{ "data": { "a": { "slug": "agent37", "name": "Agent 37 Cloud", "vendor": "Agent 37 Inc.", "vendorUrl": "https://www.agent37.com/cloud", "kind": "http-api", "category": "code-sandboxes", "summary": "Agent 37 Cloud hosts persistent Linux sandboxes for agent harnesses such as Hermes, OpenClaw, Claude Code and Codex, or a custom Docker image. A REST API creates instances, runs commands, manages files and sends messages to the agent inside.", "url": "https://www.anchorterminal.com/tools/agent37", "markdownUrl": "https://www.anchorterminal.com/tools/agent37.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agent37.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agent37.json", "repo": "https://github.com/agent37-platform/templates", "license": "Proprietary service under Agent 37's terms of service. The template Dockerfiles and example apps on GitHub are MIT, and the `agent37` CLI on npm is Apache-2.0", "transports": [ "http" ], "remoteUrl": "https://api.agent37.com/v1", "packages": [ { "registry": "npm", "name": "agent37" } ], "auth": "api-key", "authNotes": "Self-serve. A person signs up, adds a card and creates an `sk_live_` key in the dashboard, where the full key is shown once. The key is workspace-wide and goes in `Authorization: Bearer` on https://api.agent37.com/v1 and in the `X-Agent37-Key` header on each instance URL. A key can carry an IP allowlist of up to 20 addresses or CIDR ranges. No scopes, read-only keys or key-creation API were found. Browsers reach an instance port through a signed URL that lasts 60 seconds to seven days and can't be revoked.", "pricing": "usage", "pricingNotes": "Prepaid balance, metered per minute. $0.80 a vCPU-month, $0.70 a GB-month of memory and $0.09 a GB-month of disk on a 730-hour month, so 2 vCPU and 4 GB with a 4 GB disk is $4.76 a month running and $0.36 a month asleep or stopped. Performance instances on dedicated cores cost four times the compute rate. Adding a card grants a one-time $5 credit with nothing charged, limited to one 2 vCPU, 4 GB instance until the first top-up. Top-ups are $5 to $10,000 through Stripe, and automatic top-up is on by default after the first one. Managed model, search and integration calls bill at cost from the same balance (https://www.agent37.com/docs/agents-api/billing, checked 2026-10-08).", "priceSummary": "$0.0011 / vCPU-hr", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs (llms-full.txt), the pricing page or the terms (checked 2026-10-08). The wallet is topped up by card through Stripe in the dashboard.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 74, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://www.agent37.com/docs", "llmsTxt": "https://www.agent37.com/docs/llms.txt", "capabilities": [ "sandbox.persist", "sandbox.code", "sandbox.fs", "sandbox.browser" ], "tags": [ "hosted", "usage", "llms-txt", "cli", "docker", "yc", "new" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 46.1, "grade": "D", "agentReady": false, "rank": 564, "ranked": true, "rankOf": 629, "categoryRank": 10, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 65, "payments": 20, "reliability": 27, "schema": 57, "security": 49, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "Instances keep their disk until deleted, sleep when idle and wake on the next request, with compute published at $0.80 a vCPU-month and stable error codes on both APIs. The product launched on 29 September 2026. No status page, OpenAPI file, SDK library or published rate limits were found, and the starter credit needs a card.", "bestFor": "A product that gives each end user a long-lived agent machine that is idle most of the day and needs a harness preinstalled.", "strengths": [ "Disk persists until delete, and auto-sleep checkpoints an idle instance so that only disk bills ($0.09 a GB-month)", "Per-unit prices are public. A 2 vCPU, 4 GB instance running all month is $4.76, metered per minute", "Stable error codes on both APIs, with `param` and `hint` fields and written retry guidance for each transient code", "llms.txt, a 637 KB llms-full.txt and a Markdown copy of each of the 49 docs pages", "API keys take an IP allowlist of up to 20 addresses or ranges, and each instance has its own managed-spend cap" ], "weaknesses": [ "No status page was found. status.agent37.com returns 404, and the terms promise no uptime level", "No OpenAPI file, SDK library or public changelog was found. The npm package `agent37` is a CLI", "No API rate limits are published beyond one on-demand backup per instance every 15 minutes", "One workspace-wide key controls every instance. No scopes or read-only keys were found", "The $5 starter credit needs a card on file, and