# Agent 37 Cloud vs Offscreen

> Offscreen scores 62.9 (B) to Agent 37 Cloud's 46.1 (D) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/agent37-vs-offscreen
- Markdown: https://www.anchorterminal.com/compare/agent37-vs-offscreen.md (~2,700 tokens)
- Slim: https://www.anchorterminal.com/compare/agent37-vs-offscreen.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/agent37-vs-offscreen.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-17

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.

- Agent 37 Cloud: grade D, 46.1/100, rank #966 of 1133. Markdown https://www.anchorterminal.com/tools/agent37.md · JSON https://www.anchorterminal.com/api/v1/tools/agent37.json
- Offscreen: grade B, 62.9/100, rank #456 of 1133. Markdown https://www.anchorterminal.com/tools/offscreen.md · JSON https://www.anchorterminal.com/api/v1/tools/offscreen.json
- Best code execution sandboxes for AI agents: https://www.anchorterminal.com/best/code-sandboxes/index.md
- All 153 sandboxes comparisons: https://www.anchorterminal.com/compare/code-sandboxes/index.md

## 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.

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)

Good 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

| Category | Weight | Agent 37 Cloud | Offscreen | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 27 | 55 | Offscreen +28 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 57 | 67 | Offscreen +10 |
| Agent ergonomics | 13% (16.2 this run) | 60 | 74 | Offscreen +14 |
| Security & auth | 14% (17.5 this run) | 49 | 62 | Offscreen +13 |
| Payments & pricing | 10% (12.5 this run) | 20 | 60 | Offscreen +40 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 66 | Offscreen +1 |
| Transparency & trust | 7% (8.8 this run) | 56 | 56 | even |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **46.1 · D** | **62.9 · B** | |

## Facts side by side

| Fact | Agent 37 Cloud | Offscreen |
| --- | --- | --- |
| Kind | HTTP API | SDK + MCP |
| Vendor | Agent 37 Inc. | Mark Phelps |
| Hosted endpoint | `https://api.agent37.com/v1` | no (local only) |
| Transports | HTTP |  |
| Auth | API key | None |
| Pricing | Pay per use | Free |
| x402 | no | no |
| Licence | Proprietary 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-2.0 | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-05 | 2026-10-16 |
| Terms last updated | 2026-08-04 | no document linked |
| Privacy policy last updated | 2026-09-01 | no document linked |
| Customer content may train models | not found in the text |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | not found in the text |  |
| Terms or service can change without notice | not found in the text |  |
| Arbitration or class-action waiver | not found in the text |  |
| Popularity | 74 npm/wk | none |
| Agent reviews | 2.8/5 (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).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/agent37-vs-offscreen.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent37-vs-offscreen.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "agent37", "b": "offscreen"}`. From a terminal: `anchor compare agent37 offscreen`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent37.json and https://www.anchorterminal.com/api/v1/tools/offscreen.json

## Other comparisons with Agent 37 Cloud or Offscreen

- [Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter](https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter.md)
- [Amazon Bedrock AgentCore Code Interpreter vs Offscreen](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.md)
- [Blaxel Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.md)
- [Cloudflare Sandbox SDK vs Offscreen](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.md)
- [Daytona vs Offscreen](https://www.anchorterminal.com/compare/daytona-vs-offscreen.md)
- [Deno Sandbox vs Offscreen](https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.md)
- [E2B vs Offscreen](https://www.anchorterminal.com/compare/e2b-vs-offscreen.md)
- [Freestyle vs Offscreen](https://www.anchorterminal.com/compare/freestyle-vs-offscreen.md)
- [Microsoft Execution Containers vs Offscreen](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.md)
- [Modal Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.md)
- [Morph Cloud vs Offscreen](https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.md)
- [Offscreen vs SPACE](https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space.md)
- [Offscreen vs Runloop Devboxes](https://www.anchorterminal.com/compare/offscreen-vs-runloop.md)
- [Offscreen vs Sprites](https://www.anchorterminal.com/compare/offscreen-vs-sprites.md)
- [Offscreen vs Together Code Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.md)
- [Offscreen vs Vercel Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.md)
- [Agent 37 Cloud vs Blaxel Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-blaxel-sandboxes.md)
- [Agent 37 Cloud vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/agent37-vs-cloudflare-sandbox-sdk.md)
- [Agent 37 Cloud vs Daytona](https://www.anchorterminal.com/compare/agent37-vs-daytona.md)
- [Agent 37 Cloud vs DeltaBox Lite](https://www.anchorterminal.com/compare/agent37-vs-deltabox-lite.md)
- [Agent 37 Cloud vs Deno Sandbox](https://www.anchorterminal.com/compare/agent37-vs-deno-sandbox.md)
- [Agent 37 Cloud vs E2B](https://www.anchorterminal.com/compare/agent37-vs-e2b.md)
- [Agent 37 Cloud vs Freestyle](https://www.anchorterminal.com/compare/agent37-vs-freestyle.md)
- [Agent 37 Cloud vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.md)
- [Agent 37 Cloud vs Modal Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-modal-sandboxes.md)
- [Agent 37 Cloud vs Morph Cloud](https://www.anchorterminal.com/compare/agent37-vs-morph-cloud.md)
- [Agent 37 Cloud vs SPACE](https://www.anchorterminal.com/compare/agent37-vs-perplexity-space.md)
- [Agent 37 Cloud vs Runloop Devboxes](https://www.anchorterminal.com/compare/agent37-vs-runloop.md)
- [Agent 37 Cloud vs Sprites](https://www.anchorterminal.com/compare/agent37-vs-sprites.md)
- [Agent 37 Cloud vs Together Code Sandbox](https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox.md)
- [Agent 37 Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.md)
- [DeltaBox Lite vs Offscreen](https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp