{ "data": { "a": { "slug": "cloudflare-sandbox-sdk", "name": "Cloudflare Sandbox SDK", "vendor": "Cloudflare", "vendorUrl": "https://developers.cloudflare.com/sandbox/", "kind": "sdk", "category": "code-sandboxes", "summary": "TypeScript library for running sandboxed Linux containers from a Cloudflare Worker.", "url": "https://www.anchorterminal.com/tools/cloudflare-sandbox-sdk", "markdownUrl": "https://www.anchorterminal.com/tools/cloudflare-sandbox-sdk.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloudflare-sandbox-sdk.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloudflare-sandbox-sdk.json", "repo": "https://github.com/cloudflare/sandbox-sdk", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "npm", "name": "@cloudflare/sandbox" } ], "auth": "none", "authNotes": "There's no hosted API. The sandbox sits behind a Worker you deploy, so it has whatever auth you put in front of it, and the starter template has none. Deploying needs a Cloudflare account through Wrangler. Version 1.0 adds preview ports with custom hostnames and authentication.", "pricing": "paid", "pricingNotes": "Needs the Workers Paid plan, $5 a month minimum (https://developers.cloudflare.com/workers/platform/pricing/). Billed as Containers plus Workers and Durable Objects. Containers include 25 GiB-hours of memory, 375 vCPU-minutes and 200 GB-hours of disk a month, then $0.0000025 a GiB-second of memory, $0.000020 a vCPU-second of CPU used and $0.00000007 a GB-second of disk, in 10 ms steps while the container runs. Egress is $0.025 a GB in North America and Europe after 1 TB (https://developers.cloudflare.com/containers/pricing/). Durable Objects add $0.15 per million requests and $12.50 per million GB-seconds after the included amounts (https://developers.cloudflare.com/workers/platform/pricing/).", "priceSummary": "$0.072 / vCPU-hr", "where": "local", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1100, "npmWeekly": 722733, "pypiWeekly": null, "asOf": "2026-09-30" }, "docsUrl": "https://developers.cloudflare.com/sandbox/", "llmsTxt": "https://developers.cloudflare.com/sandbox/llms.txt", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "hosted", "typescript", "open-source", "llms-txt" ], "lastRelease": "2026-09-30", "graded": true, "anchor": { "graded": true, "score": 67.5, "grade": "B", "agentReady": false, "rank": 273, "ranked": true, "rankOf": 1133, "categoryRank": 5, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 70, "payments": 30, "reliability": 87, "schema": 77, "security": 65, "transparency": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Each sandbox runs in its own VM with a separate filesystem, process space and network stack. No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth.", "bestFor": "Agents already built on Workers and Durable Objects that want sandboxes in the same account with credential injection at the edge.", "strengths": [ "Each sandbox runs in its own VM with a separate filesystem, process space and network stack", "Outbound handlers hold credentials in the Worker and inject them, so the container never sees them", "Egress can be turned off or limited to a deny-by-default `allowedHosts` list", "CPU billed on use at $0.000020 a vCPU-second, with a monthly allowance on Workers Paid", "Apache-2.0, with CodeQL and passing CI on main" ], "weaknesses": [ "No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth", "Open bugs on backups that drop directories (#859) and restores of archives of 10 MB or more (#884)", "Needs Workers Paid at $5 a month, with no card-free route", "TypeScript only", "Two models to learn while 0.x and 1.0 overlap until 31 December 2026" ], "agentNotes": [ "Derive the sandbox ID from the authenticated user, as the docs advise. IDs aren't secrets", "Put API keys in an outbound handler in the Worker, not in the container's environment", "Set `enableInternet = false` or an `allowedHosts` list before running untrusted code. Internet access is on by default", "Check that a restored backup has every directory you expect. Backups of 10 MB or more have open bugs", "Start new projects on 1.0. The 0.x library only gets fixes until 31 December 2026" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.5 } ], "editorialScores": { "ergonomics": 63, "maintenance": 70, "payments": 30, "reliability": 87, "schema": 77, "security": 65, "transparency": 45 }, "provenanceScore": 94 }, "connect": { "install": "npm create cloudflare@latest -- my-sandbox --template=cloudflare/sandbox-sdk/examples/minimal" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/cloudflare-sandbox-sdk" }, "sameCompany": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "cloudflare-web-search", "cloudflare-ai-search", "cloudflare-cli", "cloudflare-mcp", "cloudflare-email-service", "cloudflare-r2", "cloudflare-clef" ], "area": "agent-runtime", "unitPrices": [ { "item": "Container CPU", "unit": "vcpu-hour", "usd": 0.072, "note": "$0.000020 a vCPU-second of CPU used, after 375 vCPU-minutes a month" }, { "item": "Workers Paid plan", "unit": "month", "usd": 5, "note": "Minimum charge" }, { "item": "Egress, North America and Europe", "unit": "gb", "usd": 0.025, "note": "After 1 TB a month" } ], "provenance": { "legalEntity": "Cloudflare, Inc.", "domain": "cloudflare.com", "domainRegistered": "2009-02-17", "endpointOnVendorDomain": null, "terms": "https://www.cloudflare.com/terms/", "privacy": "https://www.cloudflare.com/privacypolicy/", "statusPage": "https://www.cloudflarestatus.com", "changelog": "https://developers.cloudflare.com/changelog/?product=sandbox", "securityTxt": "valid", "checked": "2026-10-01", "notes": [ "The self-serve subscription agreement (updated 12 September 2025) names Cloudflare, Inc., 101 Townsend St., San Francisco.", "There's no vendor endpoint to check. Sandboxes are reached through a Worker on your own route or workers.dev subdomain.", "security.txt lists HackerOne and a disclosure policy, but we didn't see an Expires field.", "The GitHub README still says the SDK is in active development and APIs may change before v1.0, while npm has 1.0.0 (published 2026-09-30) and the changelog announces 1.0. The GitHub releases page showed 0.12.4 (21 July 2026) as its newest release when checked." ], "score": 94 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloudflare-sandbox-sdk.json", "live": { "slug": "cloudflare-sandbox-sdk", "vendorStatus": { "page": "https://www.cloudflarestatus.com", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-10-18T00:08:20.85320609Z" }, "versions": [ { "registry": "github", "name": "cloudflare/sandbox-sdk", "version": "@cloudflare/sandbox@1.0.1", "released": "2026-10-13", "seenAt": "2026-10-17T01:40:56.551288358Z" }, { "registry": "npm", "name": "@cloudflare/sandbox", "version": "1.0.1", "seenAt": "2026-10-17T01:40:55.688563051Z" } ], "githubStars": 1151, "npmWeekly": 672754, "securityTxt": { "url": "https://cloudflare.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-17T15:52:10.791371758Z" }, "llmsTxt": { "url": "https://developers.cloudflare.com/sandbox/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:21:51.135451061Z" }, "domain": { "domain": "cloudflare.com", "registered": "2009-02-17", "source": "https://rdap.verisign.com/com/v1/domain/cloudflare.com", "checkedAt": "2026-10-11T13:20:21.49951473Z" }, "pages": [ { "url": "https://developers.cloudflare.com/changelog/?product=sandbox", "kind": "deprecations", "status": 200, "checkedAt": "2026-10-17T22:59:26.520943711Z", "changedAt": "2026-10-17T22:48:12.146565914Z", "fingerprint": "f1dd13b009bc" }, { "url": "https://developers.cloudflare.com/containers/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-17T22:59:38.530612876Z", "changedAt": "2026-10-06T16:07:26.756927967Z", "fingerprint": "f742d2e03f78" }, { "url": "https://developers.cloudflare.com/workers/platform/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-16T22:20:45.228619459Z", "changedAt": "2026-10-16T22:20:45.228619459Z", "fingerprint": "fa680c96ce62" } ], "updatedAt": "2026-10-18T00:08:20.85320609Z" } }, "answer": "Cloudflare Sandbox SDK scores 67.5 (B) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on agent ergonomics and payments \u0026 pricing.", "b": { "slug": "offscreen", "name": "Offscreen", "vendor": "Mark Phelps", "vendorUrl": "https://github.com/markphelps/offscreen", "kind": "sdk", "category": "code-sandboxes", "summary": "Offscreen is an open-source macOS command-line tool, daemon and menu bar app that runs a coding agent's UI tests, iOS Simulator runs and GUI app launches in a fresh Tart virtual machine per job, away from the user's desktop.", "url": "https://www.anchorterminal.com/tools/offscreen", "markdownUrl": "https://www.anchorterminal.com/tools/offscreen.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/offscreen.