{ "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": "Offscreen scores 62.9 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and maintenance \u0026 community.", "b": { "slug": "together-code-sandbox", "name": "Together Code Sandbox", "vendor": "Together AI", "vendorUrl": "https://www.together.ai", "kind": "http-api", "category": "code-sandboxes", "summary": "Together AI's hosted virtual machine sandboxes for running commands and code, built from Docker-image snapshots and driven from the `together-sandbox` Python SDK, TypeScript SDK or CLI. Access is by allowlist, on request to Together.", "url": "https://www.anchorterminal.com/tools/together-code-sandbox", "markdownUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/together-code-sandbox.json", "repo": "https://github.com/togethercomputer/together-sandbox", "license": "Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT", "transports": [ "http" ], "remoteUrl": "https://api.bartender.codesandbox.io", "packages": [ { "registry": "pypi", "name": "together-sandbox" }, { "registry": "npm", "name": "together-sandbox" } ], "auth": "api-key", "authNotes": "Access is by allowlist. The docs say the `together-sandbox` SDK and CLI must be enabled for an organisation and to contact Together to request it. Once enabled, a project-scoped Together API key is sent as a Bearer token, read from `TOGETHER_API_KEY`. Keys are revocable, can carry an expiry date and have no finer scopes. Each running sandbox also has its own agent token for the in-VM API, which the SDKs handle.", "pricing": "usage", "pricingNotes": "The pricing page lists Code Sandbox compute at $0.0446 per vCPU-hour and $0.0149 per GiB of RAM per hour, and does not say whether that rate covers the new SDK as well as the legacy one. No free tier or sandbox lets an agent start without a contract. Together has no free trial, platform access needs a $15 first credit purchase, and the organisation must then be enabled on request (https://www.together.ai/pricing, https://docs.together.ai/docs/billing-credits).", "priceSummary": "$0.0446 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs page, the repository or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 3, "npmWeekly": 1298, "pypiWeekly": 3387, "asOf": "2026-10-08" }, "docsUrl": "https://docs.together.ai/docs/together-code-sandbox", "llmsTxt": "https://docs.together.ai/llms.txt", "openapi": "https://togethercomputer.github.io/together-sandbox/api-openapi.json", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "hosted", "usage", "allowlist", "sales-led", "openapi", "llms-txt", "python", "typescript", "cli", "security-txt" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 53.6, "grade": "D", "agentReady": false, "rank": 781, "ranked": true, "rankOf": 1133, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 83, "payments": 20, "reliability": 25, "schema": 86, "security": 47, "transparency": 60 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service.", "bestFor": "Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.", "strengths": [ "Public OpenAPI documents for the management API (17 operations) and the in-VM API (25), in the repository and on GitHub Pages", "Terminating with `memory: true` saves disk and memory, and a new sandbox created from that snapshot resumes its running processes", "List calls are cursor-paginated (1 to 100 a page) with filters for status, source snapshot and tags", "Both SDKs retry 408, 429 and 5xx three times with exponential backoff, and the docs warn that `snapshots.create` is not idempotent", "Releases on 30 September, 1 October and 7 October 2026, with a generated changelog that marks breaking changes" ], "weaknesses": [ "The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access", "No rate limits, concurrency limits or SLA found, and neither status.together.ai nor status.codesandbox.io names the service", "Every sandbox port is public unless an experimental inbound policy is set, and no outbound controls exist yet", "Three major versions between 2 June and 28 July 2026, and memory snapshots were removed in 4.0.0 and restored in 4.0.4", "The management API answers at `api.bartender.codesandbox.io`, off Together's domain, and the privacy policy's data table has no sandbox row" ], "agentNotes": [ "Confirm the organisation is on Together's allowlist before installing. A valid `TOGETHER_API_KEY` alone is not enough", "Build a snapshot first with `snapshots.create`. No default image exists, and every sandbox needs `snapshot_id` or `snapshot_alias`", "Set `ttl` at creation or call `terminate()`. Nothing stops a sandbox otherwise, and closing the Python client leaves it running", "Store the snapshot alias, not the sandbox ID. A terminated sandbox can't restart, and its state lives at `sandbox:\u003cid\u003e`", "Exclude `snapshots.create` from retries with `should_retry`, and set `experimental.network_policy` before serving anything private on a port" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.6 } ], "editorialScores": { "ergonomics": 70, "maintenance": 83, "payments": 20, "reliability": 25, "schema": 86, "security": 47, "transparency": 43 }, "provenanceScore": 77 }, "connect": { "install": "pip install together-sandbox # or npm install together-sandbox" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/together-code-sandbox" }, "sameCompany": [ "together-fine-tuning" ], "area": "agent-runtime", "unitPrices": [ { "item": "vCPU", "unit": "vcpu-hour", "usd": 0.0446, "note": "RAM extra at $0.0149 per GiB-hour. Listed under Code Sandbox on the pricing page, which doesn't name the SDK" }, { "item": "Default sandbox (1 vCPU, 2 GiB)", "unit": "session-hour", "usd": 0.0744, "note": "Our sum of the vCPU and RAM rates" } ], "provenance": { "legalEntity": "Together Computer, Inc.", "domain": "together.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": false, "terms": "https://www.together.ai/terms-of-service", "privacy": "https://www.together.ai/privacy", "statusPage": "https://status.together.ai", "changelog": "https://github.com/togethercomputer/together-sandbox/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-10-08", "notes": [ "The terms of service (updated 19 May 2026) name Together Computer, Inc., a Delaware corporation at 251 Rhode Island Street, San Francisco, and cover the website and the Services. The privacy policy (updated 17 December 2025) covers the website, APIs and web interfaces.", "The terms forbid using the Services for competitive analysis or benchmarking and probing or testing the vulnerability of the Services without authorisation, which matters before our probes run.", "The management API answers at api.bartender.codesandbox.io and sandbox URLs sit under csb.app. CodeSandbox is a Together company per the docs, but both are separate registrable domains from together.ai.", "status.together.ai has no sandbox component. status.codesandbox.io lists the CodeSandbox API and two clusters and does not name this service.", "security.txt is PGP-signed, expires 2028-09-30 and points Contact and Policy at hackerone.com/together_ai. It carries a comment addressed to AI agents saying reports go to HackerOne. Recorded as a fact, and we did not act on it.", "RDAP for together.ai gives a registration date of 2017-12-16.", "trust.together.ai is script-drawn and showed our reader only its title. No DPA or sub-processor page was found." ], "score": 77 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/together-code-sandbox.json", "live": { "slug": "together-code-sandbox", "probe": { "target": "https://api.bartender.codesandbox.io", "method": "get", "lastAt": "2026-10-18T00:14:59.399982585Z", "lastOk": true, "lastStatus": 404, "lastMs": 155, "authRequired": false, "uptime24h": 100, "uptime30d": 99.95, "p50ms24h": 146, "p95ms24h": 238, "samples24h": 253, "samples30d": 2168, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 169 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 246 }, { "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://status.together.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-17T22:51:57.687725234Z" }, "versions": [ { "registry": "github", "name": "togethercomputer/together-sandbox", "version": "together-sandbox-workspace-v4.1.1", "released": "2026-10-07", "seenAt": "2026-10-17T02:23:07.533204553Z" }, { "registry": "npm", "name": "together-sandbox", "version": "4.1.1", "seenAt": "2026-10-17T02:23:06.760013016Z" }, { "registry": "pypi", "name": "together-sandbox", "version": "4.1.1", "released": "2026-10-07", "seenAt": "2026-10-17T02:23:06.578215732Z" } ], "githubStars": 3, "npmWeekly": 3543, "pypiWeekly": 1735, "securityTxt": { "url": "https://together.ai/.well-known/security.txt", "state": "valid", "expires": "2028-09-30T00:00:00.000Z", "checkedAt": "2026-10-17T15:52:31.070079876Z" }, "llmsTxt": { "url": "https://docs.together.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:23:23.765355278Z" }, "domain": { "domain": "together.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/together.ai", "checkedAt": "2026-10-11T13:26:27.876113125Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/togethercomputer/together-sandbox/main/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-10-17T23:11:14.775269856Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "0441361f331e" }, { "url": "https://www.together.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-17T23:21:10.937714805Z", "changedAt": "2026-10-17T23:21:10.937714805Z", "fingerprint": "1cb787a1aaf0" }, { "url": "https://www.together.ai/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-17T23:21:13.0344049Z", "changedAt": "2026-10-16T22:42:24.051716602Z", "fingerprint": "e7b46f93f904" }, { "url": "https://www.together.ai/terms-of-service", "kind": "terms", "status": 304, "checkedAt": "2026-10-17T23:21:14.959483551Z", "changedAt": "2026-10-16T22:42:26.107597751Z", "fingerprint": "42da048bc97e" } ], "updatedAt": "2026-10-18T00:14:59.399982585Z" } }, "facts": [ { "a": "SDK + MCP", "b": "HTTP API", "name": "Kind" }, { "a": "Mark Phelps", "b": "Together AI", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.bartender.codesandbox.io", "name": "Hosted endpoint" }, { "a": "", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-16", "b": "2026-10-07", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "yes", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "3 stars, 1.3k npm/wk, 3.4k PyPI/wk", "name": "Popularity" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Offscreen scores 62.9 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and maintenance \u0026 community.", "question": "Which is better for AI agents, Offscreen or Together Code Sandbox?" }, { "answer": "No hosted endpoint is listed for Offscreen. Together Code Sandbox has a hosted endpoint at https://api.bartender.codesandbox.io.", "question": "Can an agent call Offscreen and Together Code Sandbox without installing anything?" }, { "answer": "Offscreen is open source (MIT). No open-source release is listed for Together Code Sandbox.", "question": "Are Offscreen and Together Code Sandbox open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 55 against 25", "Security \u0026 auth, 62 against 47", "Payments \u0026 pricing, 60 against 20" ], "also": [ "No key needed to call it", "Free to start without a card", "Open source" ], "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": [ "Schema \u0026 documentation, 86 against 67", "Maintenance \u0026 community, 83 against 66" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.", "slug": "together-code-sandbox", "watchFor": "The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access" } ], "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-together-code-sandbox.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-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-together-code-sandbox.json", "title": "Blaxel Sandboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-together-code-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-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/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-together-code-sandbox.json", "title": "Daytona vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/daytona-vs-together-code-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-together-code-sandbox.json", "title": "Deno Sandbox vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/deno-sandbox-vs-together-code-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-together-code-sandbox.json", "title": "E2B vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/e2b-vs-together-code-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-together-code-sandbox.json", "title": "Freestyle vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/freestyle-vs-together-code-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-together-code-sandbox.json", "title": "Microsoft Execution Containers vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-together-code-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-together-code-sandbox.json", "title": "Modal Sandboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/modal-sandboxes-vs-together-code-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-together-code-sandbox.json", "title": "Morph Cloud vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/morph-cloud-vs-together-code-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-vercel-sandbox.json", "title": "Offscreen vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox" }, { "json": "https://www.anchorterminal.com/compare/perplexity-space-vs-together-code-sandbox.json", "title": "SPACE vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/perplexity-space-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox.json", "title": "Runloop Devboxes vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/sprites-vs-together-code-sandbox.json", "title": "Sprites vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/sprites-vs-together-code-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-together-code-sandbox.json", "title": "Agent 37 Cloud vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-together-code-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-together-code-sandbox.json", "title": "DeltaBox Lite vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/deltabox-lite-vs-together-code-sandbox" } ], "scores": [ { "by": 