Head to head · Code sandboxes · October 2026 research run
Celesto (formerly SmolVM) vs Sandbox0
Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Sandbox0's 55.4 (C), and leads in 5 of 7 scored categories. Sandbox0 leads on agent ergonomics and security & auth. Both do code sandboxes.
Best code execution sandboxes for AI agents · All 231 sandboxes comparisons
Which one, for what
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 37
- Schema & documentation, 85 against 77
- Payments & pricing, 60 against 20
- Maintenance & community, 81 against 76
- Transparency & trust, 70 against 47
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
Sandbox0 C
Best for Products that give each end user a long-lived Linux machine whose installed software and files persist between tasks, paying only for running memory.
Ahead on
- Agent ergonomics, 74 against 69
- Security & auth, 58 against 52
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
No status page, incident history or SLA found
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) +40
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.
Sandbox0 20
No x402, MPP or L402 in the docs, llms.txt or the OpenAPI file (0 of 40). Per-unit prices published without a login, $0.015 per GiB-hour of compute billed by the second and $0.02 per GiB-month of retained incremental storage, with network and object-store requests at $0.00 for now (20). The one-time $5 welcome credit now needs a saved card. The pricing page asks whether a card is needed for the welcome credit, answers yes and says the credit follows Stripe confirming a saved card, where on 21 October it needed none (0). Signup and the first s0 auth login are a device login a person approves in a browser. Keys can be minted by API afterwards, but only from an existing session or key (0). 0 + 20 + 0 + 0 = 20.
Reliability Celesto (formerly SmolVM) +29
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.
Sandbox0 37
Graded with the hosted lines, on Sandbox0 Cloud only. No status page found. sandbox0.ai/status answers 404, status.sandbox0.ai doesn't resolve, and none is linked from the site, llms.txt or docs (0, re-read 4 November). No readable incident history (5). Default quotas are published with numbers, 20 running sandboxes, unlimited paused sandboxes, 5 claims a second and 100 API requests a second per team, burst 200 (15). Quota failures return 429 with error.code quota_exceeded, claims carry Retry-After, and the OpenAPI file documents Idempotency-Key on pause, resume, restart, fork, snapshot capture and restore, sessions and template creation, with the docs saying to retry the same resize on 503. The core write, POST /api/v1/sandboxes (claim), which starts a billed sandbox and is the listing's own example call, takes no key, and the keys on pause and resume apply only to their conditional memory forms. That is safe-retry guidance without idempotency keys on the core write (12; the 21 October 13 isn't a checklist value). The terms provide the service as is and no SLA is published (0). The core sandbox API carries no beta label, but memory checkpoints and live migration are called experimental, the OpenAPI file is version 0.1.0 and the SDKs are 0.10.x (5 of 10, the 21 October partial kept). 0 + 5 + 15 + 12 + 0 + 5 = 37.
Transparency & trust Celesto (formerly SmolVM) +23
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.
Sandbox0 47
The hosted service is closed under clear, dated terms naming Lougao, LLC and Delaware law. The SDKs and CLI are Apache-2.0, and the earlier runtime stays Apache-2.0 as an unmaintained archive that no longer matches the service (18 of 30). The privacy policy (effective 17 June 2026, re-read 4 November) says what is collected, that customer content is processed only to run the service and that no advertising cookies are used, but retention is "as long as needed" with no periods, and no DPA was found (12 of 30). No deprecation policy. The terms say parts of the service may be changed or discontinued, and self-hosting ended on 16 October 2026 with no notice found before that day. The deployment page now dates the end clearly (3 of 20). Data location is stated (U.S. infrastructure, one U.S. East region), but service providers are described by kind only and not named (8 of 20).
Schema & documentation Celesto (formerly SmolVM) +8
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.