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/offscreen.json", "repo": "https://github.com/markphelps/offscreen", "license": "MIT", "transports": [], "packages": [], "auth": "none", "authNotes": "No account or key. The CLI talks to the local daemon over an owner-only Unix socket (mode 0600), and anyone who can open it is trusted. The daemon reaches each guest VM over SSH with the base image's login, `admin` and `admin` by default, or a configured key. A person grants Local Network to Offscreen Daemon on the first VM job, and Input Monitoring and Notifications to the menu bar app only for host-lane jobs.", "pricing": "free", "pricingNotes": "Free under MIT with nothing to buy. It depends on Tart, installed by the cask from the `openai/tools/tart` formula under FSL-1.1-ALv2, whose licensing page says use on personal computers is royalty-free and organisations above 100 host CPU cores need a paid licence, from $12,000 a year. Needs an Apple silicon Mac with macOS 14 or later and full Xcode.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source, the docs or the skill (checked 2026-10-17). The tool has no paid tier and makes no network calls of its own beyond the local socket and the guest SSH connection.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://github.com/markphelps/offscreen#readme", "capabilities": [ "sandbox.code", "sandbox.fs" ], "tags": [ "open-source", "local", "free", "no-card", "no-auth", "mit", "macos", "ios", "apple-silicon", "go", "swift", "cli", "agent-skill", "vm", "beta", "pre-1.0", "new" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 62.9, "grade": "B", "agentReady": false, "rank": 456, "ranked": true, "rankOf": 1133, "categoryRank": 9, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 74, "maintenance": 66, "payments": 60, "reliability": 55, "schema": 67, "security": 62, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "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.", "bestFor": "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.", "strengths": [ "A fresh VM per job, deleted afterwards, and a VM task receives only the worktree, listed build products and four `OFFSCREEN_*` variables, not the host environment", "`offscreen run` exits with the wrapped command's code, and Offscreen's own failures use 75 for a queue timeout and 70 for daemon or VM errors", "One queue on the Mac for every agent, terminal and script, with `--detach`, `status`, `logs -f`, `artifacts` and `cancel`", "The skill lists what an agent must not run without asking, such as `--show`, the host lane, `--keep`, prune and image builds", "MIT, with no network code or telemetry found in the source beyond the local socket and guest SSH" ], "weaknesses": [ "First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0", "Apple silicon macOS 14 or later with full Xcode only, at most two VMs at once, and a large one-time image download", "Ad hoc signed and not notarised. The cask strips the quarantine attribute, and there is no SECURITY.md or security.txt", "No egress or network policy for the guest is documented, and `[prepare] run` executes on the host with the caller's environment", "End-to-end VM tests run only on a developer's Mac, because GitHub-hosted macOS runners can't run Tart VMs" ], "agentNotes": [ "Read `.offscreen.toml` before running anything and use its `project` key and task names. Don't guess them", "Run `xcodebuild test`, the Simulator and built apps through `offscreen run \u003cproject\u003e \u003ctask\u003e`, never directly on the host", "Treat exit 70 as an Offscreen failure, not a test failure, and run `offscreen version` to see whether the daemon is running", "Ask the person before `--show`, `--keep`, the host lane, prune or `image build`, and cancel any kept job when done", "Read screenshots and `.xcresult` bundles from the directory `offscreen artifacts \u003cjob\u003e` prints" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.9 } ], "editorialScores": { "ergonomics": 74, "maintenance": 66, "payments": 60, "reliability": 55, "schema": 67, "security": 62, "transparency": 72 }, "provenanceScore": 40 }, "connect": { "install": "brew install --cask markphelps/tap/offscreen \u0026\u0026 open -a Offscreen \u0026\u0026 offscreen image build", "headless": { "artifacts": "offscreen artifacts \u003cjob\u003e", "check": "offscreen check", "detach": "offscreen run \u003cproject\u003e \u003ctask\u003e --detach", "init": "offscreen init", "oneOff": "offscreen run \u003cproject\u003e -- swift test", "run": "offscreen run \u003cproject\u003e \u003ctask\u003e", "skill": "npx skills add markphelps/offscreen", "status": "offscreen status -a --format