CodeSandbox SDK vs Namespace

CodeSandbox SDK gives each sandbox a Firecracker VM that hibernates with its memory and wakes on the next HTTP request. Namespace is mainly a CI platform whose Devboxes run on Linux, macOS or Windows but shut down after 4 to 24 hours.

The companies and products

CodeSandbox SDK

CodeSandbox SDK is an API from CodeSandbox, now a Together AI company, that starts sandboxed development VMs on the same infrastructure as the CodeSandbox editor.

Each sandbox is a Firecracker microVM built from a template or any Dockerfile. When it goes idle it hibernates with a memory snapshot, and it resumes or forks from that snapshot in seconds. You drive it from a TypeScript SDK through terminals, commands, files and HTTPS hosts. Together's docs now call it the legacy offering and point new users to its successor, the together-sandbox SDK.

Self-hosting
Not offered

Namespace

Namespace is a dev platform for fast builds, tests and coding environments: CI runners, build caches and Devboxes, on its own hardware.

Most of Namespace is CI: a faster drop-in for GitHub Actions runners, with Docker, Bazel, Turborepo and Nix caching. Its Devboxes are remote Linux and macOS machines with persistent storage, made for people and AI coding agents, and they also host sessions for Claude Managed Agents, Cursor Cloud Agents and Devin. It is a different kind of product from boat, so this page compares the part where they overlap: a machine an agent works on.

Which use cases each one fits

For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “46th cheapest of 345” means 45 of the other 344 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.

Use case and its workloadCodeSandbox SDK: price rankNamespace: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Namespace places far higher than CodeSandbox SDK for a software factory, but both are compromises, while boat is a full fit with SSH, Docker and /dev/kvm.
178th of 367, with limits
$1,939 a month
39th of 367, with limits
$3,495 a month
3rd cheapest of 367
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that never stops is a compromise on both: Namespace shuts a Devbox down after at most 24 hours, and CodeSandbox SDK has no desktop or SSH.
215th of 366, with limits
$2,478 a month
303rd of 366, with limits
$6,645 a month
5th cheapest of 366
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
CodeSandbox SDK is a full fit for short code runs, because its VMs hibernate when idle and wake on the next request; on Namespace it is a compromise.
46th cheapest of 345
$642 a month
247th of 345, with limits
$250 a month
186th of 345, with limits
$2,000 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
CodeSandbox SDK wakes a user's sandbox on their next HTTP request but Scale caps it at 250 VMs at once; boat is a full fit with raw TCP and SSH as well.
140th of 361, with limits
$1,707 a month
284th of 361, with limits
$2,068 a month
Cheapest of 361
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
348th of 360, with limits
$3,861 a month
356th of 360, with limits
$9,012 a month
34th of 360, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
CodeSandbox SDK fits agent evals and Namespace is a compromise; boat fits too, with full VMs that fork while running.
64th cheapest of 364
$1,335 a month
282nd of 364, with limits
$1,043 a month
10th cheapest of 364
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Both fit CI, and CI runners with build caches are Namespace's main product; boat runs CI jobs on full VMs with Docker and /dev/kvm.
92nd cheapest of 377
$860 a month
80th cheapest of 377
$765 a month
4th cheapest of 377
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
310th of 368, with limits
$240 a month
126th of 368, with limits
$168 a month
18th cheapest of 368
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
Namespace's screenshot and click API works on macOS Devboxes only, and CodeSandbox SDK has no desktop; boat streams a 60fps Linux desktop with Chromium.
206th of 369, with limits
$691 a month
67th of 369, with limits
$982 a month
6th cheapest of 369
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
251st of 367, with limits
$443 a month
285th of 367, with limits
$789 a month
7th cheapest of 367
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
281st of 346, with limits
$508 a month
259th of 346, with limits
$332 a month
6th cheapest of 346
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
193rd of 338, with limits
$7,390 a month
226th of 338, with limits
$9,012 a month
71st of 338, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
240th of 360, with limits
$326 a month
242nd of 360, with limits
$339 a month
2nd cheapest of 360
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Can't run itCan't run itCan't run it
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Only Namespace fits here: it runs macOS on Apple Silicon, and neither CodeSandbox SDK nor boat has macOS.
Can't run it6th cheapest of 36
$1,205 a month
Can't run it

