setup commands. |
| GPU | ○ | Inferred | - | - | - |
| Runtimes | python, javascript-typescript, bash, any-oci-image | Inferred | - | - | - |
| Preview URLs | ● | Inferred | - | - | - |
| Browser inside | ◐ | Inferred | - | - | - |
| File up/download | ● | Vendor-claimed | 2026-01-15 | https://docs.runloop.ai | - |
| Sydney region | ○ | Inferred | - | - | US only. |
| Concurrent limit | 100 sandboxes | Inferred | - | - | Plan-dependent; approximate. |
| MCP server | ◐ | Inferred | - | - | - |
| SDKs | python, typescript, rest-api, cli | Inferred | - | - | - |
| Streaming output | ● | Inferred | - | - | - |
| Price / hour | - | Unknown | - | - | Tier- and usage-based pricing that is not published in a form converting cleanly to a 2 vCPU / 4 GB hour. |
| Meter | per-second | Inferred | - | - | - |
| Idle cost | storage-only | Inferred | - | - | Suspended devboxes bill storage. |
| GitHub stars | - | Inferred | - | - | - |
| Funding | seed | Community-reported | - | - | - |
| Shipped | 2024 | Inferred | - | - | - |
| Positioning | Infrastructure and evaluation harnesses for teams building coding agents. | Inferred | - | - | - |

**Verdict.** The only provider here built around evaluation rather than production traffic, blueprints, snapshots and public benchmark scaffolding are the product and the sandbox is the substrate. Overkill if you just need to run some Python; the obvious pick if you measure an agent's pass rate every night.

## Alternatives

- [ascii](https://toolweight.com/options/ascii), Agent orchestration over Telegram, running on box's VM infrastructure.
- [Blaxel](https://toolweight.com/options/blaxel), Agent-first cloud claiming ~25 ms microVM boots from snapshots.
- [box](https://toolweight.com/options/box), Persistent Linux VMs with SSH, per-VM IPv4 and disk-level forking, priced flat.
- [Cloudflare Sandbox](https://toolweight.com/options/cloudflare-sandbox), Container sandboxes driven from a Worker, addressed through Durable Objects.
- [CodeSandbox SDK](https://toolweight.com/options/codesandbox-sdk), Firecracker VMs with memory snapshots, from the online IDE, now owned by Together AI.
- [Daytona](https://toolweight.com/options/daytona), Sub-second container sandboxes for agent workloads, from a team that built a dev-env manager.
- [Self-hosted Firecracker](https://toolweight.com/options/diy-firecracker), The baseline: Firecracker on your own metal, plus every hard part you now own.
- [E2B](https://toolweight.com/options/e2b), Open-source Firecracker sandboxes with Python and TypeScript SDKs for AI agents.
- [exe.dev](https://toolweight.com/options/exe-dev), Persistent VMs you SSH into, with root, apt and systemd, on a flat monthly plan.
- [Fly.io Machines](https://toolweight.com/options/fly-machines), Raw Firecracker microVMs with a REST API, durable volumes and 35+ regions.
- [Freestyle](https://toolweight.com/options/freestyle), Run untrusted JavaScript and full dev servers, with git hosting and domains built in.
- [GitHub Codespaces](https://toolweight.com/options/github-codespaces), Devcontainer-backed cloud VMs built for humans, occasionally repurposed for agents.

## Licence and attribution

Data from toolweight (https://toolweight.com), licensed CC-BY-4.0.

- Licence: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
- Canonical HTML: https://toolweight.com/options/runloop
- Machine-readable: https://toolweight.com/options/runloop.md · https://toolweight.com/api/v1 · https://toolweight.com/mcp
- toolweight takes no affiliate revenue and sells no placements. Corrections: https://toolweight.com/suggest