keys and top-ups exist only in the dashboard", "The launch is dated 29 September 2026 and the public templates repository starts on 2 October 2026" ], "agentNotes": [ "Send the key as `Authorization: Bearer` to api.agent37.com and as `X-Agent37-Key` to the instance URL. The Bearer form on instance URLs is deprecated", "Poll `GET /v1/health` on the instance URL for `\"healthy\": true` before the first message. `status: running` only means the machine is up", "Check whether `error` is a string before reading `error.code`. Transport errors are flat strings, and a failed turn returns 200 with `status: \"failed\"`", "Don't blindly retry an exec that timed out after 13 minutes. The command keeps running, so a retry starts a second copy", "Set `auto_sleep: true`, keep anything that must survive a sleep in a file, and allow a first-byte timeout of three minutes for wakes" ], "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": 46.1 } ], "editorialScores": { "ergonomics": 60, "maintenance": 65, "payments": 20, "reliability": 27, "schema": 57, "security": 49, "transparency": 56 }, "provenanceScore": 56 }, "connect": { "http": "curl -X POST https://api.agent37.com/v1/instances \\\n -H \"Authorization: Bearer sk_live_...\" \\\n -H \"Content-Type: application/json\" \\\n -d '{ \"budget\": { \"credit_micros\": 1000000 } }'" }, "letme": { "capability": "https://letme.dev/sandbox.persist", "tool": "https://letme.dev/agent37" }, "area": "agent-runtime", "unitPrices": [ { "item": "vCPU", "unit": "vcpu-hour", "usd": 0.001096, "note": "$0.80 a vCPU-month over 730 hours. Memory extra at $0.70 a GB-month, and Performance instances cost four times the compute rate" }, { "item": "Default instance (2 vCPU, 4 GB, 4 GB disk)", "unit": "session-hour", "usd": 0.00652, "note": "$4.76 a month running, metered per minute. $0.36 a month asleep or stopped" }, { "item": "Disk", "unit": "gb-month", "usd": 0.09, "note": "Billed until the instance is deleted. $0.03 a GB-month on compressed bytes once parked in cold storage" } ], "provenance": { "legalEntity": "Agent 37 Inc.", "domain": "agent37.com", "domainRegistered": "2025-04-29", "endpointOnVendorDomain": true, "terms": "https://www.agent37.com/terms", "privacy": "https://www.agent37.com/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms (last updated 4 August 2026) name Agent 37 Inc. under New York law. The privacy policy (last updated 1 September 2026) names Agent 37 Inc. and, in its representative section, Agent37.com Inc.", "The Hosting API answers at api.agent37.com and instances at {id}.agent37.app, a second domain the docs describe as the vendor's.", "www.agent37.com/.well-known/security.txt returns 404. The site footer has a Report abuse link and no disclosure policy was found.", "status.agent37.com returns 404 (deployment not found) and no status page is linked from the site or docs. No changelog page was found.", "RDAP for agent37.com gives a registration date of 2025-04-29 and NameCheap, Inc. as registrar.", "trust.agent37.com answered 403 to our reader, so the trust centre is unread." ], "score": 56 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agent37.json", "live": { "slug": "agent37", "probe": { "target": "https://api.agent37.com/v1", "method": "get", "lastAt": "2026-10-08T18:20:23.772016566Z", "lastOk": true, "lastStatus": 404, "lastMs": 85, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 83, "p95ms24h": 364, "samples24h": 33, "samples30d": 33, "days": [ { "date": "2026-10-08", "probes": 33, "ok": 33 } ] }, "versions": [ { "registry": "npm", "name": "agent37", "version": "0.4.0", "seenAt": "2026-10-08T15:56:42.792052264Z" } ], "githubStars": 0, "npmWeekly": 74, "securityTxt": { "url": "https://agent37.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:33.079951688Z" }, "updatedAt": "2026-10-08T18:20:23.772016566Z" } }, "answer": "Microsoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category.", "b": { "slug": "microsoft-execution-containers", "name": "Microsoft Execution Containers", "vendor": "Microsoft", "vendorUrl": "https://github.com/microsoft/mxc", "kind": "sdk", "category": "code-sandboxes", "summary": "Microsoft Execution Containers (MXC) is an open-source SDK for running untrusted code in a local sandbox on Windows, Linux and macOS. An application embeds it through Node.js, .NET or Rust and sets filesystem, network and UI policy for each run.", "url": "https://www.anchorterminal.com/tools/microsoft-execution-containers", "markdownUrl": "https://www.anchorterminal.com/tools/microsoft-execution-containers.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/microsoft-execution-containers.