30, "edge": "offscreen", "key": "reliability", "name": "Reliability", "offscreen": 55, "together-code-sandbox": 25, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 19, "edge": "together-code-sandbox", "key": "schema", "name": "Schema \u0026 documentation", "offscreen": 67, "together-code-sandbox": 86, "weight": 13 }, { "by": 4, "edge": "offscreen", "key": "ergonomics", "name": "Agent ergonomics", "offscreen": 74, "together-code-sandbox": 70, "weight": 13 }, { "by": 15, "edge": "offscreen", "key": "security", "name": "Security \u0026 auth", "offscreen": 62, "together-code-sandbox": 47, "weight": 14 }, { "by": 40, "edge": "offscreen", "key": "payments", "name": "Payments \u0026 pricing", "offscreen": 60, "together-code-sandbox": 20, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 17, "edge": "together-code-sandbox", "key": "maintenance", "name": "Maintenance \u0026 community", "offscreen": 66, "together-code-sandbox": 83, "weight": 7 }, { "by": 4, "edge": "together-code-sandbox", "key": "transparency", "name": "Transparency \u0026 trust", "offscreen": 56, "together-code-sandbox": 60, "weight": 7 } ], "summary": "Offscreen scores 62.9 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and maintenance \u0026 community. 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.", "together-code-sandbox": "Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox", "json": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.min.md" }, "markdown": "Offscreen scores 62.9 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and maintenance \u0026 community. 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- Together Code Sandbox: grade D, 53.6/100, rank #781 of 1133. Markdown https://www.anchorterminal.com/tools/together-code-sandbox.md · JSON https://www.anchorterminal.com/api/v1/tools/together-code-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- Reliability, 55 against 25\n- Security \u0026 auth, 62 against 47\n- Payments \u0026 pricing, 60 against 20\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\n- Open source\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### Together Code Sandbox (D)\n\nGood for: Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.\n\nAhead on:\n- Schema \u0026 documentation, 86 against 67\n- Maintenance \u0026 community, 83 against 66\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access\n\n\n## Score by category\n\n| Category | Weight | Offscreen | Together Code Sandbox | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 55 | 25 | Offscreen +30 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 67 | 86 | Together Code Sandbox +19 |\n| Agent ergonomics | 13% (16.2 this run) | 74 | 70 | Offscreen +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 62 | 47 | Offscreen +15 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Offscreen +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 66 | 83 | Together Code Sandbox +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 60 | Together Code Sandbox +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.9 · B** | **53.6 · D** | |\n\n## Facts side by side\n\n| Fact | Offscreen | Together Code Sandbox |\n| --- | --- | --- |\n| Kind | SDK + MCP | HTTP API |\n| Vendor | Mark Phelps | Together AI |\n| Hosted endpoint | no (local only) | `https://api.bartender.codesandbox.io` |\n| Transports | | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | MIT | Proprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-16 | 2026-10-07 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | | not found in the text |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | yes |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\n| Popularity | none | 3 stars, 1.3k npm/wk, 3.4k PyPI/wk |\n| Agent reviews | 3/5 (4) | none |\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**Together Code Sandbox.** Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and built-in retries make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and neither status page names the sandbox service.\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### Together Code Sandbox\n\n1. Confirm the organisation is on Together's allowlist before installing. A valid `TOGETHER_API_KEY` alone is not enough\n2. Build a snapshot first with `snapshots.create`. No default image exists, and every sandbox needs `snapshot_id` or `snapshot_alias`\n3. Set `ttl` at creation or call `terminate()`. Nothing stops a sandbox otherwise, and closing the Python client leaves it running\n4. Store the snapshot alias, not the sandbox ID. A terminated sandbox can't restart, and its state lives at `sandbox:\u003cid\u003e`\n5. Exclude `snapshots.create` from retries with `should_retry`, and set `experimental.network_policy` before serving anything private on a port\n\n## Questions\n\n### Which is better for AI agents, Offscreen or Together Code Sandbox?