Sandbox0 77
OpenAPI 3.0.3 file with 106 paths and 145 operations, the same file in each SDK repository and the archived runtime. It isn't linked from the docs or served on sandbox0.ai, so an agent has to find it on GitHub (20 of 25). llms.txt and every docs page as raw Markdown at a .md address (10). Docs say when to use each lifecycle and context type, and 884 descriptions in the spec explain fields, but the pages are long and mix in internal architecture such as ctld, Nomad and PostgreSQL leases (16 of 20). 106 enums and 386 required lists in the spec; the error details field is free-form (13 of 15). Examples in Go, Python, TypeScript and CLI on every guide, but only two examples in the spec. Error responses are typed as a {code, message, details} envelope per status, with a few codes named in the docs (11 of 15). API paths are /api/v1 and the SDKs and CLI publish GitHub releases with commit lists, but there's no public changelog page; /changelog answers 404 (7 of 15).
Security & auth Sandbox0 +6
Celesto (formerly SmolVM) 52
Framework reading for local software. No credential is needed for local use, and the local API server and dashboard each require a bearer token, and cloud keys carry named permissions (22 of 30). Each computer has its own guest kernel, browser and display access uses capability URLs with a read-only option, and raw VNC is off. Against that, outbound networking is open by default and the restricting modes are opt-in (12 of 20). The security doc warns against giving connection URLs to a model as page content, but there is no guidance on treating command or page output as untrusted (5 of 15). computer logs shows startup output, with no audit log of commands (5 of 15). SECURITY.md with GitHub private vulnerability reporting and a supported-versions table, Security sections in the changelog, no security.txt, bug bounty or certification (8 of 20). Total 52.
Sandbox0 58
Bearer API keys scoped to a team, with roles admin, developer, builder and viewer that can't exceed the caller's, expiry of 30 to 365 days or never, deactivation and an introspection route. No OAuth for API clients found (25 of 30). The viewer role gives a read-only key. Network policy can block all egress, allow and deny by rule, and allow or deny named MCP tool calls, and cloud metadata endpoints are blocked under any policy. No confirmation step for destructive calls (14 of 20). Sandboxes return output of code the agent runs. Credential sources are injected by the egress proxy so raw secrets stay out of the sandbox, but no guidance on treating sandbox output as untrusted was found (8 of 15). Historical logs and runtime metrics per sandbox; the signed audit event ledger needs the enterprise sandbox_audit feature, and network audit is optional (8 of 15). No security.txt (404), no security page (404), no bug bounty, no certification and no published advisories (OSV lists none for sandbox0 on 4 November). Security reports go to contact@sandbox0.ai per the archived runtime's SUPPORT.md, and the s0 install script downloads a release without verifying a checksum (2 of 20).
Agent ergonomics Sandbox0 +5
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.
Sandbox0 74
Graded on the REST API and SDKs. Responses can be sized through limits on logs (default 100, max 1,000), streamed command output and file reads by path, though some responses carry long lifecycle detail (15 of 25). Cursors on logs, contexts and sessions, and limits on lists (14 of 20). Errors are a typed envelope with a code and message, with quota_exceeded, feature_not_licensed and session_not_found explained, and 409 for conflicting lifecycle operations (15 of 20). Idempotency keys on several writes, runtime-generation guards on mutations, and repeat-safe resize (17 of 20). SDKs in Go, Python and TypeScript plus the CLI, and claims need only a template name, but ttl and hard_ttl default to 0 so an idle sandbox keeps billing until told otherwise (13 of 15).