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/microsoft-execution-containers.json", "repo": "https://github.com/microsoft/mxc", "license": "MIT", "transports": [], "packages": [ { "registry": "npm", "name": "@microsoft/mxc-sdk" }, { "registry": "nuget", "name": "Microsoft.Mxc.Sdk" } ], "auth": "none", "authNotes": "No account, key or sign-in. MXC is a library the host application loads in its own process, so it holds no credential of its own. The workload runs with whatever the request grants. Network egress, ingress and host loopback resolve to `deny` when omitted, and filesystem access is limited to the `readonlyPaths` and `readwritePaths` the caller lists. On Windows the `isolation_session` backend creates a separate agent user account for each container and returns its name and SID.", "pricing": "free", "pricingNotes": "Free. The SDKs and native runtime are MIT and install from npm, NuGet and crates.io with no account or card. There is no hosted service and nothing to buy. Compute is the owner's own machine. The Windows backends need Windows 11 at the builds listed in the repository (checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, the docs or the SDK source. Local open-source software with no paid endpoint (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1506, "npmWeekly": 471674, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://github.com/microsoft/mxc/blob/main/docs/api-reference/README.md", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist" ], "tags": [ "sdk", "open-source", "local", "free", "no-auth", "no-card", "typescript", "dotnet", "rust", "windows", "linux", "macos", "json-schema", "new-1.0" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 76.3, "grade": "BB", "agentReady": true, "rank": 34, "ranked": true, "rankOf": 629, "categoryRank": 1, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 74, "maintenance": 92, "payments": 60, "reliability": 81, "schema": 81, "security": 69, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "MXC puts nine operating-system sandbox backends behind one typed request, with network access denied by default and a JSON Schema for the stable 1.0.0 contract. Version 1.0.0 is two days old as of 8 October 2026. Enforcement varies by backend, and `isolation_session` cannot restrict networking at all.", "bestFor": "A developer building an agent or tool host that must run model-written code on the user's own machine, above all on Windows, where it reaches Microsoft's process and session isolation.", "strengths": [ "MIT licence, with SDKs for Node.js, .NET and Rust all at 1.0.0 and the native runtime bundled in the npm and NuGet packages", "Egress, ingress and host loopback default to `deny`, and filesystem access is limited to listed read-only and read-write paths", "A draft-07 JSON Schema for the stable 1.0.0 request, with descriptions on 135 of 150 properties", "Errors carry one of 12 typed codes plus an optional remediation, and `validate*` calls dry-run a request without creating a container", "Telemetry is opt-in, Windows-only and gated on user consent and an administrative policy that can only block it" ], "weaknesses": [ "1.0.0 shipped on 6 October 2026, and the Node changelog still lists the V1 changes under Unreleased", "Enforcement differs by backend. `isolation_session` cannot restrict networking, and proxy routing is cooperative on Seatbelt and WSLC", "Persistent containers exist only for `isolation_session` and `wslc`, both on Windows", "On Windows the Node SDK runs a PATH-resolved `whoami` at import, reported on 24 September 2026 and still open", "The npm package is 37.7 MB compressed, needs Node.js 24 or later, and carries no `repository` field or provenance attestation" ], "agentNotes": [ "Import from `@microsoft/mxc-sdk/v1`. The package root exports nothing.", "Call `getPlatformSupport()` first and stop if `isSupported` is false. `getAvailableBackends()` is advisory and launch-time validation still applies.", "Set `network.egress.default` to `allow` only when the task needs it. Omitted network policy resolves to deny in every direction.", "Never pass `--audit` to an executor for untrusted code. It turns off all sandbox security for the workload.", "Read `ExecutionResult.warnings` after each run. Security warnings arrive there and are not written to stdout or stderr." ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 76.3 } ], "editorialScores": { "ergonomics": 74, "maintenance": 92, "payments": 60, "reliability": 81, "schema": 81, "security": 69, "transparency": 86 }, "provenanceScore": 79 }, "connect": { "install": "npm install @microsoft/mxc-sdk" }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/microsoft-execution-containers" }, "sameCompany": [ "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-speech-to-text", "azure-text-to-speech", "microsoft-agent-framework", "microsoft-entra-agent-id", "azure-key-vault", "azure-devops-mcp", "microsoft-learn-mcp", "playwright-mcp", "azure-mcp", "azure-translator", "microsoft-graph-calendar", "dynamics-365-sales", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph" ], "area": "agent-runtime", "provenance": { "legalEntity": "Microsoft Corporation", "domain": "microsoft.com", "domainRegistered": "1991-05-02", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://go.microsoft.com/fwlink/?linkid=521839", "statusPage": "", "changelog": "https://github.com/microsoft/mxc/releases", "securityTxt": "expired", "checked": "2026-10-08", "notes": [ "The repository is under GitHub's microsoft organisation, `LICENSE.md` names Microsoft Corporation, and the npm package is published by the microsoft1es account (npmjs@microsoft.com).", "www.microsoft.com/.well-known/security.txt loads and points to the MSRC researcher portal, but its Expires field is 2026-09-23T16:00:00.000Z, which had passed on 8 October 2026.", "RDAP for microsoft.com gives a registration date of 1991-05-02.", "No terms page applies to the open-source SDK beyond the MIT licence. The privacy link is the Microsoft Privacy Statement that the telemetry consent prompt uses, per docs/development/architecture/telemetry-consent-design.md.", "No status page is listed because the software runs on the owner's machine, and there is no endpoint to place on a vendor domain.", "https://learn.microsoft.com/en-us/windows/ai/mxc/ returned 404 on 8 October 2026, so the repository is the only documentation found." ], "score": 79 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-execution-containers.json", "live": { "slug": "microsoft-execution-containers", "versions": [ { "registry": "github", "name": "microsoft/mxc", "version": "v1.0.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:20:44.186904887Z" }, { "registry": "npm", "name": "@microsoft/mxc-sdk", "version": "1.0.0", "seenAt": "2026-10-08T16:20:42.947200785Z" } ], "githubStars": 1580, "npmWeekly": 471674, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "expired", "expires": "2026-09-23T16:00:00.000Z", "checkedAt": "2026-10-08T15:39:08.216544687Z" }, "pages": [ { "url": "https://go.microsoft.com/fwlink/?linkid=521839", "kind": "privacy", "status": 0, "checkedAt": "2026-10-08T18:20:40.027295892Z", "changedAt": "0001-01-01T00:00:00Z", "blockedByRobots": true } ], "updatedAt": "2026-10-08T18:20:40.027295892Z" } }, "facts": [ { "a": "HTTP API", "b": "SDK + MCP", "name": "Kind" }, { "a": "Agent 37 Inc.", "b": "Microsoft", "name": "Vendor" }, { "a": "https://api.agent37.com/v1", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary service under Agent 37's terms of service. The template Dockerfiles and example apps on GitHub are MIT, and the `agent37` CLI on npm is Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-05", "b": "2026-10-06", "name": "Last release" }, { "a": "2026-08-04", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-09-01", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "74 npm/wk", "b": "1.5k stars, 472k npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "Microsoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category.", "question": "Which is better for AI agents, Agent 37 Cloud or Microsoft Execution Containers?" }, { "answer": "Agent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Microsoft Execution Containers.", "question": "Can an agent call Agent 37 Cloud and Microsoft Execution Containers without installing anything?" }, { "answer": "No open-source release is listed for Agent 37 Cloud. Microsoft Execution Containers is open source (MIT).", "question": "Are Agent 37 Cloud and Microsoft Execution Containers open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "A product that gives each end user a long-lived agent machine that is idle most of the day and needs a harness preinstalled.", "slug": "agent37", "watchFor": "No status page was found. status.agent37.com returns 404, and the terms promise no uptime level" }, { "aheadOn": [ "Reliability, 81 against 27", "Schema \u0026 documentation, 81 against 57", "Agent ergonomics, 74 against 60", "Security \u0026 auth, 69 against 49", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 92 against 65", "Transparency \u0026 trust, 83 against 56" ], "also": [ "Agent-ready, a grade of BB or better", "No key needed to call it", "Free to start without a card", "Open source" ], "goodFor": "A developer building an agent or tool host that must run model-written code on the user's own