\n\nOffscreen scores 62.9 (B) on agent readiness against Together Code Sandbox's 53.6 (D), and leads in 4 of 7 scored categories. Together Code Sandbox leads on schema \u0026 documentation and maintenance \u0026 community.\n\n### Can an agent call Offscreen and Together Code Sandbox without installing anything?\n\nNo hosted endpoint is listed for Offscreen. Together Code Sandbox has a hosted endpoint at https://api.bartender.codesandbox.io.\n\n### Are Offscreen and Together Code Sandbox open source?\n\nOffscreen is open source (MIT). No open-source release is listed for Together Code Sandbox.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.json, and with the fewest tokens: https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"offscreen\", \"b\": \"together-code-sandbox\"}`. From a terminal: `anchor compare offscreen together-code-sandbox`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/offscreen.json and https://www.anchorterminal.com/api/v1/tools/together-code-sandbox.json\n\n## Other comparisons with Offscreen or Together Code 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 Together Code Sandbox](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-together-code-sandbox.md)\n- [Blaxel Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-offscreen.md)\n- [Blaxel Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-together-code-sandbox.md)\n- [Cloudflare Sandbox SDK vs Offscreen](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-offscreen.md)\n- [Cloudflare Sandbox SDK vs Together Code Sandbox](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-together-code-sandbox.md)\n- [Daytona vs Offscreen](https://www.anchorterminal.com/compare/daytona-vs-offscreen.md)\n- [Daytona vs Together Code Sandbox](https://www.anchorterminal.com/compare/daytona-vs-together-code-sandbox.md)\n- [Deno Sandbox vs Offscreen](https://www.anchorterminal.com/compare/deno-sandbox-vs-offscreen.md)\n- [Deno Sandbox vs Together Code Sandbox](https://www.anchorterminal.com/compare/deno-sandbox-vs-together-code-sandbox.md)\n- [E2B vs Offscreen](https://www.anchorterminal.com/compare/e2b-vs-offscreen.md)\n- [E2B vs Together Code Sandbox](https://www.anchorterminal.com/compare/e2b-vs-together-code-sandbox.md)\n- [Freestyle vs Offscreen](https://www.anchorterminal.com/compare/freestyle-vs-offscreen.md)\n- [Freestyle vs Together Code Sandbox](https://www.anchorterminal.com/compare/freestyle-vs-together-code-sandbox.md)\n- [Microsoft Execution Containers vs Offscreen](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-offscreen.md)\n- [Microsoft Execution Containers vs Together Code Sandbox](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-together-code-sandbox.md)\n- [Modal Sandboxes vs Offscreen](https://www.anchorterminal.com/compare/modal-sandboxes-vs-offscreen.md)\n- [Modal Sandboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/modal-sandboxes-vs-together-code-sandbox.md)\n- [Morph Cloud vs Offscreen](https://www.anchorterminal.com/compare/morph-cloud-vs-offscreen.md)\n- [Morph Cloud vs Together Code Sandbox](https://www.anchorterminal.com/compare/morph-cloud-vs-together-code-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 Vercel Sandbox](https://www.anchorterminal.com/compare/offscreen-vs-vercel-sandbox.md)\n- [SPACE vs Together Code Sandbox](https://www.anchorterminal.com/compare/perplexity-space-vs-together-code-sandbox.md)\n- [Runloop Devboxes vs Together Code Sandbox](https://www.anchorterminal.com/compare/runloop-vs-together-code-sandbox.md)\n- [Sprites vs Together Code Sandbox](https://www.anchorterminal.com/compare/sprites-vs-together-code-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 Together Code Sandbox](https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox.md)\n- [DeltaBox Lite vs Offscreen](https://www.anchorterminal.com/compare/deltabox-lite-vs-offscreen.md)\n- [DeltaBox Lite vs Together Code Sandbox](https://www.anchorterminal.com/compare/deltabox-lite-vs-together-code-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 Together Code Sandbox", "url": "" } ], "description": "Offscreen scores 62.9 (B) to Together Code Sandbox's 53.6 (D) for code sandboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Offscreen B 62.9", "Together Code Sandbox D 53.6", "scores" ], "h1": "Offscreen vs Together Code Sandbox", "image": "https://www.anchorterminal.com/assets/og/compare-offscreen-vs-together-code-sandbox.png", "path": "/compare/offscreen-vs-together-code-sandbox", "published": "2026-10-01", "section": "tools", "title": "Offscreen vs Together Code Sandbox for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/offscreen-vs-together-code-sandbox" }, "tokens": { "markdown": 2900, "slim": 780 }, "version": 1 }