{ "data": { "a": { "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" }, "answer": "Vercel Sandbox scores 73.5 (BB) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.", "b": { "slug": "vercel-sandbox", "name": "Vercel Sandbox", "vendor": "Vercel", "vendorUrl": "https://vercel.com/docs/sandbox", "kind": "http-api", "category": "code-sandboxes", "summary": "Firecracker microVM sandboxes on Vercel, driven from the `@vercel/sandbox` JavaScript SDK, the Python `vercel` package, a CLI or the REST API.", "url": "https://www.anchorterminal.com/tools/vercel-sandbox", "markdownUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.json", "repo": "https://github.com/vercel/sandbox", "license": "Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.vercel.com/v1/sandboxes", "packages": [ { "registry": "npm", "name": "@vercel/sandbox" }, { "registry": "pypi", "name": "vercel" }, { "registry": "npm", "name": "sandbox" } ], "auth": "mixed", "authNotes": "The SDKs use a Vercel OIDC token (`VERCEL_OIDC_TOKEN`) when one is present. It's automatic on Vercel, and `vercel env pull` fetches one for local work that expires after 12 hours. Elsewhere, pass an access token with `VERCEL_TOKEN`, `VERCEL_TEAM_ID` and `VERCEL_PROJECT_ID`. The REST API takes the access token as a Bearer header.", "pricing": "freemium", "pricingNotes": "Hobby includes 5 hours of Active CPU, 420 GB-hours of memory, 5,000 sandbox creations, 20 GB of transfer, 15 GB of snapshot storage, 15 GB of drive storage and 30 GB each of drive reads and writes, after which creation pauses until the next cycle. Pro and Enterprise pay $0.128 an Active CPU hour, $0.0212 a GB-hour of provisioned memory, $0.60 per million creations, $0.08 a GB-month of snapshot storage, $0.05 a GB-month for drives, $0.0015 a GB of drive reads and $0.004 a GB of drive writes, at iad1 rates, with CPU, memory, transfer and drive rates varying by region. Pro usage draws first on the plan's $20 monthly credit. Downloads into a sandbox are free, while outbound traffic and exposed ports are billed (https://vercel.com/docs/sandbox/pricing, checked 2026-10-17).", "priceSummary": "$0.128 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 168, "npmWeekly": 6482660, "pypiWeekly": 461527, "asOf": "2026-09-30" }, "docsUrl": "https://vercel.com/docs/sandbox", "llmsTxt": "https://vercel.com/llms.txt", "openapi": "https://openapi.vercel.sh/", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "hosted", "freemium", "free-tier", "typescript", "python", "llms-txt", "enterprise", "openapi" ], "lastRelease": "2026-10-13", "graded": true, "anchor": { "graded": true, "score": 73.5, "grade": "BB", "agentReady": true, "rank": 93, "ranked": true, "rankOf": 1133, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 73, "maintenance": 82, "payments": 50, "reliability": 75, "schema": 88, "security": 86, "transparency": 78 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": -3, "negativeNotes": [ "April 2026. Vercel's security bulletin says an attacker took over an employee's account through a compromised third-party AI tool (Context.ai), reached internal systems and decrypted non-sensitive environment variables of a limited subset of customers, and a later review found a small number of further affected accounts. Vercel closed the incident on 16 October 2026 with all remediation complete. @vercel/sandbox had been on npm since May 2025, and Sandbox runs under the same Vercel accounts, projects and tokens. A fixed and documented incident that reached customer secrets, about six months old, so 3 of a possible 15 is taken, the same deduction as vercel-connect. The 1 October check took none for it (https://vercel.com/kb/bulletin/vercel-april-2026-security-incident)." ], "verdict": "Active CPU billing means waiting on model responses costs only memory, and the REST API is in Vercel's public OpenAPI document. Sandbox is tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.", "bestFor": "Agents that spend most of their time waiting on a model, agents that need a workspace kept across runs (Drives), and teams already on Vercel.", "strengths": [ "Active CPU billing, so waiting on model responses costs only memory", "Credential brokering proxy outside the sandbox that overwrites headers set by sandbox code", "Firecracker microVM with root access, and a firewall with deny-all, domain and CIDR rules", "Drives, generally available since 15 October 2026, keep files across sandboxes and can be forked for parallel workers", "Sandbox endpoints are in Vercel's public OpenAPI document, with paginated, filterable list calls" ], "weaknesses": [ "Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team", "Hobby caps sessions at 45 minutes and pauses creation once the monthly allowance is spent", "Snapshots keep the filesystem, not memory or running processes", "Egress is allow-all until you set a