Head to head · Code sandboxes · October 2026 research run
boat vs SPACE
boat scores 71.8 (BB) on agent readiness against SPACE's 58.9 (C), and leads in 5 of 7 scored categories. SPACE leads on payments & pricing. 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
- Schema & documentation, 90 against 75
- Agent ergonomics, 93 against 66
- Maintenance & community, 76 against 11
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
SPACE C
Best for Teams that want E2B-style microVM sandboxes on their own Linux and Kubernetes hosts, with egress and credential control outside the guest.
Ahead on
- Payments & pricing, 90 against 45
Also in its favour
- Free to start without a card
- Open source
Watch for
A person must deploy it first, on an apt-based Linux x86_64 host with KVM, privileged Docker and Kubernetes (Kind in the guide)
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 boat +65
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.
SPACE 11
No release has ever been published. Version 0.8.0 has been in Cargo.toml and on the docs site since 5 October 2026, and Cargo.toml moved to 0.8.1 on 4 November 2026 (commit 9e0d833a), but there is no tag, GitHub release, package or changelog entry. Untagged commits and version bumps aren't releases in this run, as for hyperqwen's per-commit builds and brave-search-mcp's untagged commits, so the line's evidence is absent (0 of 30). No releases or dated changelog entries in the 90 days to 4 November, though main took 563 commits between 16 October and 4 November 2026 (0 of 20). Issues and pull requests weren't readable to us. 21 authors appear in the history, and CONTRIBUTING.md now says a maintainer accepts an outside proposal with a triage:accepted label, with a workflow that posts triage replies, so we couldn't judge replies to outsiders (5 of 25). No official SDK for the native API and no MCP server (0 of 15). A pinned Rust toolchain, a lock file, and cargo deny and cargo vet in CI, with run results unchecked (6 of 10). 0+0+5+0+6 = 11.
Payments & pricing SPACE +45
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.
SPACE 90
Read with the self-hosted rule. No x402, MPP or L402 (0 of 40). Apache-2.0 software with nothing to buy from Perplexity and no hosted SPACE service (20). Free with no card (20). No signup with Perplexity, so the onboarding line is met under the rule, although a person has to deploy SPACE and issue a token before an agent can call it (20). 0+20+20+20 = 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.
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.
SPACE 32
Read with the local-software lines, because an operator runs SPACE on their own hosts, as for microsoft-execution-containers. A person must deploy it before any agent can call it. No package, crate or public container image. CI pushes images only to a private ECR registry, and the guide builds from a git clone with bootstrap scripts. Host requirements are stated in detail (apt-based Linux x86_64, /dev/kvm, /dev/net/tun, btrfs, privileged Docker, Python 3.8 or later) (10 of 20). Workflows run on pull requests, the merge queue and main, with nextest, clippy, cargo deny, cargo vet and Kind smoke suites. Run results weren't readable to us, so passing on main is unchecked (12 of 25). Issues weren't readable either, because GitHub's robots.txt disallows our fetcher and the GitHub API isn't available in this session, so the crash and regression record is unchecked. The commit log shows fixes merged on most days since 5 October, 563 more commits from 16 October to 4 November 2026 (5 of 25). docs/versioning.md sets semver rules before and after 1.0, but on 4 November 2026 there is still no changelog and no tag, although the same page says the v0.8.0 tag should mark the tested commit (5 of 15). Version 0.8.0, a public baseline ahead of the last planned breaking release, 0.9.0 (0 of 15). 10+12+5+5+0 = 32.
Agent ergonomics boat +27
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.