machine, above all on Windows, where it reaches Microsoft's process and session isolation.", "slug": "microsoft-execution-containers", "watchFor": "1.0.0 shipped on 6 October 2026, and the Node changelog still lists the V1 changes under Unreleased" } ], "job": { "capability": "sandbox.persist", "name": "Sandbox persist" }, "others": [ { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-microsoft-execution-containers.json", "title": "Blaxel Sandboxes vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-microsoft-execution-containers" }, { "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/daytona-vs-microsoft-execution-containers.json", "title": "Daytona vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/daytona-vs-microsoft-execution-containers" }, { "json": "https://www.anchorterminal.com/compare/e2b-vs-microsoft-execution-containers.json", "title": "E2B vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/e2b-vs-microsoft-execution-containers" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-modal-sandboxes.json", "title": "Microsoft Execution Containers vs Modal Sandboxes", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-modal-sandboxes" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-morph-cloud.json", "title": "Microsoft Execution Containers vs Morph Cloud", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-morph-cloud" }, { "json": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-runloop.json", "title": "Microsoft Execution Containers vs Runloop Devboxes", "url": "https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-runloop" }, { "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/agent37-vs-blaxel-sandboxes.json", "title": "Agent 37 Cloud vs Blaxel Sandboxes", "url": "https://www.anchorterminal.com/compare/agent37-vs-blaxel-sandboxes" }, { "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/agent37-vs-daytona.json", "title": "Agent 37 Cloud vs Daytona", "url": "https://www.anchorterminal.com/compare/agent37-vs-daytona" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-e2b.json", "title": "Agent 37 Cloud vs E2B", "url": "https://www.anchorterminal.com/compare/agent37-vs-e2b" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-modal-sandboxes.json", "title": "Agent 37 Cloud vs Modal Sandboxes", "url": "https://www.anchorterminal.com/compare/agent37-vs-modal-sandboxes" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-morph-cloud.json", "title": "Agent 37 Cloud vs Morph Cloud", "url": "https://www.anchorterminal.com/compare/agent37-vs-morph-cloud" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-runloop.json", "title": "Agent 37 Cloud vs Runloop Devboxes", "url": "https://www.anchorterminal.com/compare/agent37-vs-runloop" }, { "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" } ], "scores": [ { "agent37": 27, "by": 54, "edge": "microsoft-execution-containers", "key": "reliability", "microsoft-execution-containers": 81, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agent37": 57, "by": 24, "edge": "microsoft-execution-containers", "key": "schema", "microsoft-execution-containers": 81, "name": "Schema \u0026 documentation", "weight": 13 }, { "agent37": 60, "by": 14, "edge": "microsoft-execution-containers", "key": "ergonomics", "microsoft-execution-containers": 74, "name": "Agent ergonomics", "weight": 13 }, { "agent37": 49, "by": 20, "edge": "microsoft-execution-containers", "key": "security", "microsoft-execution-containers": 69, "name": "Security \u0026 auth", "weight": 14 }, { "agent37": 20, "by": 40, "edge": "microsoft-execution-containers", "key": "payments", "microsoft-execution-containers": 60, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agent37": 65, "by": 27, "edge": "microsoft-execution-containers", "key": "maintenance", "microsoft-execution-containers": 92, "name": "Maintenance \u0026 community", "weight": 7 }, { "agent37": 56, "by": 27, "edge": "microsoft-execution-containers", "key": "transparency", "microsoft-execution-containers": 83, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Microsoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category. Both do sandbox persist.", "verdicts": { "agent37": "Instances keep their disk until deleted, sleep when idle and wake on the next request, with compute published at $0.80 a vCPU-month and stable error codes on both APIs. The product launched on 29 September 2026. No status page, OpenAPI file, SDK library or published rate limits were found, and the starter credit needs a card.", "microsoft-execution-containers": "MXC puts nine operating-system sandbox backends behind one typed request, with network access denied by default and a JSON Schema for the stable 1.0.0 contract. Version 1.0.0 is two days old as of 8 October 2026. Enforcement varies by backend, and `isolation_session` cannot restrict networking at all." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers", "json": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.md", "slim": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.min.md" }, "markdown": "Microsoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category. Both do sandbox persist.\n\n- Agent 37 Cloud: grade D, 46.1/100, rank #564 of 629. Markdown https://www.anchorterminal.com/tools/agent37.md · JSON https://www.anchorterminal.com/api/v1/tools/agent37.json\n- Microsoft Execution Containers: grade BB, 76.3/100, rank #34 of 629. Markdown https://www.anchorterminal.com/tools/microsoft-execution-containers.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-execution-containers.json\n\n## Which one, for what\n\n### Agent 37 Cloud (D)\n\nGood for: A product that gives each end user a long-lived agent machine that is idle most of the day and needs a harness preinstalled.\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: No status page was found. status.agent37.com returns 404, and the terms promise no uptime level\n\n### Microsoft Execution Containers (BB)\n\nGood for: A developer building an agent or tool host that must run model-written code on the user's own machine, above all on Windows, where it reaches Microsoft's process and session isolation.\n\nAhead on:\n- Reliability, 81 against 27\n- Schema \u0026 documentation, 81 against 57\n- Agent ergonomics, 74 against 60\n- Security \u0026 auth, 69 against 49\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 92 against 65\n- Transparency \u0026 trust, 83 against 56\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- No key needed to call it\n- Free to start without a card\n- Open source\n\nWatch for: 1.0.0 shipped on 6 October 2026, and the Node changelog still lists the V1 changes under Unreleased\n\n\n## Score by category\n\n| Category | Weight | Agent 37 Cloud | Microsoft Execution Containers | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 27 | 81 | Microsoft Execution Containers +54 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 57 | 81 | Microsoft Execution Containers +24 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 74 | Microsoft Execution Containers +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 49 | 69 | Microsoft Execution Containers +20 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | Microsoft Execution Containers +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 92 | Microsoft Execution Containers +27 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 56 | 83 | Microsoft Execution Containers +27 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **46.1 · D** | **76.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Agent 37 Cloud | Microsoft Execution Containers |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | Agent 37 Inc. | Microsoft |\n| Hosted endpoint | `https://api.agent37.com/v1` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | Proprietary service under Agent 37's terms of service. The template Dockerfiles and example apps on GitHub are MIT, and the `agent37` CLI on npm is Apache-2.0 | MIT |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | no |\n| Last release | 2026-10-05 | 2026-10-06 |\n| Terms last updated | 2026-08-04 | no document linked |\n| Privacy policy last updated | 2026-09-01 | couldn't be read |\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 | not found in the text | |\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 | 74 npm/wk | 1.5k stars, 472k npm/wk |\n\n## Verdicts\n\n**Agent 37 Cloud.** Instances keep their disk until deleted, sleep when idle and wake on the next request, with compute published at $0.80 a vCPU-month and stable error codes on both APIs. The product launched on 29 September 2026. No status page, OpenAPI file, SDK library or published rate limits were found, and the starter credit needs a card.\n\n**Microsoft Execution Containers.** MXC puts nine operating-system sandbox backends behind one typed request, with network access denied by default and a JSON Schema for the stable 1.0.0 contract. Version 1.0.0 is two days old as of 8 October 2026. Enforcement varies by backend, and `isolation_session` cannot restrict networking at all.