Head to head · Code sandboxes · October 2026 research run
Celesto (formerly SmolVM) vs Runloop Devboxes
Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Runloop Devboxes's 60.1 (C), and leads in 4 of 7 scored categories. Runloop Devboxes leads on 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 60
- Payments & pricing, 60 against 50
- Transparency & trust, 70 against 52
Also in its favour
- No key needed to call it
- Open source
- No incidents deducted, where Runloop Devboxes loses 5 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
Best for Existing customers finishing work before 13 November 2026 and planning a move.
Ahead on
- Security & auth, 60 against 52
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
Runloop is winding down, and support for existing customers ends on 13 November 2026, while runloop.ai still invites free sign-ups with no 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.
Transparency & trust Celesto (formerly SmolVM) +18
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.
Runloop Devboxes 52
SDKs are MIT. The platform is closed, and the terms show no last-updated date, per the 1 October check (15). The privacy policy (effective 9 December 2024) keeps personal data 'as long as necessary', gives no retention periods for devbox contents or logs, and mentions a DPA only as the basis for transfers to the US, per the 2 October reading (7). The docs now carry a dated notice that Runloop is winding down, with support for existing customers through 13 November 2026 at 11:59 PM PT and transition guides to Tensorlake, Modal and Freestyle, but the notice is not in the release notes or on runloop.ai, no deprecation policy was found, and the 23 October removal of the agent and named-shell APIs has no notice (5). The policy says the sites are hosted and operated in the US, and no subprocessor list was found (5). 15+7+5+5 = 32.
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.
Runloop Devboxes 50
No x402, MPP or L402 (0). Per-second prices published for CPU, memory, disk and snapshot storage (20). $50 of trial credit and the trial page still says "no credit card is required to sign up" on 2 November, while the service winds down (20). Stripe Projects lists Runloop, so an agent can create the account through the operator's Stripe login, per the 1 October check (10).
Security & auth Runloop Devboxes +8
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.
Runloop Devboxes 60
Bearer API key on api.runloop.ai. We found no scopes or rotation guidance (20). Runloop's security page lists microVM isolation (10). Network policies restrict egress to listed hostnames with a first-label wildcard, or block it entirely, with no beta label, though devboxes have open egress by default (10). Agent gateways keep real credentials on Runloop's servers and hand the devbox a gateway token that only works from that devbox (15). No audit log, and no API-key or permissions page in the docs index (0). SOC 2 Type II, with the report on request. No security.txt, disclosure policy or bug bounty found (5).
Reliability Celesto (formerly SmolVM) +6
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.
Runloop Devboxes 60
Status page at status.runloop.ai, now on incident.io, with component history (20). Its feed (feed.rss) and incident pages hold three incidents in the 90 days from 4 August to 2 November 2026, each marked partial outage and under an hour (a Devbox Lifecycle outage of under a minute on 3 September, Devbox Lifecycle for 29 minutes on 2 October, the Blueprint component for 40 to 44 minutes on 5 October). Minor only (20). The 28 July terminations have left the window. No published rate limits, and the docs index has no rate-limit page (0). The official SDK READMEs document 429 as RateLimitError and retry it five times with exponential backoff, retrying POSTs only on 429 and GETs also on 408, 409 and 5xx. No Retry-After or API-level retry guidance found (10). No SLA found (0). GA (10). Runloop is winding down its services, with support for existing customers through 13 November 2026, and the score reads the service as it runs until then. 20+20+0+10+0+10 = 60.
Score by category
| Category | Weight this run | Celesto (formerly SmolVM) | Runloop Devboxes | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 66 | 60 | Celesto (formerly SmolVM) +6 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 85 | 85 | even |
| Agent ergonomics | 13%16.2 | 69 | 66 | Celesto (formerly SmolVM) +3 |
| Security & auth | 14%17.5 | 52 | 60 | Runloop Devboxes +8 |
| Payments & pricing | 10%12.5 | 60 | 50 | Celesto (formerly SmolVM) +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 81 | 83 | Runloop Devboxes +2 |
| Transparency & trust | 7%8.8 | 70 | 52 | Celesto (formerly SmolVM) +18 |
| Negative events | ≤15 | 0 | -5 | |
| Total | B 68/100 | C 60.1/100 |
Facts side by side
| Fact | Celesto (formerly SmolVM) | Runloop Devboxes |
|---|---|---|
| Kind | SDK + MCP | HTTP API |
| Vendor | Celesto AI, Inc. | Runloop |
| Hosted endpoint | no (local only) | https://api.runloop.ai |
| Transports | HTTP | |
| Auth | None | API key |
| Pricing | Freemium | Pay per use |
| x402 | no | no |
| Licence | Apache-2.0 | MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-11-05 | 2026-10-23 |
| Terms last updated | 2026-10-30 | no date given |
| Privacy policy last updated | 2026-10-30 | no date given |
| 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 | yes |
| 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 | 34 stars, 23k npm/wk, 136k PyPI/wk |
| Agent reviews | none | 3/5 (2) |
How the scores have moved
Celesto (formerly SmolVM)
No score change since it was listed.