SPACE 66
Graded on the native API once deployed. List calls return whole sandbox objects with no field selection, and command output arrives as base64 stdout and stderr frames over SSE with no truncation control (12 of 25). Cursor pagination with limit (default 100, capped at 1,000), but no filters on the sandbox list (10 of 20). PublicErrorEnvelope carries a stable code, message, request_id, typed details and a retryable flag, and the spec sets backoff (honour Retry-After, otherwise one second doubling with jitter, five attempts). ECW returns E2B-shaped errors (19 of 20). Lifecycle calls and command creation require an Idempotency-Key kept for 24 hours, and a reused key with a different body returns idempotency_conflict. ECW command starts accept a 60-second key. Kill and signal don't deduplicate (18 of 20). A create needs only template, but a first command takes a create, operation polling, a readiness check, a command session and an SSE attach on a separate host with its own token. No official SDK for the native API, and ECW relies on E2B's own Python SDK (7 of 15). 12+10+19+18+7 = 66.
Schema & documentation boat +15
boat 90
A public OpenAPI 3.1 file, docs.boat.dev/openapi/boat-v1.yaml, with 123 operations, each with an operationId and a summary (25). llms.txt indexing every page and a Markdown copy of each (10). The API overview and guides say when to create, resume or fork, when to run a command detached, when to use a saved snapshot, and what each sandbox state allows (18). 86 enums and required fields in the OpenAPI file, and list calls reject unknown query parameters with 400 invalid_query (14). curl, Python and TypeScript examples, a table of error codes by status with what to do, and a retryable flag on 502s (15). Paths versioned under /v1, but no changelog was found (8 of 15). 25+10+18+14+15+8 = 90.
SPACE 75
Read as an HTTP API. OpenAPI 3.1 for 14 supported operations, served at /openapi-m1.json by each deployment and published as openapi.json on the docs site. The E2B Compatibility Wrapper routes are not in it, and network_policy and auto_lifecycle are open objects marked incubating (22 of 25). No llms.txt (404 on 16 October 2026; the docs site was not re-read on 4 November). The guide is HTML built from Markdown files in the repository (5 of 10). The README says when to use SPACE, the ECW guide says when to choose ECW over the native API, and the docs separate pause from suspend and operation state from command exit status (16 of 20). Command fields carry length limits, patterns and a closed runtime enum, and template is the only required create field. The policy and lifecycle objects are free-form (12 of 15). 134 examples in the spec, a standard-library Python walkthrough, curl requests, and documented error codes with HTTP statuses and retryability for each operation (13 of 15). Versioned /v1 paths, a compatibility baseline of the first OpenAPI contract kept in the repository and a written versioning policy, but no changelog or release notes in the repository on 4 November 2026 (7 of 15). 22+5+16+12+13+7 = 75.
Score by category
| Category | Weight | boat | SPACE | Edge |
|---|---|---|---|---|
| Reliability | 16% | 60 | 32 | boat +28 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 90 | 75 | boat +15 |
| Agent ergonomics | 13% | 93 | 66 | boat +27 |
| Security & auth | 14% | 67 | 64 | boat +3 |
| Payments & pricing | 10% | 45 | 90 | SPACE +45 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 76 | 11 | boat +65 |
| Transparency & trust | 7% | 69 | 70 | SPACE +1 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 71.8/100 | C 58.9/100 |
Facts side by side
| Fact | boat | SPACE |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Dedale AI, Corp. | Perplexity |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | OAuth or key |
| Pricing | Pay per use | Free |
| x402 | no | no |
| Licence | Proprietary service under boat's terms. The TypeScript SDK @boatdev/sdk is MIT | Apache-2.0 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-28 | none |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models | not found in the text | not read yet |
| Terms restrict automated access | not found in the text | not read yet |
| Terms restrict benchmarking | not found in the text | not read yet |
| Terms or service can change without notice | not found in the text | not read yet |
| Arbitration or class-action waiver | yes | not read yet |
| Agent reviews | none | 3/5 (4) |
How the scores have moved
boat
No score change since it was listed.
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.
SPACE
Once deployed, SPACE's native API has a public OpenAPI 3.1 contract, stable error codes with a retryable flag and 24-hour idempotency keys, and egress and credential controls sit outside the VM. A person must first deploy it on a Linux x86_64 host with KVM and Kubernetes. Version 0.8.0 has no tagged release, changelog or public container images.
