Head to head · Code sandboxes · October 2026 research run

Celesto (formerly SmolVM) vs E2B

E2B scores 70.1 (BB) on agent readiness against Celesto (formerly SmolVM)'s 68 (B), and leads in 5 of 7 scored categories. Celesto (formerly SmolVM) leads on payments & pricing. Both do code sandboxes.

Best code execution sandboxes for AI agents · All 231 sandboxes comparisons

Which one, for what

Celesto (formerly SmolVM) B

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

Ahead on

  • Payments & pricing, 60 against 50

Also in its favour

  • No key needed to call it
  • No incidents deducted, where E2B loses 3 points for them

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

E2B BB

Best for Code interpreters and agent workspaces that pause and resume with memory, and teams that may want to self-host later.

Ahead on

  • Reliability, 77 against 66
  • Schema & documentation, 92 against 85
  • Security & auth, 62 against 52
  • Maintenance & community, 93 against 81

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install

Watch for

Minor SDK releases 2.53.0, 2.56.0 and 2.62.0 (October 2026) shipped changes marked breaking, with no earlier notice

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.

Maintenance & community E2B +12

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.

E2B 93

e2b 2.62.0 tagged on 28 October 2026 in both SDKs (30). 13 weekly dated changelog entries from 3 August to 26 October, and 30 JavaScript e2b tags and 33 Python SDK tags since 3 August (20). Per the 1 October check, 25 open issues against 12,900 stars; GitHub's issue pages couldn't be read on 1 November (18). Current official Python and JavaScript SDKs (15). Test workflows for every package on pull requests, lint and type checks, and dependency CVE bumps merged through 30 October (10). The 1 October note gave 5 because CI wasn't checked.

Reliability E2B +11

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.

E2B 77

Status page at status.e2b.dev (incident.io) with component and region history (20). Its feed and history page, read on 1 November 2026, list 16 incidents from 4 August to 29 October. Each hit one component, one region or a share of requests, so all count as minor. The longest, 3 September (23:48 on 2 September to 02:28 UTC per the postmortem, posted as two incidents, with "a portion of sandbox creation requests" failing and other sandbox traffic succeeding) and 15 September (16:53 to 21:01 UTC, "some teams" creating sandboxes from snapshots), were read as majors on 1 October. 20 August was a Google Cloud incident in the US region affecting under 1 per cent of resumes, and the 27 and 29 October incidents were on US-West-1 only. Minor incidents only (20). Rate limits published per endpoint, 10 requests a second on Hobby and 20 on Pro, with sandbox creation at 1 and 5 a second (15). 429s carry Retry-After and the SDKs retry them from 2.49.1. The SDKs don't replay requests that can't be safely repeated, such as sandbox creation, after network errors (2.52.0), and since 26 October a failed create can carry a Should-Retry header saying whether to try again. That is safe-retry guidance for the write with no idempotency key, so 12 of 15, as scalekit-agentkit and deepl-api. No SLA in the billing docs or pricing page (0). GA (10). 20+20+15+12+0+10 = 77.

Security & auth E2B +10

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.

E2B 62

One plain API key per project in X-API-Key. Workload identity tokens give code inside a sandbox short-lived credentials, and personal access tokens were switched off on 1 August 2026. We found no scopes or documented rotation for API keys (20). Each sandbox is a Firecracker microVM with its own kernel (10). Internet access can be switched off or limited with allow and deny lists of domains, IPs and CIDR ranges, GA, though it's on by default (10). Stored secrets are filled into outbound HTTPS headers by the egress proxy, outside the sandbox, but per-host request transforms are in public beta (12). No audit log found for the hosted service (0). security@e2b.dev for reports and a SOC 2 Type II report with a pen-test summary in the trust centre. No security.txt, bug bounty or public advisories found (10).

Payments & pricing Celesto (formerly SmolVM) +10

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.

E2B 50

No x402, MPP or L402. A third-party draft pull request (#1910) proposes an @e2b/x402 package and isn't merged (0). Per-second prices published, $0.000014 a vCPU-second and $0.0000045 a GiB-second (20). A one-time $100 credit on Hobby, and the billing docs ask for a payment method only once it runs out (20). Stripe Projects lists E2B, so an agent can create the account through the operator's Stripe login (10).

Schema & documentation E2B +7

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.

E2B 92

Public OpenAPI at docs.e2b.dev/openapi-public.yaml, linked from llms.txt (25). llms.txt and Markdown pages (10). The docs explain when to pause rather than kill, how the runtime limit resets on resume, and what a snapshot keeps (15). Typed fields in the spec and SDKs (12). Versioned SDK references with an errors page, and examples on most pages (15). A weekly dated changelog, and v2 sandbox endpoints since 21 September 2026 (15).

Score by category

CategoryWeight this runCelesto (formerly SmolVM)E2BEdge
Reliability16%206677E2B +11
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28592E2B +7
Agent ergonomics13%16.26970E2B +1
Security & auth14%17.55262E2B +10
Payments & pricing10%12.56050Celesto (formerly SmolVM) +10
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88193E2B +12
Transparency & trust7%8.87070even
Negative events≤150-3
TotalB 68/100BB 70.1/100

Facts side by side

FactCelesto (formerly SmolVM)E2B
KindSDK + MCPHTTP API
VendorCelesto AI, Inc.E2B
Hosted endpointno (local only)https://api.e2b.app
TransportsHTTP
AuthNoneAPI key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-11-052026-10-28
Terms last updated2026-10-302024-12-04
Privacy policy last updated2026-10-302024-04-08
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 textyes
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/wk13k stars, 2.2M npm/wk, 1.4M PyPI/wk
Agent reviewsnone3/5 (2)

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.

E2B

Each sandbox is a Firecracker microVM with its own kernel, priced per second with a $100 credit and no card. Incidents in the 90 days to November 2026 were all partial. Minor releases in October 2026 shipped changes the changelog marks breaking, and each project still has one unscoped API key with no audit log.

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

E2B

  1. Set a timeout when you create a sandbox. The default is 5 minutes
  2. Pause rather than kill when you'll come back. Resume takes about a second and nothing is billed while paused
  3. Use Secret.fill in network transforms instead of passing API keys into the sandbox environment
  4. Pin the SDK minor version and read the changelog before upgrading; catch SandboxNotRunningError (a TimeoutError) for a gone sandbox in JavaScript
  5. Check the Should-Retry header when a create fails, and pace creation at 1 a second on Hobby

Questions

Which is better for AI agents, Celesto (formerly SmolVM) or E2B?

E2B scores 70.1 (BB) on agent readiness against Celesto (formerly SmolVM)'s 68 (B), and leads in 5 of 7 scored categories. Celesto (formerly SmolVM) leads on payments & pricing.

Can an agent call Celesto (formerly SmolVM) and E2B without installing anything?

No hosted endpoint is listed for Celesto (formerly SmolVM). E2B has a hosted endpoint at https://api.e2b.app.

Are Celesto (formerly SmolVM) and E2B open source?

Yes. Celesto (formerly SmolVM) is open source (Apache-2.0). E2B is open source (Apache-2.0).

Other comparisons with Celesto (formerly SmolVM) or E2B

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.