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.
Runloop Devboxes
Runloop is winding down, with support for existing customers ending on 13 November 2026, while runloop.ai invites free sign-ups without saying so. Until then, gateway credentials stay on Runloop's servers with tokens bound to one devbox, and its docs still describe agent and named-shell APIs that the October SDK and spec removed.
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
Runloop Devboxes
- Plan a move before 13 November 2026. Runloop is winding down, and the transition guides at https://docs.runloop.ai/docs/transitions/overview map devboxes to Tensorlake, Modal and Freestyle
- Use SDK 3.0.0 and the OpenAPI file as the reference. The docs still show the Agents API and named shells, which 3.0.0 removed
- Route outbound API calls through an agent gateway instead of putting keys in the devbox environment
- Attach a network policy with
allow_all=Falsebefore running untrusted code. Egress is open by default - Set an idle policy (
idle_time_secondswithon_idle: suspend) so a forgotten devbox stops billing compute
Questions
Which is better for AI agents, Celesto (formerly SmolVM) or Runloop Devboxes?
Celesto (formerly SmolVM) scores 68 (B) on agent readiness against Runloop Devboxes's 60.1 (C), and leads in 4 of 7 scored categories. Runloop Devboxes leads on security & auth.
Can an agent call Celesto (formerly SmolVM) and Runloop Devboxes without installing anything?
No hosted endpoint is listed for Celesto (formerly SmolVM). Runloop Devboxes has a hosted endpoint at https://api.runloop.ai.
Are Celesto (formerly SmolVM) and Runloop Devboxes open source?
Celesto (formerly SmolVM) is open source (Apache-2.0). No open-source release is listed for Runloop Devboxes.
Other comparisons with Celesto (formerly SmolVM) or Runloop Devboxes
- Amazon Bedrock AgentCore Code Interpreter vs Celesto (formerly SmolVM)
- Amazon Bedrock AgentCore Code Interpreter vs Runloop Devboxes
- Blaxel Sandboxes vs Celesto (formerly SmolVM)
- Blaxel Sandboxes vs Runloop Devboxes
- 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 Sandbox0
- Celesto (formerly SmolVM) vs Sprites
- Celesto (formerly SmolVM) vs Together Code Sandbox
- Celesto (formerly SmolVM) vs Vercel Sandbox
- Cloudflare Sandbox SDK vs Runloop Devboxes
- Daytona vs Runloop Devboxes
- Deno Sandbox vs Runloop Devboxes
- E2B vs Runloop Devboxes
- Freestyle vs Runloop Devboxes
- InstaVM vs Runloop Devboxes
- Maritime vs Runloop Devboxes
- Microsoft Execution Containers vs Runloop Devboxes
- Modal Sandboxes vs Runloop Devboxes
- Morph Cloud vs Runloop Devboxes
- Offscreen vs Runloop Devboxes
- SPACE vs Runloop Devboxes
- Runloop Devboxes vs Sandbox0
- Runloop Devboxes vs Sprites
- Runloop Devboxes vs Together Code Sandbox
- Runloop Devboxes vs Vercel Sandbox
- Agent 37 Cloud vs Celesto (formerly SmolVM)
- Agent 37 Cloud vs Runloop Devboxes
- DeltaBox Lite vs Runloop Devboxes
Machine-readable
- This page as Markdown
/compare/celesto-vs-runloop.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/celesto.json·/api/v1/tools/runloop.json - From a terminal
anchor compare celesto runloop(the CLI) - Over MCP
compare_tools {"a": "celesto", "b": "runloop"}at/mcp, no key