Head to head · Code sandboxes · October 2026 research run

boat vs Together Code Sandbox

boat scores 71.8 (BB) on agent readiness against Together Code Sandbox's 56 (C), and leads in 6 of 7 scored categories. Together Code Sandbox leads on maintenance & community. Both do code sandboxes.

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

Which one, for what

boat BB

Best for Long-lived, full Ubuntu VMs with Docker, a desktop and Chrome for coding agents, evals and products that give each user a sandbox, hosted in the EU.

Ahead on

  • Reliability, 60 against 32
  • Agent ergonomics, 93 against 70
  • Security & auth, 67 against 46
  • Payments & pricing, 45 against 30
  • Transparency & trust, 69 against 59

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

No security.txt or bug bounty, and SOC 2 is in progress

Together Code Sandbox C

Best for Teams already buying from Together, and former CodeSandbox SDK users, who want Docker-defined sandboxes with disk and memory snapshots from Python or TypeScript.

Ahead on

  • Maintenance & community, 83 against 76

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

The SDK and CLI work only for organisations Together has enabled, and the docs say to contact Together for access

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.

Reliability boat +28

boat 60

Hosted reading. A status page at status.ascii.dev, linked from the docs, draws its system status and metrics in a script our reader could not run, so component history was not confirmed (15 of 20). No readable incident history (5). Limits published per plan with numbers, from 12 starts a minute and 100 sandboxes at once on the $20 plan to 90 a minute and 2,000 on the $2,000 plan, plus 10,000 requests a minute per IP (15). Every 429 sends Retry-After, RateLimit headers carry the remaining starts, 503s carry retryAfterSeconds, the docs give a backoff example, and create and fork take an Idempotency-Key (15). No SLA found. The docs cite a measured 99.95% sandbox uptime, and the terms disclaim uptime warranties (0). The API is v1 with no beta label (10). 15+5+15+15+0+10 = 60.

Together Code Sandbox 32

Read with the hosted lines. status.together.ai lists the website, the playground and inference models with no component for the sandbox service, and a vendor status page with no component for the product takes 15. Incident line kept at 5. The Together page posts no incident since 6 January 2025, while status.codesandbox.io, which lists the CodeSandbox API and two clusters, wasn't re-read on 4 November (codesandbox.io answers a bot check, so its terms are unread), per the 8 October check (5). No rate or concurrency limits found, and the migration guide says the concurrency count and limit are not exposed (0). Both SDKs retry 408, 429, 500, 502, 503 and 504 three times with exponential backoff from 0.5 seconds plus jitter, and the SDK references say snapshots.create is not idempotent and should be excluded from retries. That is safe-retry guidance with no idempotency keys (12). No SLA found, and the terms make no uptime guarantee outside an order form (0). The docs still say the SDK must be enabled for an organisation, on request to sales, which is not general availability (0). 15 + 5 + 0 + 12 + 0 + 0 = 32.

Agent ergonomics boat +23

boat 93

Lists take limit from 1 to 200, commands can stream or detach, and a file read above 5 MiB returns 413 with a pointer to a signed download URL (20). Cursor pagination with hasMore and filters by name, name prefix, label and state (20). A stable error envelope with code, message, details and requestId, and a per-status table of what to do (20). Idempotency-Key on create and fork, kept 24 hours, with 409 idempotency_in_progress and 409 idempotency_key_reused, and per-code guidance on whether a command may have run (18). ttlSeconds defaults to one hour, the body of a create can be empty, and SDKs exist in Python and TypeScript beside the CLI with --json on every command (15). 20+20+20+18+15 = 93.

Together Code Sandbox 70

List calls take limit from 1 to 100, batch reads take IDs and exec output can be read from a lastSequence. No field selection (15). Cursor pagination on sandboxes and snapshots, with filters for status, source snapshot, tags and retired snapshots (20). Errors return code, message and per-parameter entries, the SDKs raise one HttpError with the status, and status_reason names causes such as out_of_capacity and oom_killed. No catalogue of codes found (14). Built-in retries, but no idempotency keys, sandbox IDs can't be chosen and snapshots.create can register duplicates (8). Python and TypeScript SDKs and a CLI, with defaults of 1 vCPU and 2 GiB. A snapshot must be built first because no default image exists (13).