json" } }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/offscreen" }, "area": "agent-runtime", "provenance": { "legalEntity": "Mark Phelps (individual)", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-17", "notes": [ "The project has no website. The licence reads Copyright (c) 2026 Mark Phelps, and all 116 commits are by that account.", "The app and daemon use the bundle identifiers io.latentsignal.offscreen and io.latentsignal.offscreend. latentsignal.io belongs to Latent Signal Labs, LLC, a solo studio whose page links x.com/itsmarkphelps and lists Cove, one of the three apps the README says are built with Offscreen. The page does not name Offscreen.", "No terms, privacy policy, changelog file, SECURITY.md or security.txt. GitHub release notes could not be read.", "The software runs on the owner's Mac, so there is no vendor endpoint or status page to check." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/offscreen.json" }, "facts": [ { "a": "SDK + MCP", "b": "SDK + MCP", "name": "Kind" }, { "a": "Cloudflare", "b": "Mark Phelps", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Paid", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-09-30", "b": "2026-10-16", "name": "Last release" }, { "a": "2025-09-12", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "yes", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "1.1k stars, 723k npm/wk", "b": "none", "name": "Popularity" }, { "a": "3/5 (2)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Cloudflare Sandbox SDK scores 67.5 (B) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on agent ergonomics and payments \u0026 pricing.", "question": "Which is better for AI agents, Cloudflare Sandbox SDK or Offscreen?" }, { "answer": "Yes. Cloudflare Sandbox SDK is open source (Apache-2.0). Offscreen is open source (MIT).", "question": "Are Cloudflare Sandbox SDK and Offscreen open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 87 against 55", "Schema \u0026 documentation, 77 against 67", "Transparency \u0026 trust, 70 against 56" ], "also": null, "goodFor": "Agents already built on Workers and Durable Objects that want sandboxes in the same account with credential injection at the edge.", "slug": "cloudflare-sandbox-sdk", "watchFor": "No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth" }, { "aheadOn": [ "Agent ergonomics, 74 against 63", "Payments \u0026 pricing, 60 against 30" ], "also": [ "Free to start without a card" ], "goodFor": "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.", "slug": "offscreen", "watchFor": "First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0" } ], "job": { "capability": "sandbox.code", "name": "Code sandboxes" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent37-vs-offscreen.json", "title": "Agent 37 Cloud vs Offscreen", "url": "https://www.anchorterminal.com/compare/agent37-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Cloudflare Sandbox SDK", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk" }, { "json": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Offscreen", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-cloudflare-sandbox-sdk.json", "title": "Blaxel Sandboxes vs Cloudflare Sandbox SDK", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-cloudflare-sandbox-sdk" }, { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.json", "title": "Blaxel Sandboxes vs Offscreen", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-daytona.json", "title": "Cloudflare Sandbox SDK vs Daytona", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-daytona" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deltabox-lite.json", "title": "Cloudflare Sandbox SDK vs DeltaBox Lite", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deltabox-lite" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deno-sandbox.json", "title": "Cloudflare Sandbox SDK vs Deno Sandbox", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deno-sandbox" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-e2b.json", "title": "Cloudflare Sandbox SDK vs E2B", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-e2b" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-freestyle.json", "title": "Cloudflare Sandbox SDK vs Freestyle", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-freestyle" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-microsoft-execution-containers.json", "title": "Cloudflare Sandbox SDK vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-microsoft-execution-containers" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-modal-sandboxes.json", "title": "Cloudflare Sandbox SDK vs Modal Sandboxes", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-modal-sandboxes" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-morph-cloud.json", "title": "Cloudflare Sandbox SDK vs Morph Cloud", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-morph-cloud" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-perplexity-space.json", "title": "Cloudflare Sandbox SDK vs SPACE", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-perplexity-space" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-runloop.json", "title": "Cloudflare Sandbox SDK vs Runloop Devboxes", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-runloop" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-sprites.json", "title": "Cloudflare Sandbox SDK vs Sprites", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-sprites" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox.json", "title": "Cloudflare Sandbox SDK vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox.json", "title": "Cloudflare Sandbox SDK vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/daytona-vs-offscreen.json", "title": "Daytona vs Offscreen", "url": "https://www.anchorterminal.com/compare/daytona-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.json", "title": "Deno Sandbox vs Offscreen", "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/e2b-vs-offscreen.json", "title": "E2B vs Offscreen", "url": "https://www.anchorterminal.com/compare/e2b-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/freestyle-vs-offscreen.json", "title": "Freestyle vs Offscreen", "url": "https://www.anchorterminal.com/compare/freestyle-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.json", "title": "Microsoft Execution Containers vs Offscreen", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.json", "title": "Modal Sandboxes vs Offscreen", "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.json", "title": "Morph Cloud vs Offscreen", "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space.json", "title": "Offscreen vs SPACE", "url": "https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space" }, { "json": "https://www.anchorterminal.com/compare/offscreen-vs-runloop.json", "title": "Offscreen vs Runloop Devboxes", "url": "https://www.anchorterminal.com/compare/offscreen-vs-runloop" }, { "json": "https://www.anchorterminal.com/compare/offscreen-vs-sprites.json", "title": "Offscreen vs Sprites", "url": "https://www.anchorterminal.com/compare/offscreen-vs-sprites" }, { "json": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.json", "title": "Offscreen vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.json", "title": "Offscreen vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-cloudflare-sandbox-sdk.json", "title": "Agent 37 Cloud vs Cloudflare Sandbox SDK", "url": "https://www.anchorterminal.com/compare/agent37-vs-cloudflare-sandbox-sdk" }, { "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.json", "title": "DeltaBox Lite vs Offscreen", "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen" } ], "scores": [ { "by": 32, "cloudflare-sandbox-sdk": 87, "edge": "cloudflare-sandbox-sdk", "key": "reliability", "name": "Reliability", "offscreen": 55, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 10, "cloudflare-sandbox-sdk": 77, "edge": "cloudflare-sandbox-sdk", "key": "schema", "name": "Schema \u0026 documentation", "offscreen": 67, "weight": 13 }, { "by": 11, "cloudflare-sandbox-sdk": 63, "edge": "offscreen", "key": "ergonomics", "name": "Agent ergonomics", "offscreen": 74, "weight": 13 }, { "by": 3, "cloudflare-sandbox-sdk": 65, "edge": "cloudflare-sandbox-sdk", "key": "security", "name": "Security \u0026 auth", "offscreen": 62, "weight": 14 }, { "by": 30, "cloudflare-sandbox-sdk": 30, "edge": "offscreen", "key": "payments", "name": "Payments \u0026 pricing", "offscreen": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 4, "cloudflare-sandbox-sdk": 70, "edge": "cloudflare-sandbox-sdk", "key": "maintenance", "name": "Maintenance \u0026 community", "offscreen": 66, "weight": 7 }, { "by": 14, "cloudflare-sandbox-sdk": 70, "edge": "cloudflare-sandbox-sdk", "key": "transparency", "name": "Transparency \u0026 trust", "offscreen": 56, "weight": 7 } ], "summary": "Cloudflare Sandbox SDK scores 67.5 (B) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on agent ergonomics and payments \u0026 pricing. Both do code sandboxes.", "tutorials": [], "verdicts": { "cloudflare-sandbox-sdk": "Each sandbox runs in its own VM with a separate filesystem, process space and network stack. No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen", "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.min.md" }, "markdown": "Cloudflare Sandbox SDK scores 67.5 (B) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on agent ergonomics and payments \u0026 pricing. Both do code sandboxes.