\n\n## Before you call either\n\n### Agent 37 Cloud\n\n1. Send the key as `Authorization: Bearer` to api.agent37.com and as `X-Agent37-Key` to the instance URL. The Bearer form on instance URLs is deprecated\n2. Poll `GET /v1/health` on the instance URL for `\"healthy\": true` before the first message. `status: running` only means the machine is up\n3. Check whether `error` is a string before reading `error.code`. Transport errors are flat strings, and a failed turn returns 200 with `status: \"failed\"`\n4. Don't blindly retry an exec that timed out after 13 minutes. The command keeps running, so a retry starts a second copy\n5. Set `auto_sleep: true`, keep anything that must survive a sleep in a file, and allow a first-byte timeout of three minutes for wakes\n\n### Microsoft Execution Containers\n\n1. Import from `@microsoft/mxc-sdk/v1`. The package root exports nothing.\n2. Call `getPlatformSupport()` first and stop if `isSupported` is false. `getAvailableBackends()` is advisory and launch-time validation still applies.\n3. Set `network.egress.default` to `allow` only when the task needs it. Omitted network policy resolves to deny in every direction.\n4. Never pass `--audit` to an executor for untrusted code. It turns off all sandbox security for the workload.\n5. Read `ExecutionResult.warnings` after each run. Security warnings arrive there and are not written to stdout or stderr.\n\n## Questions\n\n### Which is better for AI agents, Agent 37 Cloud or Microsoft Execution Containers?\n\nMicrosoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category.\n\n### Can an agent call Agent 37 Cloud and Microsoft Execution Containers without installing anything?\n\nAgent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Microsoft Execution Containers.\n\n### Are Agent 37 Cloud and Microsoft Execution Containers open source?\n\nNo open-source release is listed for Agent 37 Cloud. Microsoft Execution Containers is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent37\", \"b\": \"microsoft-execution-containers\"}`. From a terminal: `anchor compare agent37 microsoft-execution-containers`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent37.json and https://www.anchorterminal.com/api/v1/tools/microsoft-execution-containers.json\n\n## Other comparisons with Agent 37 Cloud or Microsoft Execution Containers\n\n- [Blaxel Sandboxes vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-microsoft-execution-containers.md)\n- [Cloudflare Sandbox SDK vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/cloudflare-sandbox-sdk-vs-microsoft-execution-containers.md)\n- [Daytona vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/daytona-vs-microsoft-execution-containers.md)\n- [E2B vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/e2b-vs-microsoft-execution-containers.md)\n- [Microsoft Execution Containers vs Modal Sandboxes](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-modal-sandboxes.md)\n- [Microsoft Execution Containers vs Morph Cloud](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-morph-cloud.md)\n- [Microsoft Execution Containers vs Runloop Devboxes](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-runloop.md)\n- [Microsoft Execution Containers vs Vercel Sandbox](https://www.anchorterminal.com/compare/microsoft-execution-containers-vs-vercel-sandbox.md)\n- [Agent 37 Cloud vs Blaxel Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-blaxel-sandboxes.md)\n- [Agent 37 Cloud vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/agent37-vs-cloudflare-sandbox-sdk.md)\n- [Agent 37 Cloud vs Daytona](https://www.anchorterminal.com/compare/agent37-vs-daytona.md)\n- [Agent 37 Cloud vs E2B](https://www.anchorterminal.com/compare/agent37-vs-e2b.md)\n- [Agent 37 Cloud vs Modal Sandboxes](https://www.anchorterminal.com/compare/agent37-vs-modal-sandboxes.md)\n- [Agent 37 Cloud vs Morph Cloud](https://www.anchorterminal.com/compare/agent37-vs-morph-cloud.md)\n- [Agent 37 Cloud vs Runloop Devboxes](https://www.anchorterminal.com/compare/agent37-vs-runloop.md)\n- [Agent 37 Cloud vs Vercel Sandbox](https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Agent 37 Cloud vs Microsoft Execution Containers", "url": "" } ], "description": "Microsoft Execution Containers scores 76.3 (BB) on agent readiness against Agent 37 Cloud's 46.1 (D), and leads in every scored category. Both do sandbox persist. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Agent 37 Cloud D 46.1", "Microsoft Execution Containers BB 76.3", "scores" ], "h1": "Agent 37 Cloud vs Microsoft Execution Containers", "image": "https://www.anchorterminal.com/assets/og/compare-agent37-vs-microsoft-execution-containers.png", "path": "/compare/agent37-vs-microsoft-execution-containers", "published": "2026-10-01", "section": "tools", "title": "Agent 37 Cloud vs Microsoft Execution Containers for AI agents", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers" }, "tokens": { "markdown": 2500, "slim": 780 }, "version": 1 }