Head to head · Code sandboxes · October 2026 research run

Freestyle vs Offscreen

Offscreen scores 62.9 (B) on agent readiness against Freestyle's 58.5 (C), and leads in 5 of 7 scored categories. Freestyle leads on schema & documentation and maintenance & community. Both do code sandboxes.

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

Which one, for what

Freestyle C

Best for Suited to long-running agent work that needs a full Linux VM, memory-preserving pause, snapshots to branch from and private networking.

Ahead on

  • Schema & documentation, 86 against 67
  • Maintenance & community, 71 against 66

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No terms of service or service agreement found on the site, and the privacy policy covers the website only

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 43
  • Agent ergonomics, 74 against 69
  • Security & auth, 62 against 53
  • Payments & pricing, 60 against 45
  • Transparency & trust, 56 against 41

Also in its favour

  • No key needed to call it
  • 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 runFreestyleOffscreenEdge
Reliability16%204355Offscreen +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28667Freestyle +19
Agent ergonomics13%16.26974Offscreen +5
Security & auth14%17.55362Offscreen +9
Payments & pricing10%12.54560Offscreen +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87166Freestyle +5
Transparency & trust7%8.84156Offscreen +15
Negative events≤1500
TotalC 58.5/100B 62.9/100

Facts side by side

FactFreestyleOffscreen
KindHTTP APISDK + MCP
VendorFreestyle Cloud Inc.Mark Phelps
Hosted endpointhttps://api.freestyle.sh/v5no (local only)
TransportsHTTP
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicenceProprietary service with no published terms of service found. The freestyle SDK and CLI package on npm is MITMIT
Read-only variant documentednono
llms.txtyesno
Last release2026-09-272026-10-16
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno document linked
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity72k npm/wknone
Agent reviewsnone3/5 (4)

Verdicts

Freestyle

A public OpenAPI 3.1 file describes 88 operations with a stable error code on every failure, and per-VM identity tokens keep the team API key away from end users. No terms of service, product privacy policy, request rate limit or incident history was found, and the only SDK is TypeScript.

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

Freestyle

  1. Send a firewall object on every POST /v5/vms. It is required, and a VM with no rules has no outbound internet
  2. Ask the owner to run freestyle login in a browser once, then mint a key with freestyle tokens create --output json
  3. Do not retry an exec that answers 409 VM_NON_RESPONSIVE. The command may already have run
  4. Keep exec-await under its 300,000 ms cap and use a PTY session or x-freestyle-background-after-secs for longer work
  5. Call the /v5 paths. The unversioned duplicates in the OpenAPI file are marked deprecated

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, Freestyle or Offscreen?

Offscreen scores 62.9 (B) on agent readiness against Freestyle's 58.5 (C), and leads in 5 of 7 scored categories. Freestyle leads on schema & documentation and maintenance & community.

Can an agent call Freestyle and Offscreen without installing anything?

Freestyle has a hosted endpoint at https://api.freestyle.sh/v5. No hosted endpoint is listed for Offscreen.

Are Freestyle and Offscreen open source?

No open-source release is listed for Freestyle. Offscreen is open source (MIT).

Other comparisons with Freestyle 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.