Security & auth boat +21

boat 67

Scoped API keys with presets (read-only, full-sandbox, ci, admin), a TTL, per-sandbox limits, and documented rotation and revocation (30). Read-only and per-sandbox keys exist, but outbound traffic is open by default, the API has no network rule setting, and delete has no confirmation step (14 of 20). Each sandbox is its own VM. An AI credentials proxy keeps real model keys out of sandboxes, and a "Safe for third parties" environment strips the owner's secrets before an end user gets a sandbox (10 of 15). Per-key usage, command history and logs, and signed webhooks (9 of 15). Security reports go to support with "security" in the subject. No security.txt (404), no bug bounty, and SOC 2 is listed as in progress (4 of 20). 30+14+10+9+4 = 67.

Together Code Sandbox 46

Project-scoped API keys, revocable within about five minutes, with optional expiry and rotation guidance, read as the Together inference and fine-tuning listings read the same key model (30). The in-VM OpenAPI document still lists ?token= as a documented way to authenticate the WebSocket exec path, so the checklist's fixed 10 comes off (20). Each sandbox is a virtual machine. Every port is open to everyone unless the experimental inbound policy is set, no outbound rules exist, and project roles are admin and editor with no read-only role (8). The sandbox returns the output of code the agent ran, with no guidance on untrusted output found (8). Sandboxes can be listed with tags and status_reason. No audit log found (3). A PGP-signed security.txt (Expires 2028-09-30) points Contact and Policy at HackerOne with no acknowledgement time, the value this run gives a disclosure route with no stated time (7). 20 + 8 + 8 + 3 + 7 = 46.

Payments & pricing boat +15

boat 45

No x402, MPP or L402 (0). Per-hour prices for each size published without login, from $0.018 an hour for small to $0.20 for xlarge, with overage and start prices (30). The 7-day trial (25 compute hours) needs a card in Stripe Checkout (0). An agent can register itself through the auth.md agent registration protocol or AgentID, but a person has to claim the agent or verify the AgentMail organisation and enter a card before a sandbox can start (15 of 30). 0+30+0+15 = 45.

Together Code Sandbox 30

No x402, MPP or L402 found (0). The pricing page still lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB of RAM per hour without a login, and does not say whether the rate covers the new SDK as well as the legacy one (20). The billing docs say Together has no free trial and that platform access needs a minimum $15 credit purchase (0). Access needs a browser signup, a payment and a request to Together to enable the organisation (0). 0 + 20 + 0 + 0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Transparency & trust boat +10

boat 69

Closed service under terms of 12 October 2026 from Dedale AI, Corp., a Delaware corporation (15). The terms, privacy policy and docs agree on retention. A stopped sandbox's disk is kept at least 14 days, saved snapshots have no scheduled expiry, and zero data retention can be turned on. The terms say the cleanup job does not yet delete in production. A DPA is available on request (25 of 30). The Box to boat rename on 15 September 2026 put Deprecation and Sunset headers on old surfaces with a dated sunset of 31 October 2026, and deprecated endpoints are marked in the reference (18 of 20). Infrastructure hosts (OVH, Hetzner) and other processors are named, sandboxes run in Germany, Finland and France, and snapshot copies can be stored outside the EU (16 of 20). 15+25+18+16 = 74.

Together Code Sandbox 59

A closed service under Together's terms of service (19 May 2026). The SDKs, CLI and OpenAPI documents are MIT, which doesn't raise the line for a closed API, as for the Together inference and fine-tuning listings (15). The privacy policy (17 December 2025) says data is not used for training without opt-in. Its table of data types covers inference, fine-tuning and GPU clusters with no sandbox row, and no retention period for sandbox filesystems or snapshots was found beyond an optional snapshot ttl (12). The legacy @codesandbox/sdk page is still marked deprecated with no end date, the deprecations page covers models only, and breaking SDK changes are marked in the changelog. Kept as a partial (8). No sub-processor list or data locations for sandboxes found. A docs example names a cluster na-us-ce-01, and the trust centre was unread (3). 15 + 12 + 8 + 3 = 38.

Maintenance & community Together Code Sandbox +7

boat 76

Python SDK boat-sdk 1.13.0 on 28 October 2026 (30). 25 SDK releases from 1.0.0 on 16 September to 1.13.0 on 28 October 2026 on PyPI (20). Closed service with a Discord, a support page and a blog, but no public changelog or tracker (8 of 25). Official SDKs in Python and TypeScript (@boatdev/sdk 1.13.0) generated from the OpenAPI file (15). No public source repository or CI for the SDKs was found (3 of 10). 30+20+8+15+3 = 76.

