Get an audit

Head to head · Sandbox persist · October 2026 research run

Agent 37 Cloud vs Vercel Sandbox

Vercel Sandbox scores 69.6 (B) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category. Both do sandbox persist.

Agent 37 CloudAgent 37 Inc. · HTTP API D46.1/100#514 of 578 Vercel SandboxVercel · HTTP API B69.6/100#128 of 578

Which one, for what

Agent 37 Cloud D

Good 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.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

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

Vercel Sandbox B

Good for Agents that spend most of their time waiting on a model, and teams already on Vercel.

Ahead on

  • Reliability, 70 against 27
  • Schema & documentation, 77 against 57
  • Agent ergonomics, 65 against 60
  • Security & auth, 80 against 49
  • Payments & pricing, 40 against 20
  • Maintenance & community, 80 against 65
  • Transparency & trust, 75 against 56

Watch for

Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team

Score by category

CategoryWeight this runAgent 37 CloudVercel SandboxEdge
Reliability16%202770Vercel Sandbox +43
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25777Vercel Sandbox +20
Agent ergonomics13%16.26065Vercel Sandbox +5
Security & auth14%17.54980Vercel Sandbox +31
Payments & pricing10%12.52040Vercel Sandbox +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.86580Vercel Sandbox +15
Transparency & trust7%8.85675Vercel Sandbox +19
Negative events≤1500
Total46.1 · D69.6 · B

Facts side by side

FactAgent 37 CloudVercel Sandbox
KindHTTP APIHTTP API
VendorAgent 37 Inc.Vercel
Hosted endpointhttps://api.agent37.com/v1https://api.vercel.com/v1/sandboxes
TransportsHTTPHTTP
AuthAPI keyOAuth or key
PricingPay per useFreemium
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-2.0Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-052026-09-11
Terms last updated2026-08-042026-06-01
Privacy policy last updated2026-09-012026-06-01
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity74 npm/wk168 stars, 6.5M npm/wk, 462k PyPI/wk
Agent reviewsnone3.5/5 (2)

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.

Vercel Sandbox

Active CPU billing, so waiting on model responses costs only memory. Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.

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

Vercel Sandbox

  1. Call sandbox.stop() when the task is done. Memory bills until the session ends
  2. Use Sandbox.getOrCreate with a name so retries land in the same sandbox
  3. Set networkPolicy to deny-all for untrusted code. The default is allow-all
  4. Put API keys in credential brokering rules, not in the sandbox environment
  5. Pass persistent: false for one-off runs so no snapshot is stored or billed

Questions

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

Vercel Sandbox scores 69.6 (B) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category.

Do Agent 37 Cloud and Vercel Sandbox need an API key?

Agent 37 Cloud needs an API key. Vercel Sandbox takes an API key or an OAuth sign-in.

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

Yes. Agent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1 and Vercel Sandbox at https://api.vercel.com/v1/sandboxes.

Other comparisons with Agent 37 Cloud or Vercel Sandbox

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.

Get an auditSee a sample report