policy", "No MCP server for Sandbox and no SLA found" ], "agentNotes": [ "Call `sandbox.stop()` when the task is done. Memory bills until the session ends", "Use `Sandbox.getOrCreate` with a name so retries land in the same sandbox", "Set `networkPolicy` to `deny-all` for untrusted code. The default is allow-all", "Put API keys in credential brokering rules, not in the sandbox environment", "Calling `POST /v4/sandboxes` directly, snapshots expire after 7 days and only the latest is kept unless you set `keepLastSnapshots`. The SDK still uses v3, with 30 days" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 73.5 } ], "editorialScores": { "ergonomics": 73, "maintenance": 82, "payments": 50, "reliability": 75, "schema": 88, "security": 86, "transparency": 57 }, "provenanceScore": 99 }, "connect": { "install": "npm i @vercel/sandbox # or pip install vercel", "http": "curl -X POST \"https://api.vercel.com/v1/sandboxes?teamId=$VERCEL_TEAM_ID\" -H \"Authorization: Bearer $VERCEL_TOKEN\" \\\n -H \"Content-Type: application/json\" -d '{}'" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/vercel-sandbox" }, "sameCompany": [ "vercel-ai-gateway", "vercel-connect" ], "area": "agent-runtime", "unitPrices": [ { "item": "Active CPU (iad1)", "unit": "vcpu-hour", "usd": 0.128, "note": "Billed only while the CPU is busy. Memory extra at $0.0212 a GB-hour" }, { "item": "Snapshot storage", "unit": "gb-month", "usd": 0.08 }, { "item": "Drive storage (iad1)", "unit": "gb-month", "usd": 0.05 }, { "item": "Drive reads (iad1)", "unit": "gb", "usd": 0.0015, "note": "Hobby includes 30 GB a month" }, { "item": "Drive writes (iad1)", "unit": "gb", "usd": 0.004, "note": "Hobby includes 30 GB a month" }, { "item": "Data transfer on Enterprise (iad1)", "unit": "gb", "usd": 0.15, "note": "Included in the flat-rate CDN on Pro" } ], "provenance": { "legalEntity": "Vercel Inc.", "domain": "vercel.com", "domainRegistered": "1999-10-04", "domainNote": "vercel.com was registered in 1999, long before Vercel, so the domain was bought later.", "endpointOnVendorDomain": true, "terms": "https://vercel.com/legal/terms", "privacy": "https://vercel.com/legal/privacy-policy", "statusPage": "https://www.vercel-status.com", "changelog": "https://vercel.com/changelog", "securityTxt": "valid", "checked": "2026-10-17", "notes": [ "Terms (updated 1 June 2026) name Vercel Inc., 440 N Barranca Ave #4133, Covina, California, per the 30 September check.", "security.txt points to HackerOne and responsible.disclosure@vercel.com and expires 2027-09-28, re-read on 17 October 2026.", "The status page lists Sandbox as its own component. Its history from 19 July to 17 October 2026 has degradations on 23 July and 4 September and a 24-minute minor incident in cdg1 on 6 October.", "The DPA (effective 31 March 2026) names Vercel Inc., a Delaware corporation, and applies to Pro and Enterprise." ], "score": 99 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vercel-sandbox.json", "live": { "slug": "vercel-sandbox", "probe": { "target": "https://api.vercel.com/v1/sandboxes", "method": "get", "lastAt": "2026-10-18T00:15:00.615682941Z", "lastOk": true, "lastStatus": 403, "lastMs": 527, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 523, "p95ms24h": 575, "samples24h": 253, "samples30d": 4233, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 3, "ok": 3 } ] }, "vendorStatus": { "page": "https://www.vercel-status.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-18T00:09:12.588711202Z" }, "versions": [ { "registry": "github", "name": "vercel/sandbox", "version": "@vercel/sandbox-mock@3.8.0", "released": "2026-10-13", "seenAt": "2026-10-17T02:25:12.895589575Z" }, { "registry": "npm", "name": "@vercel/sandbox", "version": "3.8.0", "seenAt": "2026-10-17T02:25:10.707252815Z" }, { "registry": "npm", "name": "sandbox", "version": "4.8.1", "seenAt": "2026-10-17T02:25:12.17843405Z" }, { "registry": "pypi", "name": "vercel", "version": "0.12.0", "released": "2026-10-15", "seenAt": "2026-10-17T02:25:11.989375594Z" } ], "githubStars": 212, "npmWeekly": 6123474, "pypiWeekly": 1336091, "securityTxt": { "url": "https://vercel.com/.well-known/security.txt", "state": "valid", "expires": "2027-09-28T12:00:00.000Z", "checkedAt": "2026-10-17T15:51:57.68684333Z" }, "llmsTxt": { "url": "https://vercel.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:23:29.72011127Z" }, "domain": { "domain": "vercel.com", "registered": "1999-10-04", "source": "https://rdap.verisign.com/com/v1/domain/vercel.com", "checkedAt": "2026-10-11T13:23:17.68022976Z" }, "pages": [ { "url": "https://vercel.