{ "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", "dns": "agent37.grade.anchorterminal.com", "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 and creates an `sk_live_` key in the dashboard, or a program calls `POST /v1/signup` with no credentials and gets a workspace and its first key. Either way the full key is shown once, and no endpoint mints further keys. 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 or read-only keys 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 in the dashboard grants a one-time $5 credit with nothing charged; an account created through `POST /v1/signup` gets no credit. Top-ups are $5 to $10,000 through Stripe, from the dashboard or a Checkout link from `POST /v1/billing/top-up`. Managed model, search and integration calls bill at cost from the same balance (https://www.agent37.com/docs/agents-api/billing, checked 2026-11-05).", "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": null, "pypiWeekly": null, "asOf": "2026-11-05" }, "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": "2026-11-01", "graded": true, "anchor": { "graded": true, "score": 53.9, "grade": "D", "agentReady": false, "rank": 922, "ranked": true, "rankOf": 1486, "categoryRank": 19, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 65, "payments": 30, "reliability": 57, "schema": 57, "security": 48, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-05" }, "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. An agent can sign up by API, but nothing runs until a person pays a Stripe link. No OpenAPI file, SDK package or published rate limits were found.", "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 794 KB llms-full.txt and a Markdown copy of each of the 84 docs pages", "A status page with components for the API, sandbox creation, sandbox URLs and regions, and an unauthenticated signup endpoint that returns a key" ], "weaknesses": [ "The status page is new, with history only from October 2026, and the terms promise no uptime level", "No OpenAPI file, SDK package or public changelog was found. The Python client is one file to copy", "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 in the dashboard, and an account created by API must be funded through a Stripe Checkout link" ], "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", "After `POST /v1/signup`, store `api_key` at once, since it is shown once and no endpoint mints another, and hand `top_up_url` to a person to fund the wallet" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.9 } ], "editorialScores": { "ergonomics": 60, "maintenance": 65, "payments": 30, "reliability": 57, "schema": 57, "security": 48, "transparency": 56 }, "provenanceScore": 71, "checked": { "categories": { "ergonomics": "2026-11-05", "maintenance": "2026-11-05", "payments": "2026-11-05", "reliability": "2026-11-05", "schema": "2026-11-05", "security": "2026-11-05", "transparency": "2026-11-05" }, "last": "2026-11-05", "lastMoved": "2026-11-05", "oldest": "2026-11-05", "stale": false, "staleAfterDays": 90 } }, "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": "https://status.agent37.com/", "changelog": "", "securityTxt": "none", "checked": "2026-11-05", "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 returned 404 on 8 October 2026. The site footer has a Report abuse link and no disclosure policy was found.", "status.agent37.com, which returned 404 on 8 October 2026, is a Better Stack status page with component history on 5 November 2026. No changelog page was found.", "trust.agent37.com was readable on 5 November 2026 and lists SOC 2 and GDPR as in progress." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agent37.json", "live": { "slug": "agent37", "probe": { "target": "https://api.agent37.com/v1", "method": "get", "lastAt": "2026-11-07T18:20:08.66063893Z", "lastOk": true, "lastStatus": 404, "lastMs": 61, "authRequired": false, "uptime24h": 100, "uptime30d": 99.97, "p50ms24h": 68, "p95ms24h": 217, "samples24h": 239, "samples30d": 7463, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "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": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 246 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 248, "ok": 248 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 187, "ok": 187 } ] }, "vendorStatus": { "page": "https://status.agent37.com", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:47:04.5687349Z" }, "versions": [ { "registry": "npm", "name": "agent37", "version": "0.4.1", "seenAt": "2026-11-06T23:03:14.570610004Z" } ], "githubStars": 0, "npmWeekly": 336, "securityTxt": { "url": "https://agent37.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:38.734868485Z" }, "llmsTxt": { "url": "https://www.agent37.com/docs/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:05.753477142Z" }, "domain": { "domain": "agent37.com", "registered": "2025-04-29", "source": "https://rdap.verisign.com/com/v1/domain/agent37.com", "checkedAt": "2026-11-01T14:24:11.587268763Z" }, "pages": [ { "url": "https://www.agent37.com/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:24:21.584518595Z", "changedAt": "2026-11-05T13:08:24.456280942Z", "fingerprint": "77e6ffee1276" }, { "url": "https://www.agent37.com/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:24:23.773061538Z", "changedAt": "2026-11-05T13:08:26.71465785Z", "fingerprint": "2019838a1fbf" } ], "github": { "repo": "agent37-platform/templates", "checkedAt": "2026-11-02T08:28:38.554686143Z", "stars": 0, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-01T09:20:25Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 36, "ci": { "branch": "main", "runs": 36, "success": 36, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-11-01T09:11:55Z" } }, "updatedAt": "2026-11-07T18:20:08.66063893Z" } }, "answer": "Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category.", "b": { "slug": "celesto", "name": "Celesto (formerly SmolVM)", "vendor": "Celesto AI, Inc.", "vendorUrl": "https://celesto.ai", "kind": "sdk", "category": "code-sandboxes", "summary": "Celesto, formerly SmolVM, is an open-source Python SDK and CLI from Celesto AI that runs disposable Firecracker or QEMU microVMs on the owner's machine for agent code, browsers and desktops, with an optional paid Celesto Cloud.", "url": "https://www.anchorterminal.com/tools/celesto", "markdownUrl": "https://www.anchorterminal.com/tools/celesto.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/celesto.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/celesto.json", "dns": "celesto.grade.anchorterminal.com", "repo": "https://github.com/CelestoAI/Celesto", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "pypi", "name": "celesto" } ], "auth": "none", "authNotes": "Local use needs no account or key. The local API server and dashboard each require a bearer token, generated at start or read from CELESTO_SERVER_TOKEN and CELESTO_DASHBOARD_TOKEN. Celesto Cloud uses an organisation-bound CELESTO_API_KEY with named permissions (see, execute, delete) set in the dashboard.", "pricing": "freemium", "pricingNotes": "The local SDK and CLI are free under Apache-2.0. Celesto Cloud bills sandboxes by the running hour from $0.015 (Micro, 1 vCPU, 2 GB) to $0.16 (XL, 8 vCPU, 32 GB), prepaid from $2.01, with a one-time $5 Micro credit and no card.", "priceSummary": "$0.015 / session-hr", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the docs, llms.txt or the pricing page (checked 2026-11-06). Cloud runtime is prepaid by card under Settings \u003e Billing.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 1149, "npmWeekly": null, "pypiWeekly": 699, "asOf": "2026-11-06" }, "docsUrl": "https://celesto.ai/docs", "llmsTxt": "https://celesto.ai/llms.txt", "openapi": "https://github.com/CelestoAI/Celesto/blob/main/ts/celesto-local-server.openapi.json", "capabilities": [ "sandbox.code", "sandbox.fs", "sandbox.persist", "sandbox.browser" ], "tags": [ "open-source", "local", "self-hosted", "hosted", "freemium", "no-card", "free-tier", "apache-2.0", "python", "typescript", "cli", "microvm", "firecracker", "llms-txt", "openapi", "telemetry", "pre-1.0", "renamed" ], "lastRelease": "2026-11-05", "graded": true, "anchor": { "graded": true, "score": 68, "grade": "B", "agentReady": false, "rank": 298, "ranked": true, "rankOf": 1486, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 69, "maintenance": 81, "payments": 60, "reliability": 66, "schema": 85, "security": 52, "transparency": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "Celesto runs each agent task in a local Firecracker or QEMU microVM with its own kernel, driven by a CLI with a stable JSON envelope and a Python SDK, free under Apache-2.0. It is pre-1.0, renamed from SmolVM on 19 September 2026, sends usage telemetry after a first-use notice, and leaves outbound networking open unless a mode is set.", "bestFor": "Local microVM sandboxes for agent code, browsers and desktops on Linux and macOS, with a path to a hosted cloud.", "strengths": [ "Apache-2.0, installs from PyPI with `celesto setup` and `celesto doctor`, and runs local microVMs with no account or key", "Every `--json` response has the same `ok`, `command`, `exit_code`, `data` and `error` fields, with recovery commands in errors", "Network modes `off`, `public` (proxy that rejects private and metadata addresses) and `restricted` with CIDR or domain allowlists", "Dated changelog with Security sections, breaking changes marked, and 22 PyPI releases in the 90 days to 6 November 2026", "OpenAPI documents for the local server (24 operations) and the cloud API (171 operations) in the repository, plus llms.txt" ], "weaknesses": [ "Version 0.1.13 and declared pre-1.0 in SECURITY.md, with the TypeScript SDK an alpha installed from a GitHub tarball", "Outbound network access is open by default, and Linux TAP mode does not block every private network or metadata service", "Usage telemetry to PostHog is on after a first-use notice, until switched off", "Renamed from SmolVM on 19 September 2026 in a breaking release that removed the `smolvm` command and import path", "No security.txt, bug bounty or certification found, and CI results could not be read" ], "agentNotes": [ "Pass `--json` to every `celesto` command and branch on `ok` and `exit_code`, not on printed text", "Create computers with unique names and delete them by exact name when the job ends, including after failures", "Set `internet_settings={\"mode\": \"off\"}` or `restricted` for untrusted code, since the default is open", "Set CELESTO_NO_TELEMETRY=1 in unattended runs if usage events must not leave the machine", "Never paste browser or display connection URLs into model context; possession of the URL grants control" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 68 } ], "editorialScores": { "ergonomics": 69, "maintenance": 81, "payments": 60, "reliability": 66, "schema": 85, "security": 52, "transparency": 74 }, "provenanceScore": 66, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install celesto \u0026\u0026 celesto setup \u0026\u0026 celesto doctor", "headless": { "create": "celesto computer create --name agent-job --json", "delete": "celesto computer delete agent-job --json", "exec": "celesto computer exec agent-job --json -- python -m pytest" } }, "letme": { "capability": "https://letme.dev/sandbox.code", "tool": "https://letme.dev/celesto" }, "area": "agent-runtime", "unitPrices": [ { "item": "Cloud Micro sandbox (1 vCPU, 2 GB)", "unit": "session-hour", "usd": 0.015, "note": "Billed by the running hour; local use is free" }, { "item": "Cloud XL sandbox (8 vCPU, 32 GB)", "unit": "session-hour", "usd": 0.16, "note": "Largest size on the pricing page" } ], "provenance": { "legalEntity": "Celesto AI, Inc.", "domain": "celesto.ai", "domainRegistered": "2025-07-13", "endpointOnVendorDomain": null, "terms": "https://celesto.ai/legal/terms", "privacy": "https://celesto.ai/legal/privacy-policy", "statusPage": "", "changelog": "https://github.com/CelestoAI/Celesto/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "The privacy policy, last updated 30 October 2026, names Celesto AI, Inc., a Delaware corporation with a Wilmington mailing address. It has no clause on automated access.", "celesto.ai/robots.txt allows all crawlers. docs.celesto.ai carries Content-Signal ai-train=yes, search=yes, ai-input=yes.", "RDAP gives celesto.ai a registration date of 13 July 2025.", "/.well-known/security.txt returns 404. SECURITY.md asks for private reports through GitHub's vulnerability reporting. No status page is linked from the pricing page." ], "score": 66 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/celesto.json", "live": { "slug": "celesto", "versions": [ { "registry": "github", "name": "CelestoAI/Celesto", "version": "v0.1.13", "released": "2026-11-05", "seenAt": "2026-11-06T23:13:37.416837168Z" }, { "registry": "pypi", "name": "celesto", "version": "0.1.13", "released": "2026-11-05", "seenAt": "2026-11-06T23:13:37.309276304Z" } ], "githubStars": 1149, "pypiWeekly": 699, "securityTxt": { "url": "https://celesto.ai/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-07T16:01:01.176888246Z" }, "llmsTxt": { "url": "https://celesto.