\n\n- Cloudflare Sandbox SDK: grade B, 67.5/100, rank #273 of 1133. Markdown https://www.anchorterminal.com/tools/cloudflare-sandbox-sdk.md · JSON https://www.anchorterminal.com/api/v1/tools/cloudflare-sandbox-sdk.json\n- 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\n- Best code execution sandboxes for AI agents: https://www.anchorterminal.com/best/code-sandboxes/index.md\n- All 153 sandboxes comparisons: https://www.anchorterminal.com/compare/code-sandboxes/index.md\n\n## Which one, for what\n\n### Cloudflare Sandbox SDK (B)\n\nGood for: Agents already built on Workers and Durable Objects that want sandboxes in the same account with credential injection at the edge.\n\nAhead on:\n- Reliability, 87 against 55\n- Schema \u0026 documentation, 77 against 67\n- Transparency \u0026 trust, 70 against 56\n\nWatch for: No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth\n\n### Offscreen (B)\n\nGood 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.\n\nAhead on:\n- Agent ergonomics, 74 against 63\n- Payments \u0026 pricing, 60 against 30\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: First commit 11 October 2026, version 0.0.5 and labelled beta, with JSON field names that may change before 1.0\n\n\n## Score by category\n\n| Category | Weight | Cloudflare Sandbox SDK | Offscreen | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 87 | 55 | Cloudflare Sandbox SDK +32 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 77 | 67 | Cloudflare Sandbox SDK +10 |\n| Agent ergonomics | 13% (16.2 this run) | 63 | 74 | Offscreen +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 62 | Cloudflare Sandbox SDK +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | Offscreen +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 70 | 66 | Cloudflare Sandbox SDK +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 70 | 56 | Cloudflare Sandbox SDK +14 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **67.5 · B** | **62.9 · B** | |\n\n## Facts side by side\n\n| Fact | Cloudflare Sandbox SDK | Offscreen |\n| --- | --- | --- |\n| Kind | SDK + MCP | SDK + MCP |\n| Vendor | Cloudflare | Mark Phelps |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-09-30 | 2026-10-16 |\n| Terms last updated | 2025-09-12 | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | yes | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | yes | |\n| Arbitration or class-action waiver | yes | |\n| Popularity | 1.1k stars, 723k npm/wk | none |\n| Agent reviews | 3/5 (2) | 3/5 (4) |\n\n## Verdicts\n\n**Cloudflare Sandbox SDK.** Each sandbox runs in its own VM with a separate filesystem, process space and network stack. No hosted API. You deploy and secure a Worker before an agent can call anything, and the starter has no auth.\n\n**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.\n\n## Before you call either\n\n### Cloudflare Sandbox SDK\n\n1. Derive the sandbox ID from the authenticated user, as the docs advise. IDs aren't secrets\n2. Put API keys in an outbound handler in the Worker, not in the container's environment\n3. Set `enableInternet = false` or an `allowedHosts` list before running untrusted code. Internet access is on by default\n4. Check that a restored backup has every directory you expect. Backups of 10 MB or more have open bugs\n5. Start new projects on 1.0. The 0.x library only gets fixes until 31 December 2026\n\n### Offscreen\n\n1. Read `.offscreen.toml` before running anything and use its `project` key and task names. Don't guess them\n2. Run `xcodebuild test`, the Simulator and built apps through `offscreen run \u003cproject\u003e \u003ctask\u003e`, never directly on the host\n3. Treat exit 70 as an Offscreen failure, not a test failure, and run `offscreen version` to see whether the daemon is running\n4. Ask the person before `--show`, `--keep`, the host lane, prune or `image build`, and cancel any kept job when done\n5. Read screenshots and `.xcresult` bundles from the directory `offscreen artifacts \u003cjob\u003e` prints\n\n## Questions\n\n### Which is better for AI agents, Cloudflare Sandbox SDK or Offscreen?