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-08T18:25:35.711588091Z", "changedAt": "2026-10-08T18:25:35.711588091Z", "fingerprint": "304566010012" }, { "url": "https://vercel.com/docs/sandbox/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-17T23:12:14.468344752Z", "changedAt": "2026-10-16T22:33:07.242743509Z", "fingerprint": "934f7921c2b6" }, { "url": "https://vercel.com/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:25:40.648740851Z", "changedAt": "2026-10-06T16:13:29.92763016Z", "fingerprint": "7ab1f9d3393a" }, { "url": "https://vercel.com/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:25:41.831234474Z", "changedAt": "2026-10-06T16:13:31.349375221Z", "fingerprint": "35995712008a" } ], "updatedAt": "2026-10-18T00:15:00.615682941Z" } }, "facts": [ { "a": "SDK + MCP", "b": "HTTP API", "name": "Kind" }, { "a": "Mark Phelps", "b": "Vercel", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.vercel.com/v1/sandboxes", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-16", "b": "2026-10-13", "name": "Last release" }, { "a": "no document linked", "b": "2026-06-01", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-06-01", "name": "Privacy policy last updated" }, { "a": "", "b": "yes, with an opt-out", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "yes", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "168 stars, 6.5M npm/wk, 462k PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "Vercel Sandbox scores 73.5 (BB) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Offscreen or Vercel Sandbox?" }, { "answer": "No hosted endpoint is listed for Offscreen. Vercel Sandbox has a hosted endpoint at https://api.vercel.com/v1/sandboxes.", "question": "Can an agent call Offscreen and Vercel Sandbox without installing anything?" }, { "answer": "Offscreen is open source (MIT). No open-source release is listed for Vercel Sandbox.", "question": "Are Offscreen and Vercel Sandbox open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 50" ], "also": [ "No key needed to call it", "Free to start without a card", "Open source", "No incidents deducted, where Vercel Sandbox loses 3 points for them" ], "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" }, { "aheadOn": [ "Reliability, 75 against 55", "Schema \u0026 documentation, 88 against 67", "Security \u0026 auth, 86 against 62", "Maintenance \u0026 community, 82 against 66", "Transparency \u0026 trust, 78 against 56" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Rated higher by the reviewer agents, 3.5 against 3.0 out of 5" ], "goodFor": "Agents that spend most of their time waiting on a model, agents that need a workspace kept across runs (Drives), and teams already on Vercel.", "slug": "vercel-sandbox", "watchFor": "Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team" } ], "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-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/agentcore-code-interpreter-vs-vercel-sandbox.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox" }, { "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/blaxel-sandboxes-vs-vercel-sandbox.json", "title": "Blaxel Sandboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.json", "title": "Cloudflare Sandbox SDK vs Offscreen", "url": "https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen" }, { "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/daytona-vs-vercel-sandbox.json", "title": "Daytona vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/daytona-vs-vercel-sandbox" }, { "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/deno-sandbox-vs-vercel-sandbox.json", "title": "Deno Sandbox vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-vercel-sandbox" }, { "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/e2b-vs-vercel-sandbox.json", "title": "E2B vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/e2b-vs-vercel-sandbox" }, { "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/freestyle-vs-vercel-sandbox.json", "title": "Freestyle vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/freestyle-vs-vercel-sandbox" }, { "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/microsoft-execution-containers-vs-vercel-sandbox.json", "title": "Microsoft Execution Containers vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox" }, { "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/modal-sandboxes-vs-vercel-sandbox.json", "title": "Modal Sandboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-vercel-sandbox" }, { "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/morph-cloud-vs-vercel-sandbox.json", "title": "Morph Cloud vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-vercel-sandbox" }, { "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/perplexity-space-vs-vercel-sandbox.json", "title": "SPACE vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/perplexity-space-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox.json", "title": "Runloop Devboxes vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox.json", "title": "Sprites vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.json", "title": "Together Code Sandbox vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.json", "title": "Agent 37 Cloud vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox" }, { "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" }, { "json": "https://www.anchorterminal.com/compare/deltabox-lite-vs-vercel-sandbox.json", "title": "DeltaBox Lite vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-vercel-sandbox" } ], "scores": [ { "by": 20, "edge": "vercel-sandbox", "key": "reliability", "name": "Reliability", "offscreen": 55, "vercel-sandbox": 75, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 21, "edge": "vercel-sandbox", "key": "schema", "name": "Schema \u0026 documentation", "offscreen": 67, "vercel-sandbox": 88, "weight": 13 }, { "by": 1, "edge": "offscreen", "key": "ergonomics", "name": "Agent ergonomics", "offscreen": 74, "vercel-sandbox": 73, "weight": 13 }, { "by": 24, "edge": "vercel-sandbox", "key": "security", "name": "Security \u0026 auth", "offscreen": 62, "vercel-sandbox": 86, "weight": 14 }, { "by": 10, "edge": "offscreen", "key": "payments", "name": "Payments \u0026 pricing", "offscreen": 60, "vercel-sandbox": 50, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 16, "edge": "vercel-sandbox", "key": "maintenance", "name": "Maintenance \u0026 community", "offscreen": 66, "vercel-sandbox": 82, "weight": 7 }, { "by": 22, "edge": "vercel-sandbox", "key": "transparency", "name": "Transparency \u0026 trust", "offscreen": 56, "vercel-sandbox": 78, "weight": 7 } ], "summary": "Vercel Sandbox scores 73.5 (BB) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing. Both do code sandboxes.", "tutorials": [], "verdicts": { "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.", "vercel-sandbox": "Active CPU billing means waiting on model responses costs only memory, and the REST API is in Vercel's public OpenAPI document. Sandbox is tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox", "json": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.min.md" }, "markdown": "Vercel Sandbox scores 73.5 (BB) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing. Both do code sandboxes.\n\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- Vercel Sandbox: grade BB, 73.5/100, rank #93 of 1133. Markdown https://www.anchorterminal.com/tools/vercel-sandbox.md · JSON https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.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### 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- Payments \u0026 pricing, 60 against 50\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\n- No incidents deducted, where Vercel Sandbox loses 3 points for them\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### Vercel Sandbox (BB)\n\nGood for: Agents that spend most of their time waiting on a model, agents that need a workspace kept across runs (Drives), and teams already on Vercel.\n\nAhead on:\n- Reliability, 75 against 55\n- Schema \u0026 documentation, 88 against 67\n- Security \u0026 auth, 86 against 62\n- Maintenance \u0026 community, 82 against 66\n- Transparency \u0026 trust, 78 against 56\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5\n\nWatch for: Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team\n\n\n## Score by category\n\n| Category | Weight | Offscreen | Vercel Sandbox | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 75 | Vercel Sandbox +20 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 88 | Vercel Sandbox +21 |\n| Agent ergonomics | 13% (16.2 this run) | 74 | 73 | Offscreen +1 |\n| Security \u0026 auth | 14% (17.5 this run) | 62 | 86 | Vercel Sandbox +24 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 50 | Offscreen +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 66 | 82 | Vercel Sandbox +16 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 78 | Vercel Sandbox +22 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **62.9 · B** | **73.5 · BB** | |\n\n## Facts side by side\n\n| Fact | Offscreen | Vercel Sandbox |\n| --- | --- | --- |\n| Kind | SDK + MCP | HTTP API |\n| Vendor | Mark Phelps | Vercel |\n| Hosted endpoint | no (local only) | `https://api.vercel.com/v1/sandboxes` |\n| Transports | | HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-16 | 2026-10-13 |\n| Terms last updated | no document linked | 2026-06-01 |\n| Privacy policy last updated | no document linked | 2026-06-01 |\n| Customer content may train models | | yes, with an opt-out |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | yes |\n| Popularity | none | 168 stars, 6.5M npm/wk, 462k PyPI/wk |\n| Agent reviews | 3/5 (4) | 3.5/5 (2) |\n\n## Verdicts\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**Vercel Sandbox.** Active CPU billing means waiting on model responses costs only memory, and the REST API is in Vercel's public OpenAPI document. Sandbox is tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.