Head to head · Persistent sandboxes · October 2026 research run
Agent 37 Cloud vs Celesto (formerly SmolVM)
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.
Best code execution sandboxes for AI agents · All 231 sandboxes comparisons
Which one, for what
Best 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.
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
The status page is new, with history only from October 2026, and the terms promise no uptime level
Best for Local microVM sandboxes for agent code, browsers and desktops on Linux and macOS, with a path to a hosted cloud.
Ahead on
- Reliability, 66 against 57
- Schema & documentation, 85 against 57
- Agent ergonomics, 69 against 60
- Payments & pricing, 60 against 30
- Maintenance & community, 81 against 65
- Transparency & trust, 70 against 64
Also in its favour
- No key needed to call it
- Free to start without a card
- Open source
Watch for
Version 0.1.13 and declared pre-1.0 in SECURITY.md, with the TypeScript SDK an alpha installed from a GitHub tarball
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Celesto (formerly SmolVM) +30
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.
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.
Schema & documentation Celesto (formerly SmolVM) +28
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.
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.
Maintenance & community Celesto (formerly SmolVM) +16
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.
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.
Reliability Celesto (formerly SmolVM) +9
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.
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.
Agent ergonomics Celesto (formerly SmolVM) +9
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.
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.
Transparency & trust Celesto (formerly SmolVM) +6
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.
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.
Score by category
| Category | Weight this run | Agent 37 Cloud | Celesto (formerly SmolVM) | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 57 | 66 | Celesto (formerly SmolVM) +9 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 57 | 85 | Celesto (formerly SmolVM) +28 |
| Agent ergonomics | 13%16.2 | 60 | 69 | Celesto (formerly SmolVM) +9 |
| Security & auth | 14%17.5 | 48 | 52 | Celesto (formerly SmolVM) +4 |
| Payments & pricing | 10%12.5 | 30 | 60 | Celesto (formerly SmolVM) +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 65 | 81 | Celesto (formerly SmolVM) +16 |
| Transparency & trust | 7%8.8 | 64 | 70 | Celesto (formerly SmolVM) +6 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 53.9/100 | B 68/100 |
Facts side by side
| Fact | Agent 37 Cloud | Celesto (formerly SmolVM) |
|---|---|---|
| Kind | HTTP API | SDK + MCP |
| Vendor | Agent 37 Inc. | Celesto AI, Inc. |
| Hosted endpoint | https://api.agent37.com/v1 | no (local only) |
| Transports | HTTP | |
| Auth | API key | None |
| Pricing | Pay per use | Freemium |
| x402 | no | no |
| 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 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-01 | 2026-11-05 |
| Terms last updated | 2026-08-04 | 2026-10-30 |
| Privacy policy last updated | 2026-09-01 | 2026-10-30 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | none | 1.1k stars, 699 PyPI/wk |
| Agent reviews | 2.8/5 (4) | none |
How the scores have moved
Celesto (formerly SmolVM)
No score change since it was listed.
Verdicts
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.
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.
Before you call either
Agent 37 Cloud
- Send the key as
Authorization: Bearerto api.agent37.com and asX-Agent37-Keyto the instance URL. The Bearer form on instance URLs is deprecated - Poll
GET /v1/healthon the instance URL for"healthy": truebefore the first message.status: runningonly means the machine is up - Check whether
erroris a string before readingerror.code. Transport errors are flat strings, and a failed turn returns 200 withstatus: "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, storeapi_keyat once, since it is shown once and no endpoint mints another, and handtop_up_urlto a person to fund the wallet
Celesto (formerly SmolVM)
- Pass
--jsonto everycelestocommand and branch onokandexit_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"}orrestrictedfor 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
Questions
Which is better for AI agents, Agent 37 Cloud or Celesto (formerly SmolVM)?
Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Agent 37 Cloud's 53.9 (D), and leads in every scored category.
Can an agent call Agent 37 Cloud and Celesto (formerly SmolVM) without installing anything?
Agent 37 Cloud has a hosted endpoint at https://api.agent37.com/v1. No hosted endpoint is listed for Celesto (formerly SmolVM).
Are Agent 37 Cloud and Celesto (formerly SmolVM) open source?
No open-source release is listed for Agent 37 Cloud. Celesto (formerly SmolVM) is open source (Apache-2.0).
Other comparisons with Agent 37 Cloud or Celesto (formerly SmolVM)
- Agent 37 Cloud vs Amazon Bedrock AgentCore Code Interpreter
- Agent 37 Cloud vs Offscreen
- Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)
- Blaxel Sandboxes vs Celesto (formerly SmolVM)
- Celesto (formerly SmolVM) vs Cloudflare Sandbox SDK
- Celesto (formerly SmolVM) vs Daytona
- Celesto (formerly SmolVM) vs DeltaBox Lite
- Celesto (formerly SmolVM) vs Deno Sandbox
- Celesto (formerly SmolVM) vs E2B
- Celesto (formerly SmolVM) vs Freestyle
- Celesto (formerly SmolVM) vs InstaVM
- Celesto (formerly SmolVM) vs Maritime
- Celesto (formerly SmolVM) vs Microsoft Execution Containers
- Celesto (formerly SmolVM) vs Modal Sandboxes
- Celesto (formerly SmolVM) vs Morph Cloud
- Celesto (formerly SmolVM) vs Offscreen
- Celesto (formerly SmolVM) vs SPACE
- Celesto (formerly SmolVM) vs Runloop Devboxes
- Celesto (formerly SmolVM) vs Sandbox0
- Celesto (formerly SmolVM) vs Sprites
- Celesto (formerly SmolVM) vs Together Code Sandbox
- Celesto (formerly SmolVM) vs Vercel Sandbox
- Agent 37 Cloud vs Blaxel Sandboxes
- Agent 37 Cloud vs Cloudflare Sandbox SDK
- Agent 37 Cloud vs Daytona
- Agent 37 Cloud vs DeltaBox Lite
- Agent 37 Cloud vs Deno Sandbox
- Agent 37 Cloud vs E2B
- Agent 37 Cloud vs Freestyle
- Agent 37 Cloud vs InstaVM
- Agent 37 Cloud vs Maritime
- Agent 37 Cloud vs Microsoft Execution Containers
- Agent 37 Cloud vs Modal Sandboxes
- Agent 37 Cloud vs Morph Cloud
- Agent 37 Cloud vs SPACE
- Agent 37 Cloud vs Runloop Devboxes
- Agent 37 Cloud vs Sandbox0
- Agent 37 Cloud vs Sprites
- Agent 37 Cloud vs Together Code Sandbox
- Agent 37 Cloud vs Vercel Sandbox
Machine-readable
- This page as Markdown
/compare/agent37-vs-celesto.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/agent37.json·/api/v1/tools/celesto.json - From a terminal
anchor compare agent37 celesto(the CLI) - Over MCP
compare_tools {"a": "agent37", "b": "celesto"}at/mcp, no key