Together Code Sandbox 83

Last release together-sandbox 4.1.1 on 7 October 2026, 28 days before 4 November (30). Four tagged releases from 6 August, 4.0.3 (10 August), 4.0.4 (30 September), 4.1.0 (1 October) and 4.1.1 (7 October), each changing SDK or API code (20). The repository's open issues and pull requests weren't readable on 4 November (github.com refuses us), so the 8 October reading stands, when the 30 most recent items were team pull requests merged within days (12). Current official Python and TypeScript SDKs and a CLI, versioned together (15). Pull requests run the TypeScript unit tests, end-to-end tests run on pushes to main, and packages publish by OIDC trusted publishing. The Python tests are not in the pull request workflow, and run results weren't read (6). 30 + 20 + 12 + 15 + 6 = 83.

Score by category

CategoryWeightboatTogether Code SandboxEdge
Reliability16%6032boat +28
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9086boat +4
Agent ergonomics13%9370boat +23
Security & auth14%6746boat +21
Payments & pricing10%4530boat +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7683Together Code Sandbox +7
Transparency & trust7%6959boat +10
Negative events≤1500
TotalBB 71.8/100C 56/100

Facts side by side

FactboatTogether Code Sandbox
KindHTTP APIHTTP API
VendorDedale AI, Corp.Together AI
Hosted endpointno (local only)https://api.bartender.codesandbox.io
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceProprietary service under boat's terms. The TypeScript SDK @boatdev/sdk is MITProprietary service under Together's terms of service. The SDKs, CLI and OpenAPI documents on GitHub are MIT
Read-only variant documentedyesno
llms.txtyesyes
Last release2026-10-282026-10-07
Terms last updatedno date givenno date given
Privacy policy last updatedno date givenno date given
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 textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularitynone3 stars, 1.3k npm/wk

How the scores have moved

Verdicts

boat

boat publishes an OpenAPI 3.1 contract with 123 operations, per-hour prices, scoped expiring keys and idempotent creates for full Ubuntu VMs in the EU. It has no security.txt, SLA or readable incident history, SOC 2 is in progress, and the trial needs a card.

Together Code Sandbox

Two public OpenAPI documents, MIT clients for Python and TypeScript, cursor pagination and SDK retries with guidance on which writes not to retry make the surface easy for an agent to drive. Access is the limit. Together enables the SDK per organisation on request, publishes no rate limits or SLA, and its status page has no sandbox component.

Before you call either

boat

  1. Send an Idempotency-Key on every create and fork, and resend the same key and body after a timeout or 5xx
  2. Check GET /limits before a batch of starts. A retry loop does not help once the hour or day start limit is full
  3. Set detached: true for any command that may run past 30 seconds, then attach to its stream
  4. If a 502 sandbox_direct_failed has retryable false, check the command's effect before you run it again
  5. Use a read-only or per-sandbox key with a short TTL for anything that does not create sandboxes

Together Code Sandbox

  1. Confirm the organisation is on Together's allowlist before installing. A valid TOGETHER_API_KEY alone is not enough
  2. Build a snapshot first with snapshots.create. No default image exists, and every sandbox needs snapshot_id or snapshot_alias
  3. Set ttl at creation or call terminate(). Nothing stops a sandbox otherwise, and closing the Python client leaves it running
  4. Store the snapshot alias, not the sandbox ID. A terminated sandbox can't restart, and its state lives at sandbox:<id>
  5. Exclude snapshots.create from retries with should_retry, and set experimental.network_policy before serving anything private on a port

Questions

Which is better for AI agents, boat or Together Code Sandbox?

boat scores 71.8 (BB) on agent readiness against Together Code Sandbox's 56 (C), and leads in 6 of 7 scored categories. Together Code Sandbox leads on maintenance & community.

Do boat and Together Code Sandbox need an API key?

Both need an API key.

Can an agent call boat and Together Code Sandbox without installing anything?

No hosted endpoint is listed for boat. Together Code Sandbox has a hosted endpoint at https://api.bartender.codesandbox.io.

Other comparisons with boat or Together Code Sandbox

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.