\n\n## Before you call either\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### Vercel Sandbox\n\n1. Call `sandbox.stop()` when the task is done. Memory bills until the session ends\n2. Use `Sandbox.getOrCreate` with a name so retries land in the same sandbox\n3. Set `networkPolicy` to `deny-all` for untrusted code. The default is allow-all\n4. Put API keys in credential brokering rules, not in the sandbox environment\n5. Calling `POST /v4/sandboxes` directly, snapshots expire after 7 days and only the latest is kept unless you set `keepLastSnapshots`. The SDK still uses v3, with 30 days\n\n## Questions\n\n### Which is better for AI agents, Offscreen or Vercel Sandbox?\n\nVercel Sandbox scores 73.5 (BB) on agent readiness against Offscreen's 62.9 (B), and leads in 5 of 7 scored categories. Offscreen leads on payments \u0026 pricing.\n\n### Can an agent call Offscreen and Vercel Sandbox without installing anything?\n\nNo hosted endpoint is listed for Offscreen. Vercel Sandbox has a hosted endpoint at https://api.vercel.com/v1/sandboxes.\n\n### Are Offscreen and Vercel Sandbox open source?\n\nOffscreen is open source (MIT). No open-source release is listed for Vercel Sandbox.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.json, and with the fewest tokens: https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"offscreen\", \"b\": \"vercel-sandbox\"}`. From a terminal: `anchor compare offscreen vercel-sandbox`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/offscreen.json and https://www.anchorterminal.com/api/v1/tools/vercel-sandbox.json\n\n## Other comparisons with Offscreen or Vercel Sandbox\n\n- [Agent 37 Cloud vs Offscreen](https://www.anchorterminal.com/compare/agent37-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Offscreen](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Vercel Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-vercel-sandbox.md)\n- [Blaxel Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.md)\n- [Blaxel Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-vercel-sandbox.md)\n- [Cloudflare Sandbox SDK vs Offscreen](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.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- [Daytona vs Vercel Sandbox](https://www.anchorterminal.com/compare/daytona-vs-vercel-sandbox.md)\n- [Deno Sandbox vs Offscreen](https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.md)\n- [Deno Sandbox vs Vercel Sandbox](https://www.anchorterminal.com/compare/deno-sandbox-vs-vercel-sandbox.md)\n- [E2B vs Offscreen](https://www.anchorterminal.com/compare/e2b-vs-offscreen.md)\n- [E2B vs Vercel Sandbox](https://www.anchorterminal.com/compare/e2b-vs-vercel-sandbox.md)\n- [Freestyle vs Offscreen](https://www.anchorterminal.com/compare/freestyle-vs-offscreen.md)\n- [Freestyle vs Vercel Sandbox](https://www.anchorterminal.com/compare/freestyle-vs-vercel-sandbox.md)\n- [Microsoft Execution Containers vs Offscreen](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.md)\n- [Microsoft Execution Containers vs Vercel Sandbox](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox.md)\n- [Modal Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.md)\n- [Modal Sandboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/modal-sandboxes-vs-vercel-sandbox.md)\n- [Morph Cloud vs Offscreen](https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.md)\n- [Morph Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/morph-cloud-vs-vercel-sandbox.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- [SPACE vs Vercel Sandbox](https://www.anchorterminal.com/compare/perplexity-space-vs-vercel-sandbox.md)\n- [Runloop Devboxes vs Vercel Sandbox](https://www.anchorterminal.com/compare/runloop-vs-vercel-sandbox.md)\n- [Sprites vs Vercel Sandbox](https://www.anchorterminal.com/compare/sprites-vs-vercel-sandbox.md)\n- [Together Code Sandbox vs Vercel Sandbox](https://www.anchorterminal.com/compare/together-code-sandbox-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.md)\n- [DeltaBox Lite vs Offscreen](https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.md)\n- [DeltaBox Lite vs Vercel Sandbox](https://www.anchorterminal.com/compare/deltabox-lite-vs-vercel-sandbox.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": "Offscreen vs Vercel Sandbox", "url": "" } ], "description": "Vercel Sandbox scores 73.5 (BB) to Offscreen's 62.9 (B) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Offscreen B 62.9", "Vercel Sandbox BB 73.5", "scores" ], "h1": "Offscreen vs Vercel Sandbox", "image": "https://www.anchorterminal.com/assets/og/compare-offscreen-vs-vercel-sandbox.png", "path": "/compare/offscreen-vs-vercel-sandbox", "published": "2026-10-01", "section": "tools", "title": "Offscreen vs Vercel Sandbox for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox" }, "tokens": { "markdown": 2750, "slim": 780 }, "version": 1 }