Head to head · Code sandboxes · October 2026 research run

Celesto (formerly SmolVM) vs Render Sandboxes

Celesto (formerly SmolVM) scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 2 of 7 scored categories. Render Sandboxes leads on security & auth and transparency & trust. Both do code sandboxes.

Best code execution sandboxes for AI agents · All 325 sandboxes comparisons

Which one, for what

Celesto (formerly SmolVM) BB

Best for Local microVM sandboxes for agent code, browsers and desktops on Linux and macOS, with a path to a hosted cloud.

Ahead on

  • Schema & documentation, 85 against 79
  • Payments & pricing, 90 against 30

Also in its favour

  • Agent-ready, a grade of BB or better
  • 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

Render Sandboxes B

Best for Teams already on Render that want agent sandboxes beside their services, or anyone who needs long-running sandboxes with idle suspension and process snapshots.

Ahead on

  • Security & auth, 63 against 52
  • Transparency & trust, 80 against 70

Watch for

Public beta since 4 November 2026, with one region (Oregon) and no SLA outside Enterprise

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) +60

Celesto (formerly SmolVM) 90

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. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Render Sandboxes 30

No x402, MPP or L402 (0). Per-unit prices published without login, $0.12 per CPU-hour used and $0.019 per GB-hour of memory, also given per minute and per second (30). No free sandbox allowance was found. Hobby workspaces cost $0 but sandbox compute is billed from the first second, and whether a payment method is needed first was not stated (0). A person signs up and creates the API key in the dashboard (0). 0+30+0+0 = 30.

Security & auth Render Sandboxes +11

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.

Render Sandboxes 63

A plain revocable Render API key that reaches every workspace its owner belongs to. Scoped keys are listed as not yet generally available (20 of 30). Network policy can be an HTTPS allowlist or deny-all, but the default allows all outbound traffic, and the CLI asks for --confirm before stopping a sandbox or deleting a group (10 of 20). Sandboxes run untrusted code in Firecracker microVMs. Brokered credentials that keep secrets out of the sandbox are alpha, and the agent templates warn that code in the sandbox can read its environment variables (8 of 15). Workspace audit logs on Pro and above per the pricing page. Whether they record sandbox calls was not found (7 of 15). Valid security.txt to 3 October 2027, a HackerOne disclosure programme, SOC 2 Type 2 and ISO 27001 on render.com/security. No paid bounty was established (18 of 20). 20+10+8+7+18 = 63.

Transparency & trust Render Sandboxes +10

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.

Render Sandboxes 80

The service is closed, under terms last modified 10 July 2026. The SDKs are open source (MIT and Apache-2.0) (20 of 30). A privacy policy and DPA, plus stated lifetimes for sandbox data. The filesystem is deleted on termination, suspended sandboxes stay resumable 30 days, and snapshots expire 30 days after last use unless the TTL is changed (20 of 30). The docs warn that APIs, defaults and limits might change during the beta, and the SDK changelog marks breaking changes with migration steps, but no deprecation policy or notice period was found (8 of 20). Eight sub-processors with countries on render.com/security, and the region (Oregon) is stated (15 of 20). 20+20+8+15 = 63.

Schema & documentation Celesto (formerly SmolVM) +6

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.

Render Sandboxes 79

No public REST API or OpenAPI document for sandboxes, and the SDK README lists the REST API as "Soon". The SDKs are typed and generated from Render's API schema, and the TypeScript and Python references document every method, which we count as 15 of 25 for an SDK, the reading modal-sandboxes was given (15). render.com/llms.txt, a Markdown twin of every page and a single sandboxes bundle at /docs/sandboxes/all (10). The guides say when to use idle suspension, runtime timeouts, filesystem or process snapshots and sandbox groups, and what a deleted snapshot breaks (15). Typed SDK inputs with a plan enum, a network policy type and documented bounds such as a 64-character snapshot name (12). Examples in CLI, TypeScript and both Python styles on every page, and 18 named error types with when each is thrown. No list of API error codes (14). Semver SDK changelog with dates and Render's product changelog. The 1.9.0 breaking change came in a minor version, called out in the changelog (13). 15+10+15+12+14+13 = 79.

Score by category

CategoryWeightCelesto (formerly SmolVM)Render SandboxesEdge
Reliability16%6668Render Sandboxes +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8579Celesto (formerly SmolVM) +6
Agent ergonomics13%6973Render Sandboxes +4
Security & auth14%5263Render Sandboxes +11
Payments & pricing10%9030Celesto (formerly SmolVM) +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8185Render Sandboxes +4
Transparency & trust7%7080Render Sandboxes +10
Negative events≤1500
TotalBB 71.8/100B 67.5/100

Facts side by side

FactCelesto (formerly SmolVM)Render Sandboxes
KindSDK + MCPSDK + MCP
VendorCelesto AI, Inc.Render Services, Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneAPI key
PricingFreemiumPay per use
x402nono
LicenceApache-2.0The service is proprietary under Render's terms. The SDK is MIT (TypeScript @renderinc/sdk) and Apache-2.0 (Python render)
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-052026-11-16
Terms last updated2026-10-302026-07-10
Privacy policy last updated2026-10-302026-07-10
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textyes
Popularity1.1k stars, 699 PyPI/wk27 stars

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.

Render Sandboxes

Render Sandboxes has per-operation rate limits, per-second prices and typed SDKs in three languages, with sandboxes that suspend when idle and resume from snapshots. It is a public beta in one region, with no public REST API, no idempotency on create and API keys that reach every workspace.

Before you call either

Celesto (formerly SmolVM)

  1. Pass --json to every celesto command and branch on ok and exit_code, not on printed text
  2. Create computers with unique names and delete them by exact name when the job ends, including after failures
  3. Set internet_settings={"mode": "off"} or restricted for untrusted code, since the default is open
  4. Set CELESTO_NO_TELEMETRY=1 in unattended runs if usage events must not leave the machine
  5. Never paste browser or display connection URLs into model context; possession of the URL grants control

Render Sandboxes

  1. Set timeoutSeconds when you create a sandbox. A disabled timeout keeps the sandbox, and its billing, running until you terminate it
  2. Pass networkPolicy with an allowlist or deny-all at creation, since the default allows outbound traffic to any destination
  3. Check the exit event's exit_code after exec. A nonzero exit code does not raise an error in the SDK
  4. If create returns 429, check whether the group is at its concurrency cap before you retry. Rate and concurrency limits share the same code
  5. Use ttlSeconds on snapshots with SDK 1.9.0 or later. The expiresAt option was removed in 1.9.0

Questions

Which is better for AI agents, Celesto (formerly SmolVM) or Render Sandboxes?

Celesto (formerly SmolVM) scores 71.8 (BB) on agent readiness against Render Sandboxes's 67.5 (B), and leads in 2 of 7 scored categories. Render Sandboxes leads on security & auth and transparency & trust.

Are Celesto (formerly SmolVM) and Render Sandboxes open source?

Celesto (formerly SmolVM) is open source (Apache-2.0). No open-source release is listed for Render Sandboxes.

Other comparisons with Celesto (formerly SmolVM) or Render Sandboxes

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.