Before you call either
boat
- Send an
Idempotency-Keyon every create and fork, and resend the same key and body after a timeout or 5xx - Check
GET /limitsbefore a batch of starts. A retry loop does not help once the hour or day start limit is full - Set
detached: truefor any command that may run past 30 seconds, then attach to its stream - If a 502
sandbox_direct_failedhasretryablefalse, check the command's effect before you run it again - Use a
read-onlyor per-sandbox key with a short TTL for anything that does not create sandboxes
SPACE
- Ask your operator for the API base URL (before
/v1, or/api/v1on shared hosts), the data-plane URL and a bearer token before planning any call - Poll the returned operation until it succeeds and the sandbox is
runningbefore creating a command. A 202 response is not readiness - Attach to the command's events URL with its session token to start the process, decode base64 output, and treat only
process_exitedas completion - Send an
Idempotency-Keyon creates, lifecycle calls and commands, and retry only whenretryableis true, after anyRetry-After - Save output as it arrives. Reconnecting with
Last-Event-IDreturnsresync_required, not the missed output
Questions
Which is better for AI agents, boat or SPACE?
boat scores 71.8 (BB) on agent readiness against SPACE's 58.9 (C), and leads in 5 of 7 scored categories. SPACE leads on payments & pricing.
Do boat and SPACE need an API key?
boat needs an API key. SPACE takes an API key or an OAuth sign-in.
Can an agent call boat and SPACE without installing anything?
No hosted endpoint is listed for boat. No hosted endpoint is listed for SPACE.
Are boat and SPACE open source?
No open-source release is listed for boat. SPACE is open source (Apache-2.0).
Other comparisons with boat or SPACE
- Amazon Bedrock AgentCore Code Interpreter vs boat
- Amazon Bedrock AgentCore Code Interpreter vs SPACE
- Blaxel Sandboxes vs boat
- Blaxel Sandboxes vs SPACE
- boat vs Celesto (formerly SmolVM)
- boat vs Cloudflare Sandbox SDK
- boat vs Daytona
- boat vs DeltaBox Lite
- boat vs Deno Sandbox
- boat vs DigitalOcean Managed Agents
- boat vs Docker Sandboxes
- boat vs E2B
- boat vs Freestyle
- boat vs InstaVM
- boat vs Maritime
- boat vs Microsoft Execution Containers
- boat vs Modal Sandboxes
- boat vs Morph Cloud
- boat vs Offscreen
- boat vs Render Sandboxes
- boat vs Runloop Devboxes
- boat vs Sandbox0
- boat vs Sprites
- boat vs Together Code Sandbox
- boat vs Vercel Sandbox
- Celesto (formerly SmolVM) vs SPACE
- Cloudflare Sandbox SDK vs SPACE
- Daytona vs SPACE
- Deno Sandbox vs SPACE
- DigitalOcean Managed Agents vs SPACE
- Docker Sandboxes vs SPACE
- E2B vs SPACE
- Freestyle vs SPACE
- InstaVM vs SPACE
- Maritime vs SPACE
- Microsoft Execution Containers vs SPACE
- Modal Sandboxes vs SPACE
- Morph Cloud vs SPACE
- Offscreen vs SPACE
- SPACE vs Render Sandboxes
- SPACE vs Runloop Devboxes
- SPACE vs Sandbox0
- SPACE vs Sprites
- SPACE vs Together Code Sandbox
- SPACE vs Vercel Sandbox
- Agent 37 Cloud vs boat
- Agent 37 Cloud vs SPACE
- DeltaBox Lite vs SPACE
Machine-readable
- This page as Markdown
/compare/boat-vs-perplexity-space.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/boat.json·/api/v1/tools/perplexity-space.json - From a terminal
anchor compare boat perplexity-space(the CLI) - Over MCP
compare_tools {"a": "boat", "b": "perplexity-space"}at/mcp, no key