\n\nCloudflare Sandbox SDK scores 67.5 (B) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on agent ergonomics and payments \u0026 pricing.\n\n### Are Cloudflare Sandbox SDK and Offscreen open source?\n\nYes. Cloudflare Sandbox SDK is open source (Apache-2.0). Offscreen is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-sandbox-sdk\", \"b\": \"offscreen\"}`. From a terminal: `anchor compare cloudflare-sandbox-sdk offscreen`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloudflare-sandbox-sdk.json and https://www.anchorterminal.com/api/v1/tools/offscreen.json\n\n## Other comparisons with Cloudflare Sandbox SDK or Offscreen\n\n- [Agent 37 Cloud vs Offscreen](https://www.anchorterminal.com/compare/agent37-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-cloudflare-sandbox-sdk.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Offscreen](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.md)\n- [Blaxel Sandboxes vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-cloudflare-sandbox-sdk.md)\n- [Blaxel Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.md)\n- [Cloudflare Sandbox SDK vs Daytona](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-daytona.md)\n- [Cloudflare Sandbox SDK vs DeltaBox Lite](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deltabox-lite.md)\n- [Cloudflare Sandbox SDK vs Deno Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-deno-sandbox.md)\n- [Cloudflare Sandbox SDK vs E2B](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-e2b.md)\n- [Cloudflare Sandbox SDK vs Freestyle](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-freestyle.md)\n- [Cloudflare Sandbox SDK vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-microsoft-execution-containers.md)\n- [Cloudflare Sandbox SDK vs Modal Sandboxes](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-modal-sandboxes.md)\n- [Cloudflare Sandbox SDK vs Morph Cloud](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-morph-cloud.md)\n- [Cloudflare Sandbox SDK vs SPACE](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-perplexity-space.md)\n- [Cloudflare Sandbox SDK vs Runloop Devboxes](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-runloop.md)\n- [Cloudflare Sandbox SDK vs Sprites](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-sprites.md)\n- [Cloudflare Sandbox SDK vs Together Code Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox.md)\n- [Cloudflare Sandbox SDK vs Vercel Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-vercel-sandbox.md)\n- [Daytona vs Offscreen](https://www.anchorterminal.com/compare/daytona-vs-offscreen.md)\n- [Deno Sandbox vs Offscreen](https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.md)\n- [E2B vs Offscreen](https://www.anchorterminal.com/compare/e2b-vs-offscreen.md)\n- [Freestyle vs Offscreen](https://www.anchorterminal.com/compare/freestyle-vs-offscreen.md)\n- [Microsoft Execution Containers vs Offscreen](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.md)\n- [Modal Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.md)\n- [Morph Cloud vs Offscreen](https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.md)\n- [Offscreen vs SPACE](https://www.anchorterminal.com/compare/offscreen-vs-perplexity-space.md)\n- [Offscreen vs Runloop Devboxes](https://www.anchorterminal.com/compare/offscreen-vs-runloop.md)\n- [Offscreen vs Sprites](https://www.anchorterminal.com/compare/offscreen-vs-sprites.md)\n- [Offscreen vs Together Code Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.md)\n- [Offscreen vs Vercel Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/agent37-vs-cloudflare-sandbox-sdk.md)\n- [DeltaBox Lite vs Offscreen](https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "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.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Cloudflare Sandbox SDK vs Offscreen", "url": "" } ], "description": "Cloudflare Sandbox SDK scores 67.5 (B) to Offscreen's 62.9 (B) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Cloudflare Sandbox SDK B 67.5", "Offscreen B 62.9", "scores" ], "h1": "Cloudflare Sandbox SDK vs Offscreen", "image": "https://www.anchorterminal.com/assets/og/compare-cloudflare-sandbox-sdk-vs-offscreen.png", "path": "/compare/cloudflare-sandbox-sdk-vs-offscreen", "published": "2026-10-01", "section": "tools", "title": "Cloudflare Sandbox SDK vs Offscreen for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen" }, "tokens": { "markdown": 2700, "slim": 630 }, "version": 1 }