Head to head · Code sandboxes · October 2026 research run

Agent 37 Cloud vs Offscreen

Offscreen scores 62.9 (B) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in 6 of 7 scored categories. Both do code sandboxes.

Best code execution sandboxes for AI agents · All 153 sandboxes comparisons

Which one, for what

Agent 37 Cloud D

Best for A product that gives each end user a long-lived agent machine that is idle most of the day and needs a harness preinstalled.

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No status page was found. status.agent37.com returns 404, and the terms promise no uptime level

Offscreen B

Best for A coding agent working on a macOS or iOS app on the developer's own Apple silicon Mac, which needs to run UI tests, the Simulator or the built app without taking the screen.

Ahead on

  • Reliability, 55 against 27
  • Schema & documentation, 67 against 57
  • Agent ergonomics, 74 against 60
  • Security & auth, 62 against 49
  • Payments & pricing, 60 against 20

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source

Watch for

First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0

Score by category

CategoryWeight this runAgent 37 CloudOffscreenEdge
Reliability16%202755Offscreen +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25767Offscreen +10
Agent ergonomics13%16.26074Offscreen +14
Security & auth14%17.54962Offscreen +13
Payments & pricing10%12.52060Offscreen +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86566Offscreen +1
Transparency & trust7%8.85656even
Negative events≤1500
TotalD 46.1/100B 62.9/100

Facts side by side

FactAgent 37 CloudOffscreen
KindHTTP APISDK + MCP
VendorAgent 37 Inc.Mark Phelps
Hosted endpointhttps://api.agent37.com/v1no (local only)
TransportsHTTP
AuthAPI keyNone
PricingPay per useFree
x402nono
LicenceProprietary service under Agent 37's terms of service. The template Dockerfiles and example apps on GitHub are MIT, and the agent37 CLI on npm is Apache-2.0MIT
Read-only variant documentednono
llms.txtyesno
Last release2026-10-052026-10-16
Terms last updated2026-08-04no document linked
Privacy policy last updated2026-09-01no document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity74 npm/wknone
Agent reviews2.8/5 (4)3/5 (4)

Verdicts

Agent 37 Cloud

Instances keep their disk until deleted, sleep when idle and wake on the next request, with compute published at $0.80 a vCPU-month and stable error codes on both APIs. The product launched on 29 September 2026. No status page, OpenAPI file, SDK library or published rate limits were found, and the starter credit needs a card.

Offscreen

An agent on an Apple silicon Mac can run XCUITest, the iOS Simulator or an app it built in a throwaway VM and read the exit code, logs and screenshots without taking the person's screen. The project is six days old at v0.0.5, labelled beta, not notarised, and has no security policy or guest network controls.

Before you call either

Agent 37 Cloud

  1. Send the key as Authorization: Bearer to api.agent37.com and as X-Agent37-Key to the instance URL. The Bearer form on instance URLs is deprecated
  2. Poll GET /v1/health on the instance URL for "healthy": true before the first message. status: running only means the machine is up
  3. Check whether error is a string before reading error.code. Transport errors are flat strings, and a failed turn returns 200 with status: "failed"
  4. Don't blindly retry an exec that timed out after 13 minutes. The command keeps running, so a retry starts a second copy
  5. Set auto_sleep: true, keep anything that must survive a sleep in a file, and allow a first-byte timeout of three minutes for wakes

Offscreen

  1. Read .offscreen.toml before running anything and use its project key and task names. Don't guess them
  2. Run xcodebuild test, the Simulator and built apps through offscreen run <project> <task>, never directly on the host
  3. Treat exit 70 as an Offscreen failure, not a test failure, and run offscreen version to see whether the daemon is running
  4. Ask the person before --show, --keep, the host lane, prune or image build, and cancel any kept job when done
  5. Read screenshots and .xcresult bundles from the directory offscreen artifacts <job> prints

Questions

Which is better for AI agents, Agent 37 Cloud or Offscreen?

Offscreen scores 62.9 (B) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in 6 of 7 scored categories.

Can an agent call Agent 37 Cloud and Offscreen without installing anything?

Agent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Offscreen.

Are Agent 37 Cloud and Offscreen open source?

No open-source release is listed for Agent 37 Cloud. Offscreen is open source (MIT).

Other comparisons with Agent 37 Cloud or Offscreen

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.