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:31:46.784166983Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/CelestoAI/Celesto/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:00.719411253Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8ddae4a6adbd" }, { "url": "https://celesto.ai/legal/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:00:50.868104256Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "87ce310b1db6" }, { "url": "https://celesto.ai/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:00:53.107282947Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1dece6f9a42e" } ], "updatedAt": "2026-11-07T16:01:01.176888246Z" } }, "edges": [ { "by": 30, "category": "payments", "leads": "celesto", "name": "Payments \u0026 pricing", "reasons": { "a": "No x402, MPP or L402 on the API (0). Per-unit prices for vCPU, memory and disk are published without login (20). The one-time $5 credit is granted only after a card is added in the dashboard, and accounts created by API get no credit, so there is no free tier without a card (0). `POST /v1/signup`, unauthenticated, now creates a workspace and returns a full API key and a Stripe Checkout link, and `POST /v1/billing/top-up` mints further links. Nothing runs until someone pays that link, so a person completes the step that makes access useful (10 of 20). Total 30.", "b": "Read with the self-hosted rule, scoring the hosted option for the price lines. No x402, MPP or L402 (0 of 40). Celesto Cloud publishes hourly prices for six sizes without a login (20). A one-time $5 Micro credit needs no card, and the local SDK is free (20). The graded local SDK installs from PyPI and runs with no account, so an agent needs no signup (20). Cloud use needs a browser signup and a card top-up. Total 60." }, "scores": { "a": 30, "b": 60 } }, { "by": 28, "category": "schema", "leads": "celesto", "name": "Schema \u0026 documentation", "reasons": { "a": "No OpenAPI or other machine-readable contract is shown or linked, and the 794 KB llms-full.txt never mentions one (0). llms.txt now lists 84 pages, with llms-full.txt and a Markdown copy of every page (10). Pages say what each call is for and when to choose another, such as stop against delete, resize against fork and exec for anything unwrapped (17). Parameters are documented with types, ranges, defaults and patterns in prose, with no schema to validate against (10). Curl, Python and JavaScript examples with responses on each page, and an error reference for the Hosting API, transport failures and the Agent API (15). The path is versioned at /v1 and template images carry immutable dated tags, but no public changelog was found (5). Total 57.", "b": "Read as an SDK and CLI. The repository ships an OpenAPI document for the local server (24 operations) and the cloud API (171 operations), from which the TypeScript client is generated (25). llms.txt at celesto.ai, plus Markdown docs in the repository (10). The README's runtime table says when to use each runtime, and the automation section says to prefer `exec` and keep `shell`, `ssh` and `desktop` for interactive work (14 of 20). Network modes are closed values (`open`, `off`, `public`, `restricted`) and the SDK takes typed keyword arguments, though `internet_settings` is a plain dict (11 of 15). Examples directory, a JSON envelope for every command and documented cloud error fields such as `required_scope`, without a full error catalogue (12 of 15). Dated changelog and tags, pre-1.0 (13 of 15). Total 85." }, "scores": { "a": 57, "b": 85 } }, { "by": 16, "category": "maintenance", "leads": "celesto", "name": "Maintenance \u0026 community", "reasons": { "a": "Scored on the closed-service scale. The newest template image tag is b2b-hermes/2026.11.01a (Hermes v0.22.5), four days before the check (30). The repository holds 77 dated image tags for the API's system templates (14 more are for the Personal Agents app), on 16 days from 2 October to 1 November 2026, each pushed by the publish script for a commit that names the change (20). No public changelog. Support is by email, a dashboard chat and a founder's booking link, and we couldn't read GitHub issues (5 of 15). No SDK library. The `agent37` CLI on npm was at 0.4.0 per the 8 October check, not re-read on 5 November, and `langchain-agent37` 0.1.0 was tagged on 26 October (5 of 15). The templates repository has a test workflow, whose results we couldn't read (5 of 10). Total 65.", "b": "0.1.13 on PyPI on 5 November 2026, tagged 6 November (30). 22 PyPI releases in the 90 days to 6 November (20). Most open issues are filed by maintainers. Outside reports such as the thread-safety issue got replies, and several recent ones have none yet; pull-request reply times were not read (15 of 25). The Python SDK is current, the TypeScript SDK is an alpha not published to npm (8 of 15). uv and Cargo lock files, CodeQL and publish workflows, with run results unread (8 of 10). Total 81." }, "scores": { "a": 65, "b": 81 } }, { "by": 9, "category": "reliability", "leads": "celesto", "name": "Reliability", "reasons": { "a": "Graded as a hosted service. A Better Stack status page now answers at status.agent37.com, with components for the website and dashboard, the API, sandbox creation, sandbox URLs and three regions (20). It did not exist on 8 October, when the host answered 404, so the record is short. Its feed lists two incidents, both partial: on 20 October fewer than 1 per cent of US sandboxes restarted (21 minutes degraded), and on 29 October some sandbox creations failed from 14:55 to 16:00 UTC while running sandboxes were not affected. A short record with minor incidents only (15). No request rate limits are published. The only numbers are one on-demand backup per instance every 15 minutes, three concurrent template builds and 20 feedback reports a day (0). Retry guidance is written per code, with backoff for `try_again`, `no_capacity` and 429, a `Retry-After` header on the backup limit, an idempotency key on budget top-ups and a warning that a timed-out exec keeps running, but instance create and exec take no idempotency key (12 of 15). The terms promise no uptime level unless agreed in writing (0). The Cloud API carries no beta label (10). Total 57.", "b": "Read with the local-software lines, because the graded surface runs on the owner's machine. Installs from PyPI as `celesto` with Python 3.11 or newer on Linux and macOS stated, plus an install script (20). The repository has pytest, e2e, lint, TypeScript and smoke-test workflows and 38 test packages, but GitHub's API answered with a rate limit, so no run result was read (15 of 25, unchecked). 22 open issues and pull requests against about 188 commits in 90 days. The open bugs include a snapshot restore that can lose a VM's disk if interrupted and a thread-safety issue with five replies (18 of 25). A dated changelog with Security, Fixed, Added and Removed sections, and the rename to Celesto marked as a breaking release, though versions stay below 1.0 (13 of 15). Pre-1.0 per SECURITY.md (0). Total 66." }, "scores": { "a": 57, "b": 66 } }, { "by": 9, "category": "ergonomics", "leads": "celesto", "name": "Agent ergonomics", "reasons": { "a": "Exec output is capped at 512 KB a stream with a `truncated` flag, logs take a `tail` and chat can return one JSON body instead of a stream, but there is no field selection and `GET /v1/instances` returns every full object (12). No pagination or filters were found on the instance, session or file lists. Usage and metrics take date or hour windows (8). Errors carry stable codes, with `param`, `hint` and `response_id` on the Agent API and a remedy per code (20). An idempotency key on budget top-ups, `X-Expected-Mtime` and `overwrite=false` on file writes and documented safe retries, with none on create or exec (12). An empty create body works and every field is optional. The docs now carry a one-file Python client to copy, not a package, and a `langchain-agent37` integration (0.1.0, 26 October), beside the CLI and raw HTTP examples (8). Total 60.", "b": "A CLI and SDK add no tool definitions to an agent's context. Collected command output is capped at 8 MiB with streaming as the alternative (18 of 25). `computer list`, `logs --follow` and name lookups, with little filtering (10 of 20). JSON errors carry a recovery command where Celesto has one, and cloud errors carry stable codes, operation and computer context and recovery fields since 0.1.7 (18 of 20). State-changing cloud requests are never replayed automatically and computers are addressed by unique names, but there are no idempotency keys (10 of 20). `with Computer()` creates and deletes a computer with no parameters, with Python and an alpha TypeScript SDK (13 of 15). Total 69." }, "scores": { "a": 60, "b": 69 } }, { "by": 6, "category": "transparency", "leads": "celesto", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service with dated terms (4 August 2026, re-read on 5 November). Template Dockerfiles and example apps are MIT and the CLI is Apache-2.0 (15). The privacy policy (1 September 2026) gives retention by category, seven days for a deleted instance's recovery copy, up to 30 days for request logs and about seven years for billing records, and the docs repeat the seven-day window. No DPA was found (22). One deprecation is documented, the Bearer header on instance URLs, with an email promised before removal and no date. No written policy (5). The policy names 12 kinds of third-party service and the docs say instances run on dedicated servers in the United States. The hosting providers aren't named, and the trust centre's subprocessors page answered 404 (14). Total 56.", "b": "Apache-2.0 in LICENSE and on PyPI (30). The privacy policy of 30 October 2026 links a subprocessor registry and describes the CLI telemetry in the same terms as the docs, but gives no retention periods beyond as long as necessary. Stopped cloud disks are kept 30 days per the pricing page (18 of 30). The changelog marks removals and the breaking rename, and the glossary lists older names still accepted, with no written deprecation policy (10 of 20). Telemetry is disclosed in the README, CLI reference and privacy policy, with three opt-outs, but it is on by default after the notice (16 of 20). Total 74." }, "scores": { "a": 64, "b": 70 } } ], "facts": [ { "a": "HTTP API", "b": "SDK + MCP", "name": "Kind" }, { "a": "Agent 37 Inc.", "b": "Celesto AI, Inc.", "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": "Freemium", "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": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-11-01", "b": "2026-11-05", "name": "Last release" }, { "a": "2026-08-04", "b": "2026-10-30", "name": "Terms last updated" }, { "a": "2026-09-01", "b": "2026-10-30", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "1.1k stars, 699 PyPI/wk", "name": "Popularity" }, { "a": "2.8/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category.", "question": "Which is better for AI agents, Agent 37 Cloud or Celesto (formerly SmolVM)?" }, { "answer": "Agent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Celesto (formerly SmolVM).", "question": "Can an agent call Agent 37 Cloud and Celesto (formerly SmolVM) without installing anything?" }, { "answer": "No open-source release is listed for Agent 37 Cloud. Celesto (formerly SmolVM) is open source (Apache-2.0).", "question": "Are Agent 37 Cloud and Celesto (formerly SmolVM) 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": "The status page is new, with history only from October 2026, and the terms promise no uptime level" }, { "aheadOn": [ "Reliability, 66 against 57", "Schema \u0026 documentation, 85 against 57", "Agent ergonomics, 69 against 60", "Payments \u0026 pricing, 60 against 30", "Maintenance \u0026 community, 81 against 65", "Transparency \u0026 trust, 70 against 64" ], "also": [ "No key needed to call it", "Free to start without a card", "Open source" ], "goodFor": "Local microVM sandboxes for agent code, browsers and desktops on Linux and macOS, with a path to a hosted cloud.", "slug": "celesto", "watchFor": "Version 0.1.13 and declared pre-1.0 in SECURITY.md, with the TypeScript SDK an alpha installed from a GitHub tarball" } ], "history": { "agent37": [ { "causes": [ "reliability", "product", "correction" ], "date": "2026-11-05", "delta": 7.6, "from": 46.3, "fromGrade": "D", "to": 53.9, "toGrade": "D" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 46.1, "fromGrade": "D", "to": 46.3, "toGrade": "D" } ], "celesto": null }, "job": { "capability": "sandbox.persist", "name": "Persistent sandboxes" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter.json", "title": "Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter", "url": "https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter" }, { "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-celesto.json", "title": "Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)", "url": "https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-celesto" }, { "json": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-celesto.json", "title": "Blaxel Sandboxes vs Celesto (formerly SmolVM)", "url": "https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-celesto" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-cloudflare-sandbox-sdk.json", "title": "Celesto (formerly SmolVM) vs Cloudflare Sandbox SDK", "url": "https://www.anchorterminal.com/compare/celesto-vs-cloudflare-sandbox-sdk" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-daytona.json", "title": "Celesto (formerly SmolVM) vs Daytona", "url": "https://www.anchorterminal.com/compare/celesto-vs-daytona" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-deltabox-lite.json", "title": "Celesto (formerly SmolVM) vs DeltaBox Lite", "url": "https://www.anchorterminal.com/compare/celesto-vs-deltabox-lite" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-deno-sandbox.json", "title": "Celesto (formerly SmolVM) vs Deno Sandbox", "url": "https://www.anchorterminal.com/compare/celesto-vs-deno-sandbox" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-e2b.json", "title": "Celesto (formerly SmolVM) vs E2B", "url": "https://www.anchorterminal.com/compare/celesto-vs-e2b" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-freestyle.json", "title": "Celesto (formerly SmolVM) vs Freestyle", "url": "https://www.anchorterminal.com/compare/celesto-vs-freestyle" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-instavm.json", "title": "Celesto (formerly SmolVM) vs InstaVM", "url": "https://www.anchorterminal.com/compare/celesto-vs-instavm" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-maritime.json", "title": "Celesto (formerly SmolVM) vs Maritime", "url": "https://www.anchorterminal.com/compare/celesto-vs-maritime" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-microsoft-execution-containers.json", "title": "Celesto (formerly SmolVM) vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/celesto-vs-microsoft-execution-containers" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-modal-sandboxes.json", "title": "Celesto (formerly SmolVM) vs Modal Sandboxes", "url": "https://www.anchorterminal.com/compare/celesto-vs-modal-sandboxes" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-morph-cloud.json", "title": "Celesto (formerly SmolVM) vs Morph Cloud", "url": "https://www.anchorterminal.com/compare/celesto-vs-morph-cloud" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-offscreen.json", "title": "Celesto (formerly SmolVM) vs Offscreen", "url": "https://www.anchorterminal.com/compare/celesto-vs-offscreen" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-perplexity-space.json", "title": "Celesto (formerly SmolVM) vs SPACE", "url": "https://www.anchorterminal.com/compare/celesto-vs-perplexity-space" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-runloop.json", "title": "Celesto (formerly SmolVM) vs Runloop Devboxes", "url": "https://www.anchorterminal.com/compare/celesto-vs-runloop" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-sandbox0.json", "title": "Celesto (formerly SmolVM) vs Sandbox0", "url": "https://www.anchorterminal.com/compare/celesto-vs-sandbox0" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-sprites.json", "title": "Celesto (formerly SmolVM) vs Sprites", "url": "https://www.anchorterminal.com/compare/celesto-vs-sprites" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-together-code-sandbox.json", "title": "Celesto (formerly SmolVM) vs Together Code Sandbox", "url": "https://www.anchorterminal.com/compare/celesto-vs-together-code-sandbox" }, { "json": "https://www.anchorterminal.com/compare/celesto-vs-vercel-sandbox.json", "title": "Celesto (formerly SmolVM) vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/celesto-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-deltabox-lite.json", "title": "Agent 37 Cloud vs DeltaBox Lite", "url": "https://www.anchorterminal.com/compare/agent37-vs-deltabox-lite" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-deno-sandbox.json", "title": "Agent 37 Cloud vs Deno Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-deno-sandbox" }, { "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-freestyle.json", "title": "Agent 37 Cloud vs Freestyle", "url": "https://www.anchorterminal.com/compare/agent37-vs-freestyle" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-instavm.json", "title": "Agent 37 Cloud vs InstaVM", "url": "https://www.anchorterminal.com/compare/agent37-vs-instavm" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-maritime.json", "title": "Agent 37 Cloud vs Maritime", "url": "https://www.anchorterminal.com/compare/agent37-vs-maritime" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.json", "title": "Agent 37 Cloud vs Microsoft Execution Containers", "url": "https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers" }, { "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-perplexity-space.json", "title": "Agent 37 Cloud vs SPACE", "url": "https://www.anchorterminal.com/compare/agent37-vs-perplexity-space" }, { "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-sandbox0.json", "title": "Agent 37 Cloud vs Sandbox0", "url": "https://www.anchorterminal.com/compare/agent37-vs-sandbox0" }, { "json": "https://www.anchorterminal.com/compare/agent37-vs-sprites.json", "title": "Agent 37 Cloud vs Sprites", "url": "https://www.anchorterminal.com/compare/agent37-vs-sprites" }, { "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/agent37-vs-vercel-sandbox.json", "title": "Agent 37 Cloud vs Vercel Sandbox", "url": "https://www.anchorterminal.com/compare/agent37-vs-vercel-sandbox" } ], "panel": null, "scores": [ { "agent37": 57, "by": 9, "celesto": 66, "edge": "celesto", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agent37": 57, "by": 28, "celesto": 85, "edge": "celesto", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "agent37": 60, "by": 9, "celesto": 69, "edge": "celesto", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "agent37": 48, "by": 4, "celesto": 52, "edge": "celesto", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "agent37": 30, "by": 30, "celesto": 60, "edge": "celesto", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agent37": 65, "by": 16, "celesto": 81, "edge": "celesto", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "agent37": 64, "by": 6, "celesto": 70, "edge": "celesto", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category. Both do persistent sandboxes.", "tasks": null, "tutorials": [], "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. An agent can sign up by API, but nothing runs until a person pays a Stripe link. No OpenAPI file, SDK package or published rate limits were found.", "celesto": "Celesto runs each agent task in a local Firecracker or QEMU microVM with its own kernel, driven by a CLI with a stable JSON envelope and a Python SDK, free under Apache-2.0. It is pre-1.0, renamed from SmolVM on 19 September 2026, sends usage telemetry after a first-use notice, and leaves outbound networking open unless a mode is set." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agent37-vs-celesto", "json": "https://www.anchorterminal.com/compare/agent37-vs-celesto.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agent37-vs-celesto.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/agent37-vs-celesto.min.md" }, "markdown": "Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category. Both do persistent sandboxes.\n\n- Agent 37 Cloud: grade D, 53.9/100, rank #922 of 1486. Markdown https://www.anchorterminal.com/tools/agent37.md · JSON https://www.anchorterminal.com/api/v1/tools/agent37.json\n- Celesto (formerly SmolVM): grade B, 68/100, rank #298 of 1486. Markdown https://www.anchorterminal.com/tools/celesto.md · JSON https://www.anchorterminal.com/api/v1/tools/celesto.json\n- Best code execution sandboxes for AI agents: https://www.anchorterminal.com/best/code-sandboxes/index.md\n- All 231 sandboxes comparisons: https://www.anchorterminal.com/compare/code-sandboxes/index.md\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: The status page is new, with history only from October 2026, and the terms promise no uptime level\n\n### Celesto (formerly SmolVM) (B)\n\nGood for: Local microVM sandboxes for agent code, browsers and desktops on Linux and macOS, with a path to a hosted cloud.\n\nAhead on:\n- Reliability, 66 against 57\n- Schema \u0026 documentation, 85 against 57\n- Agent ergonomics, 69 against 60\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 81 against 65\n- Transparency \u0026 trust, 70 against 64\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: Version 0.1.13 and declared pre-1.0 in SECURITY.md, with the TypeScript SDK an alpha installed from a GitHub tarball\n\n\n## Why the edge\n\n### Payments \u0026 pricing: Celesto (formerly SmolVM) +30\n\n- Agent 37 Cloud (30): No x402, MPP or L402 on the API (0). Per-unit prices for vCPU, memory and disk are published without login (20). The one-time $5 credit is granted only after a card is added in the dashboard, and accounts created by API get no credit, so there is no free tier without a card (0). `POST /v1/signup`, unauthenticated, now creates a workspace and returns a full API key and a Stripe Checkout link, and `POST /v1/billing/top-up` mints further links. Nothing runs until someone pays that link, so a person completes the step that makes access useful (10 of 20). Total 30.\n- Celesto (formerly SmolVM) (60): Read with the self-hosted rule, scoring the hosted option for the price lines. No x402, MPP or L402 (0 of 40). Celesto Cloud publishes hourly prices for six sizes without a login (20). A one-time $5 Micro credit needs no card, and the local SDK is free (20). The graded local SDK installs from PyPI and runs with no account, so an agent needs no signup (20). Cloud use needs a browser signup and a card top-up. Total 60.\n\n### Schema \u0026 documentation: Celesto (formerly SmolVM) +28\n\n- Agent 37 Cloud (57): No OpenAPI or other machine-readable contract is shown or linked, and the 794 KB llms-full.txt never mentions one (0). llms.txt now lists 84 pages, with llms-full.txt and a Markdown copy of every page (10). Pages say what each call is for and when to choose another, such as stop against delete, resize against fork and exec for anything unwrapped (17). Parameters are documented with types, ranges, defaults and patterns in prose, with no schema to validate against (10). Curl, Python and JavaScript examples with responses on each page, and an error reference for the Hosting API, transport failures and the Agent API (15). The path is versioned at /v1 and template images carry immutable dated tags, but no public changelog was found (5). Total 57.\n- Celesto (formerly SmolVM) (85): Read as an SDK and CLI. The repository ships an OpenAPI document for the local server (24 operations) and the cloud API (171 operations), from which the TypeScript client is generated (25). llms.txt at celesto.ai, plus Markdown docs in the repository (10). The README's runtime table says when to use each runtime, and the automation section says to prefer `exec` and keep `shell`, `ssh` and `desktop` for interactive work (14 of 20). Network modes are closed values (`open`, `off`, `public`, `restricted`) and the SDK takes typed keyword arguments, though `internet_settings` is a plain dict (11 of 15). Examples directory, a JSON envelope for every command and documented cloud error fields such as `required_scope`, without a full error catalogue (12 of 15). Dated changelog and tags, pre-1.0 (13 of 15). Total 85.\n\n### Maintenance \u0026 community: Celesto (formerly SmolVM) +16\n\n- Agent 37 Cloud (65): Scored on the closed-service scale. The newest template image tag is b2b-hermes/2026.11.01a (Hermes v0.22.5), four days before the check (30). The repository holds 77 dated image tags for the API's system templates (14 more are for the Personal Agents app), on 16 days from 2 October to 1 November 2026, each pushed by the publish script for a commit that names the change (20). No public changelog. Support is by email, a dashboard chat and a founder's booking link, and we couldn't read GitHub issues (5 of 15). No SDK library. The `agent37` CLI on npm was at 0.4.0 per the 8 October check, not re-read on 5 November, and `langchain-agent37` 0.1.0 was tagged on 26 October (5 of 15). The templates repository has a test workflow, whose results we couldn't read (5 of 10). Total 65.\n- Celesto (formerly SmolVM) (81): 0.1.13 on PyPI on 5 November 2026, tagged 6 November (30). 22 PyPI releases in the 90 days to 6 November (20). Most open issues are filed by maintainers. Outside reports such as the thread-safety issue got replies, and several recent ones have none yet; pull-request reply times were not read (15 of 25). The Python SDK is current, the TypeScript SDK is an alpha not published to npm (8 of 15). uv and Cargo lock files, CodeQL and publish workflows, with run results unread (8 of 10). Total 81.\n\n### Reliability: Celesto (formerly SmolVM) +9\n\n- Agent 37 Cloud (57): Graded as a hosted service. A Better Stack status page now answers at status.agent37.com, with components for the website and dashboard, the API, sandbox creation, sandbox URLs and three regions (20). It did not exist on 8 October, when the host answered 404, so the record is short. Its feed lists two incidents, both partial: on 20 October fewer than 1 per cent of US sandboxes restarted (21 minutes degraded), and on 29 October some sandbox creations failed from 14:55 to 16:00 UTC while running sandboxes were not affected. A short record with minor incidents only (15). No request rate limits are published. The only numbers are one on-demand backup per instance every 15 minutes, three concurrent template builds and 20 feedback reports a day (0). Retry guidance is written per code, with backoff for `try_again`, `no_capacity` and 429, a `Retry-After` header on the backup limit, an idempotency key on budget top-ups and a warning that a timed-out exec keeps running, but instance create and exec take no idempotency key (12 of 15). The terms promise no uptime level unless agreed in writing (0). The Cloud API carries no beta label (10). Total 57.