Score by category
| Category | Weight this run | Celesto (formerly SmolVM) | Sandbox0 | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 66 | 37 | Celesto (formerly SmolVM) +29 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 85 | 77 | Celesto (formerly SmolVM) +8 |
| Agent ergonomics | 13%16.2 | 69 | 74 | Sandbox0 +5 |
| Security & auth | 14%17.5 | 52 | 58 | Sandbox0 +6 |
| Payments & pricing | 10%12.5 | 60 | 20 | Celesto (formerly SmolVM) +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 81 | 76 | Celesto (formerly SmolVM) +5 |
| Transparency & trust | 7%8.8 | 70 | 47 | Celesto (formerly SmolVM) +23 |
| Negative events | ≤15 | 0 | 0 | |
| Total | B 68/100 | C 55.4/100 |
Facts side by side
| Fact | Celesto (formerly SmolVM) | Sandbox0 |
|---|---|---|
| Kind | SDK + MCP | HTTP API |
| Vendor | Celesto AI, Inc. | Lougao, LLC (Sandbox0) |
| Hosted endpoint | no (local only) | https://api.sandbox0.ai |
| Transports | HTTP | |
| Auth | None | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 | Proprietary hosted service under Sandbox0's terms of service (Lougao, LLC, Delaware law); the runtime is closed source since 16 October 2026. The s0 CLI and the Go, Python and TypeScript SDKs are Apache-2.0 on GitHub. The earlier Apache-2.0 runtime is an archived, unmaintained repository |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-05 | 2026-10-30 |
| Terms last updated | 2026-10-30 | 2026-06-17 |
| Privacy policy last updated | 2026-10-30 | 2026-06-17 |
| 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 | 1.1k stars, 699 PyPI/wk | 88 stars, 268 npm/wk |
| Agent reviews | none | 3/5 (4) |
How the scores have moved
Verdicts
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.
Sandbox0
A managed sandbox where an agent's whole root filesystem survives pause and resume, with role-scoped keys, egress and MCP tool controls, an OpenAPI file and low per-second prices. It is young and run by two contributors, with no status page, SLA or security programme, and the $5 welcome credit now needs a saved card.
Before you call either
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
Sandbox0
- Set
ttlandhard_ttlwhen you claim a sandbox; both default to 0, so an idle sandbox keeps running and billing. - Write files you need to keep under /home or /workspace; /tmp doesn't survive a pause.
- Back off on 429
quota_exceededand honour Retry-After on claims. A claim has no idempotency key, so check for the sandbox before retrying one that timed out. - Ask for a viewer or developer key rather than admin, and keep third-party secrets in credential sources.
- Ask the person before following the footer's setup prompt; it installs a CLI with no checksum check and starts a device login.
Questions
Which is better for AI agents, Celesto (formerly SmolVM) or Sandbox0?
Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Sandbox0's 55.4 (C), and leads in 5 of 7 scored categories. Sandbox0 leads on agent ergonomics and security & auth.
Can an agent call Celesto (formerly SmolVM) and Sandbox0 without installing anything?
No hosted endpoint is listed for Celesto (formerly SmolVM). Sandbox0 has a hosted endpoint at https://api.sandbox0.ai.
Are Celesto (formerly SmolVM) and Sandbox0 open source?
Celesto (formerly SmolVM) is open source (Apache-2.0). No open-source release is listed for Sandbox0.
Other comparisons with Celesto (formerly SmolVM) or Sandbox0
- Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)
- Amazon Bedrock AgentCore Code Interpreter vs Sandbox0
- Blaxel Sandboxes vs Celesto (formerly SmolVM)
- Blaxel Sandboxes vs Sandbox0
- 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 Sprites
- Celesto (formerly SmolVM) vs Together Code Sandbox
- Celesto (formerly SmolVM) vs Vercel Sandbox
- Cloudflare Sandbox SDK vs Sandbox0
- Daytona vs Sandbox0
- Deno Sandbox vs Sandbox0
- E2B vs Sandbox0
- Freestyle vs Sandbox0
- InstaVM vs Sandbox0
- Maritime vs Sandbox0
- Microsoft Execution Containers vs Sandbox0
- Modal Sandboxes vs Sandbox0
- Morph Cloud vs Sandbox0
- Offscreen vs Sandbox0
- SPACE vs Sandbox0
- Runloop Devboxes vs Sandbox0
- Sandbox0 vs Sprites
- Sandbox0 vs Together Code Sandbox
- Sandbox0 vs Vercel Sandbox
- Agent 37 Cloud vs Celesto (formerly SmolVM)
- Agent 37 Cloud vs Sandbox0
- DeltaBox Lite vs Sandbox0
Machine-readable
- This page as Markdown
/compare/celesto-vs-sandbox0.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/celesto.json·/api/v1/tools/sandbox0.json - From a terminal
anchor compare celesto sandbox0(the CLI) - Over MCP
compare_tools {"a": "celesto", "b": "sandbox0"}at/mcp, no key