Key features

FeatureCodeSandbox SDKNamespaceboat
What it isAn SDK for sandboxed dev VMs, now called legacy by Together AIA CI and build platform with Devboxes for people and coding agentsA sandbox platform built for agents, on full VMs
IsolationFirecracker microVM with its own kernelLinux Devboxes run from a container image on Namespace's own hardware; the docs do not say if each has its own kernelFull VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU speed (Node.js build-and-test, 4 vCPU / 8 GB)Not measured21.79 runs/s26.69 runs/s
How long a session can runNo hard cap; hibernates after an idle timeout of up to one dayDevboxes shut down after 4, 5 or 24 hours by plan, even while you workNo session cap on paid plans
Pause and wakeHibernates with a memory snapshot; an HTTP request wakes it with processes still runningDevboxes stop after an idle timeout and start again when you connectDisk saved every minute and on stop; a stopped sandbox is started by API and boots again
ForkFork a hibernated sandbox from its snapshot, or a running one sharing its memoryNo fork; compute instances can suspend and resume with RAM keptFork a running sandbox with its disk
Docker and nested virtualizationDocker and root, built from any Dockerfile; nested virtualization not documentedDocker in Linux Devboxes; /dev/kvm on Linux compute instancesDocker, root, systemd and /dev/kvm on every machine
Operating systemsLinux onlyLinux, macOS on Apple Silicon, and Windows on Team plans and upLinux only; Wine for Windows apps
Shell accessTerminals, commands and files through the SDK; no SSHSSH into Devboxes, plus an MCP server to create them and run commandsSSH, plus exec and files over the API
Reaching the sandboxHTTPS host per port, public by default; no raw TCP or public IPHTTPS URLs that need a Namespace login; TCP through a CLI port-forward; no public IPHTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4
Desktop and computer useNo desktop; a headless Chromium templateScreenshot and click API on macOS Devboxes only; VNC and RDP for compute instances60fps Linux desktop with Chromium, computer use and browser control
Outbound internetOpen internet; no egress allowlistEgress policies per blueprint, runner or instance: block, advisory or allow by domainOpen internet on every plan; no provider-side allowlist
Keeping API keys out of the sandboxSecrets passed in as environment variablesEgress rules inject a header from Namespace Vault, resolved outside the workloadCredentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Coding agentsRun your own agent through the command APIHosts Claude Managed Agents, Cursor and Devin sessions through those partnersClaude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Every feature Battleships tracks (43)
FeatureCodeSandbox SDKNamespaceboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationNoYesYes
RootYesYesYes
SystemdNot publishedNot publishedYes
Desktop GUINoYesYes
BrowserNoNoYes
Computer-use APINoYesYes
SSHNoYesYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesNoYes
Live fork (no pause)YesNoYes
Memory forkYesNoNo
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo
Wake on requestYesYesNo
HTTPS preview URLsYesYesYes
Raw TCP inboundNoYesYes
Public IPv4NoNoNo
Egress allowlistNoYesNo
Secret proxyNoYesYes
Secret proxy for any APINoYesYes
Preinstalled agentsNoYesYes
Agent harness APINoNoYes
MCP serverNoYesNo
GPUNoNoNo
WindowsNoYesNo
Arm64NoYesNo
Self-hostingNoNoNo
BYOCNoNoNo
Open sourceNoNoNo
Scoped API keysNot publishedNot publishedYes
Spend limitsNot publishedYesYes
Usage per sandbox (API)NoNoYes
Audit logsNot publishedYesNo
SSOYesYesNo
SOC 2YesYesNo
HIPAANoNoNo
EU data residencyNoYesYes
Zero data retentionNot publishedNot publishedYes

Performance

CodeSandbox SDKNot measured
Namespace21.79 runs/s
boat26.69 runs/s

In StarSling's public run of 2026-09-29 at 4 vCPU / 8 GB, boat did 26.69 Node.js build-and-test runs per second and Namespace did 21.79, so the same build takes about a fifth longer on Namespace. CodeSandbox SDK was not part of that run, so there is no comparable CPU number for it.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Namespace measured on: Linux compute instance (unit-minutes, PAYG/overage $0.0015). CodeSandbox SDK has no published run in this suite yet, so there is no like-for-like number to compare.

Pricing in five scenarios

Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario.

ScenarioCodeSandbox SDK, a monthNamespace, a monthboat, a month
One coding agent, workdays
4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days
$193 · Scale$50 · Devbox (pay as you go)$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$341 · Scale$176 · Devbox (pay as you go) · with limits$26 · $20/mo
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$2,500 · Scale$2,198 · Devbox (pay as you go)$317 · $20/mo × 3 seats
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$815 · Scale · with limits$1,214 · Devbox (pay as you go)$200 · $100/mo × 2 seats
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$1,632 · Scale · with limits$3,237 · Devbox (pay as you go)$2,000 · $2000/mo · with limits

CodeSandbox SDK: You buy VM credits and each size burns a fixed number per hour, billed per started minute while the VM runs, including the idle time before it hibernates. The Scale plan adds a $170 monthly platform fee that is not usage credit, and a hibernated VM costs nothing.

Namespace: Devboxes are billed pay as you go at $0.004 per Devbox Minute, and a 4 vCPU / 8 GB Devbox uses one a minute. Plan minutes cover runners and instances, not Devboxes, and stored files cost $0.20 per GB-month.

Namespace: Plans start at $20 a month and all of it is usage credit, spent per second while sandboxes run. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

On CodeSandbox SDK the limit that bites is concurrency: Scale allows 250 VMs at once, so the 300 user sandboxes and the 1,000 short jobs do not fit without Enterprise. On Namespace it is time: a Devbox shuts down after at most 24 hours, so the agent that never stops has to restart at least once a day. Neither publishes an egress price, and CodeSandbox SDK does not publish a price for disk beyond 20 GiB. boat fits every scenario except the 1,000 short jobs, where its start limits queue the burst.