\n- Celesto (formerly SmolVM) (66): Read with the local-software lines, because the graded surface runs on the owner's machine. Installs from PyPI as `celesto` with Python 3.11 or newer on Linux and macOS stated, plus an install script (20). The repository has pytest, e2e, lint, TypeScript and smoke-test workflows and 38 test packages, but GitHub's API answered with a rate limit, so no run result was read (15 of 25, unchecked). 22 open issues and pull requests against about 188 commits in 90 days. The open bugs include a snapshot restore that can lose a VM's disk if interrupted and a thread-safety issue with five replies (18 of 25). A dated changelog with Security, Fixed, Added and Removed sections, and the rename to Celesto marked as a breaking release, though versions stay below 1.0 (13 of 15). Pre-1.0 per SECURITY.md (0). Total 66.\n\n### Agent ergonomics: Celesto (formerly SmolVM) +9\n\n- Agent 37 Cloud (60): Exec output is capped at 512 KB a stream with a `truncated` flag, logs take a `tail` and chat can return one JSON body instead of a stream, but there is no field selection and `GET /v1/instances` returns every full object (12). No pagination or filters were found on the instance, session or file lists. Usage and metrics take date or hour windows (8). Errors carry stable codes, with `param`, `hint` and `response_id` on the Agent API and a remedy per code (20). An idempotency key on budget top-ups, `X-Expected-Mtime` and `overwrite=false` on file writes and documented safe retries, with none on create or exec (12). An empty create body works and every field is optional. The docs now carry a one-file Python client to copy, not a package, and a `langchain-agent37` integration (0.1.0, 26 October), beside the CLI and raw HTTP examples (8). Total 60.\n- Celesto (formerly SmolVM) (69): A CLI and SDK add no tool definitions to an agent's context. Collected command output is capped at 8 MiB with streaming as the alternative (18 of 25). `computer list`, `logs --follow` and name lookups, with little filtering (10 of 20). JSON errors carry a recovery command where Celesto has one, and cloud errors carry stable codes, operation and computer context and recovery fields since 0.1.7 (18 of 20). State-changing cloud requests are never replayed automatically and computers are addressed by unique names, but there are no idempotency keys (10 of 20). `with Computer()` creates and deletes a computer with no parameters, with Python and an alpha TypeScript SDK (13 of 15). Total 69.\n\n### Transparency \u0026 trust: Celesto (formerly SmolVM) +6\n\n- Agent 37 Cloud (64): Closed service with dated terms (4 August 2026, re-read on 5 November). Template Dockerfiles and example apps are MIT and the CLI is Apache-2.0 (15). The privacy policy (1 September 2026) gives retention by category, seven days for a deleted instance's recovery copy, up to 30 days for request logs and about seven years for billing records, and the docs repeat the seven-day window. No DPA was found (22). One deprecation is documented, the Bearer header on instance URLs, with an email promised before removal and no date. No written policy (5). The policy names 12 kinds of third-party service and the docs say instances run on dedicated servers in the United States. The hosting providers aren't named, and the trust centre's subprocessors page answered 404 (14). Total 56.\n- Celesto (formerly SmolVM) (70): Apache-2.0 in LICENSE and on PyPI (30). The privacy policy of 30 October 2026 links a subprocessor registry and describes the CLI telemetry in the same terms as the docs, but gives no retention periods beyond as long as necessary. Stopped cloud disks are kept 30 days per the pricing page (18 of 30). The changelog marks removals and the breaking rename, and the glossary lists older names still accepted, with no written deprecation policy (10 of 20). Telemetry is disclosed in the README, CLI reference and privacy policy, with three opt-outs, but it is on by default after the notice (16 of 20). Total 74.\n\n## Score by category\n\n| Category | Weight | Agent 37 Cloud | Celesto (formerly SmolVM) | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 57 | 66 | Celesto (formerly SmolVM) +9 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 57 | 85 | Celesto (formerly SmolVM) +28 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 69 | Celesto (formerly SmolVM) +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 48 | 52 | Celesto (formerly SmolVM) +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | Celesto (formerly SmolVM) +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 65 | 81 | Celesto (formerly SmolVM) +16 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 70 | Celesto (formerly SmolVM) +6 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **53.9 · D** | **68 · B** | |\n\n## Facts side by side\n\n| Fact | Agent 37 Cloud | Celesto (formerly SmolVM) |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | Agent 37 Inc. | Celesto AI, Inc. |\n| Hosted endpoint | `https://api.agent37.com/v1` | no (local only) |\n| Transports | HTTP | |\n| Auth | API key | None |\n| Pricing | Pay per use | Freemium |\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 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-11-01 | 2026-11-05 |\n| Terms last updated | 2026-08-04 | 2026-10-30 |\n| Privacy policy last updated | 2026-09-01 | 2026-10-30 |\n| Customer content may train models | not found in the text | not found in the text |\n| Terms restrict automated access | not found in the text | not found in the text |\n| Terms restrict benchmarking | not found in the text | not found in the text |\n| Terms or service can change without notice | not found in the text | not found in the text |\n| Arbitration or class-action waiver | not found in the text | not found in the text |\n| Popularity | none | 1.1k stars, 699 PyPI/wk |\n| Agent reviews | 2.8/5 (4) | none |\n\n## How the scores have moved\n\n### Agent 37 Cloud\n\n- +7.6 on 5 November 2026: reliability, product, correction\n- +0.2 on 27 October 2026: checklist\n\n### Celesto (formerly SmolVM)\n\nNo score change since it was listed.\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. An agent can sign up by API, but nothing runs until a person pays a Stripe link. No OpenAPI file, SDK package or published rate limits were found.\n\n**Celesto (formerly SmolVM).** Celesto runs each agent task in a local Firecracker or QEMU microVM with its own kernel, driven by a CLI with a stable JSON envelope and a Python SDK, free under Apache-2.0. It is pre-1.0, renamed from SmolVM on 19 September 2026, sends usage telemetry after a first-use notice, and leaves outbound networking open unless a mode is set.\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. After `POST /v1/signup`, store `api_key` at once, since it is shown once and no endpoint mints another, and hand `top_up_url` to a person to fund the wallet\n\n### Celesto (formerly SmolVM)\n\n1. Pass `--json` to every `celesto` command and branch on `ok` and `exit_code`, not on printed text\n2. Create computers with unique names and delete them by exact name when the job ends, including after failures\n3. Set `internet_settings={\"mode\": \"off\"}` or `restricted` for untrusted code, since the default is open\n4. Set CELESTO_NO_TELEMETRY=1 in unattended runs if usage events must not leave the machine\n5. Never paste browser or display connection URLs into model context; possession of the URL grants control\n\n## Questions\n\n### Which is better for AI agents, Agent 37 Cloud or Celesto (formerly SmolVM)?\n\nCelesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category.\n\n### Can an agent call Agent 37 Cloud and Celesto (formerly SmolVM) without installing anything?\n\nAgent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Celesto (formerly SmolVM).\n\n### Are Agent 37 Cloud and Celesto (formerly SmolVM) open source?\n\nNo open-source release is listed for Agent 37 Cloud. Celesto (formerly SmolVM) is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agent37-vs-celesto.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agent37-vs-celesto.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agent37\", \"b\": \"celesto\"}`. From a terminal: `anchor compare agent37 celesto`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agent37.json and https://www.anchorterminal.com/api/v1/tools/celesto.json\n\n## Other comparisons with Agent 37 Cloud or Celesto (formerly SmolVM)\n\n- [Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter](https://www.anchorterminal.com/compare/agent37-vs-agentcore-code-interpreter.md)\n- [Agent 37 Cloud vs Offscreen](https://www.anchorterminal.com/compare/agent37-vs-offscreen.md)\n- [Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)](https://www.anchorterminal.com/compare/agentcore-code-interpreter-vs-celesto.md)\n- [Blaxel Sandboxes vs Celesto (formerly SmolVM)](https://www.anchorterminal.com/compare/blaxel-sandboxes-vs-celesto.md)\n- [Celesto (formerly SmolVM) vs Cloudflare Sandbox SDK](https://www.anchorterminal.com/compare/celesto-vs-cloudflare-sandbox-sdk.md)\n- [Celesto (formerly SmolVM) vs Daytona](https://www.anchorterminal.com/compare/celesto-vs-daytona.md)\n- [Celesto (formerly SmolVM) vs DeltaBox Lite](https://www.anchorterminal.com/compare/celesto-vs-deltabox-lite.md)\n- [Celesto (formerly SmolVM) vs Deno Sandbox](https://www.anchorterminal.com/compare/celesto-vs-deno-sandbox.md)\n- [Celesto (formerly SmolVM) vs E2B](https://www.anchorterminal.com/compare/celesto-vs-e2b.md)\n- [Celesto (formerly SmolVM) vs Freestyle](https://www.anchorterminal.com/compare/celesto-vs-freestyle.md)\n- [Celesto (formerly SmolVM) vs InstaVM](https://www.anchorterminal.com/compare/celesto-vs-instavm.md)\n- [Celesto (formerly SmolVM) vs Maritime](https://www.anchorterminal.com/compare/celesto-vs-maritime.md)\n- [Celesto (formerly SmolVM) vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/celesto-vs-microsoft-execution-containers.md)\n- [Celesto (formerly SmolVM) vs Modal Sandboxes](https://www.anchorterminal.com/compare/celesto-vs-modal-sandboxes.md)\n- [Celesto (formerly SmolVM) vs Morph Cloud](https://www.anchorterminal.com/compare/celesto-vs-morph-cloud.md)\n- [Celesto (formerly SmolVM) vs Offscreen](https://www.anchorterminal.com/compare/celesto-vs-offscreen.md)\n- [Celesto (formerly SmolVM) vs SPACE](https://www.anchorterminal.com/compare/celesto-vs-perplexity-space.md)\n- [Celesto (formerly SmolVM) vs Runloop Devboxes](https://www.anchorterminal.com/compare/celesto-vs-runloop.md)\n- [Celesto (formerly SmolVM) vs Sandbox0](https://www.anchorterminal.com/compare/celesto-vs-sandbox0.md)\n- [Celesto (formerly SmolVM) vs Sprites](https://www.anchorterminal.com/compare/celesto-vs-sprites.md)\n- [Celesto (formerly SmolVM) vs Together Code Sandbox](https://www.anchorterminal.com/compare/celesto-vs-together-code-sandbox.md)\n- [Celesto (formerly SmolVM) vs Vercel Sandbox](https://www.anchorterminal.com/compare/celesto-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 DeltaBox Lite](https://www.anchorterminal.com/compare/agent37-vs-deltabox-lite.md)\n- [Agent 37 Cloud vs Deno Sandbox](https://www.anchorterminal.com/compare/agent37-vs-deno-sandbox.md)\n- [Agent 37 Cloud vs E2B](https://www.anchorterminal.com/compare/agent37-vs-e2b.md)\n- [Agent 37 Cloud vs Freestyle](https://www.anchorterminal.com/compare/agent37-vs-freestyle.md)\n- [Agent 37 Cloud vs InstaVM](https://www.anchorterminal.com/compare/agent37-vs-instavm.md)\n- [Agent 37 Cloud vs Maritime](https://www.anchorterminal.com/compare/agent37-vs-maritime.md)\n- [Agent 37 Cloud vs Microsoft Execution Containers](https://www.anchorterminal.com/compare/agent37-vs-microsoft-execution-containers.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 SPACE](https://www.anchorterminal.com/compare/agent37-vs-perplexity-space.md)\n- [Agent 37 Cloud vs Runloop Devboxes](https://www.anchorterminal.com/compare/agent37-vs-runloop.md)\n- [Agent 37 Cloud vs Sandbox0](https://www.anchorterminal.com/compare/agent37-vs-sandbox0.md)\n- [Agent 37 Cloud vs Sprites](https://www.anchorterminal.com/compare/agent37-vs-sprites.md)\n- [Agent 37 Cloud vs Together Code Sandbox](https://www.anchorterminal.com/compare/agent37-vs-together-code-sandbox.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)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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": "Agent 37 Cloud vs Celesto (formerly SmolVM)", "url": "" } ], "description": "Celesto scores 68 (B) to Agent 37 Cloud's 53.9 (D) for persistent sandboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Agent 37 Cloud D 53.9", "Celesto (formerly SmolVM) B 68", "scores" ], "h1": "Agent 37 Cloud vs Celesto (formerly SmolVM)", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/agent37-vs-celesto", "published": "2026-10-01", "section": "tools", "title": "Agent 37 Cloud vs Celesto for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/agent37-vs-celesto" }, "tokens": { "markdown": 5500, "slim": 2980 }, "version": 1 }