ScenarioCodeSandbox SDKNamespaceboat
One coding agent, workdays
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • egress price not published
None that bite
One agent that never stops
  • disk beyond 20 GiB: price unknown
  • egress price not published
  • sessions end after 24 h: needs restarts to run 24/7
  • egress price not published
None that bite
50 agents in parallel
  • egress price not published
  • egress price not published
None that bite
Sandboxes for your users
  • Scale: max 250 concurrent
  • egress price not published
  • egress price not published
None that bite
1,000 short jobs at once
  • Scale: max 250 concurrent
  • egress price not published
  • egress price not published
  • max 2,400 starts/day (needs ~6,667)
  • max 600 starts/hour (needs ~1,000)
  • bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use CodeSandbox SDK when

your sandboxes sleep between visits and should wake on the next HTTP request with their memory intact, or when you fork many runs from one warm state, and you are fine building on what Together now calls its legacy SDK.

  • Memory hibernation and wake on request. Good for previews and code runs used in bursts: a request wakes a sleeping VM with its processes still running.
  • Forks that share memory. Good for branching many runs, such as rollouts or test variants, from one warm running state.
  • No clock on a busy sandbox. Good for long jobs: a sandbox that keeps working has no hard time limit, and only idle time makes it hibernate.

Use Namespace when

you need macOS or Windows machines, faster GitHub Actions runners with build caches, or Devboxes for people that stop when idle and start when you connect.

  • macOS and Windows. Useful if agents build iOS or Mac apps or test on Windows: Namespace runs both, and CodeSandbox SDK is Linux only.
  • CI runners and build caches. Useful if you want faster GitHub Actions: Namespace is a drop-in runner with Docker, Bazel and Turborepo caching.
  • Egress rules and key injection. Useful if agents may reach only chosen domains, with keys added to requests from a vault outside the workload.

Where boat fits

If what you are really running is coding agents on Linux for hours or days, both tools leave gaps. CodeSandbox SDK gives you a VM you drive only through its SDK, and Namespace gives you a dev machine with a clock on it. boat gives each agent a full, faster VM with no session cap, a desktop, and agents you drive from outside.

A whole machine that keeps running

A Namespace Devbox is shut down after 4 to 24 hours even mid-task, and CodeSandbox SDK has no SSH or documented /dev/kvm. boat gives SSH, systemd, Docker and /dev/kvm, with no session cap on paid plans.

A Linux desktop for computer use

CodeSandbox SDK has no desktop, and Namespace's screenshot and click API rejects Linux Devboxes. On either you install a desktop and VNC yourself, or on Namespace pay for macOS minutes. boat streams a 60fps desktop with Chromium.

Agents and keys already set up

On CodeSandbox SDK you wire your own agent through commands and pass keys as environment variables; on Namespace a partner runs the agent loop. boat ships Claude Code, Codex and others with a prompt, steer and events API and a credentials proxy.

Use boat when your agents work on Linux for hours or days: a full, faster VM with no session cap, Docker and /dev/kvm, a 60fps desktop, hosting on 50 ports and raw TCP, and coding agents you drive from outside. Compare it one to one: boat vs CodeSandbox SDK and boat vs Namespace.

Questions people ask

Is CodeSandbox SDK cheaper than Namespace?

Mostly no. One coding agent on workdays comes to $193 a month on CodeSandbox SDK and $50 on Namespace, and 50 agents in parallel come to $2,500 versus $2,198. One agent running all month is $341 on CodeSandbox SDK and $176 on Namespace, but Namespace has to restart it at least once a day.

Which is faster, CodeSandbox SDK or Namespace?

There is no comparable CPU measurement for CodeSandbox SDK. Namespace did 21.79 Node.js runs per second at 4 vCPU / 8 GB in StarSling's benchmark, and boat did 26.69 in the same run.

How long can a sandbox run on each?

CodeSandbox SDK has no hard cap on a busy sandbox; it hibernates after an idle timeout of up to one day. A Namespace Devbox shuts down after 4, 5 or 24 hours by plan, even while you work in it. boat has no session cap on paid plans.

Can CodeSandbox SDK and Namespace run Docker?

Yes, both run Docker inside the sandbox, and CodeSandbox SDK builds sandboxes from any Dockerfile. Namespace offers /dev/kvm on Linux compute instances, while CodeSandbox SDK does not document nested virtualization. boat has Docker, systemd and /dev/kvm on every machine.

Which one runs macOS or Windows?

Only Namespace. It runs macOS on Apple M4 Pro and M5 Max chips, and Windows on Team plans and up. CodeSandbox SDK and boat are Linux only, with Wine docs on boat for Windows apps.

Is CodeSandbox SDK still maintained?

CodeSandbox is now part of Together AI. Together's docs call the CodeSandbox-based SDK deprecated and name together-sandbox as its successor, while self-serve sign-up still runs through CodeSandbox.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons