Namespace vs Modal VM Sandboxes

Namespace is a build platform: CI runners, caches and Devboxes on Linux, macOS and Windows that stop after 4 to 24 hours. Modal VM Sandboxes are Linux VMs with their own kernel that you create from code, run for up to 24 hours and then throw away.

The companies and products

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 bochka, so this page compares the part where they overlap: a machine an agent works on.

Products: GitHub Actions runners, Docker, Bazel, Turborepo and Nix caching, Devboxes, and a compute API
Hardware: Its own hardware in its own racks: AMD EPYC for Linux and Windows, Apple M4 Pro or M5 Max for macOS
Linux Devboxes: Run from a container image you choose and include Docker; the docs do not say whether each one has its own kernel
Devbox time limit: 4 hours on Developer, 5 on Team, 24 on Business, even while you are working
Customers: Says 1,000+ companies, including Ramp, ElevenLabs, Zed and Vanta
Funding: Announced a $42M Series B
Compliance: Trust center lists SOC 2 Type II

Modal VM Sandboxes

Modal is a serverless cloud for AI work, and VM Sandboxes are the version of its sandboxes that run in a virtual machine with their own Linux kernel.

You create a VM Sandbox from Python, TypeScript or Go code with runtime="vm", run commands in it, and terminate it when the job is done. Modal built the runtime on the Rust-based Cloud Hypervisor, so Docker, FUSE, systemd and nested cgroups work, with the same API, images and prices as its gVisor sandboxes. It became generally available on 1 October 2026 and suits teams that want many short-lived agent machines next to Modal's inference and training.

Founders: Erik Bernhardsson and Akshat Bubna
Offices: New York, Stockholm and San Francisco
Funding: Over $466M raised
Isolation: Virtual machine per sandbox on Cloud Hypervisor, with its own Linux 7.2 kernel
Generally available: 1 October 2026; early customers launched over 20 million VMs before that
Session length: Default 5 minutes, maximum 24 hours
Compliance: SOC 2 on every plan; HIPAA on Enterprise

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. “80th cheapest of 377” means 79 of the other 376 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 workload	Namespace: price rank	Modal VM Sandboxes: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Both are a compromise for a software factory because each machine ends within 24 hours; bochka ranks 3rd here with a VM that keeps its disk and has no session cap on paid plans.	39th of 367, with limits $3,495 a month	84th of 367, with limits $759 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An agent that never stops is cut off on both: a Namespace Devbox and a Modal VM Sandbox each end within 24 hours, while bochka has no session cap on paid plans.	303rd of 366, with limits $6,645 a month	Can't run it	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	247th of 345, with limits $250 a month	Can't run it	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	284th of 361, with limits $2,068 a month	Can't run it	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 Modal is built for huge bursts of short sandboxes, so it does better than Namespace for rollouts, and bochka's start limits queue the largest bursts.	356th of 360, with limits $9,012 a month	171st of 360, with limits $16,322 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	282nd of 364, with limits $1,043 a month	Can't run it	10th cheapest of 364 $200 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI runners are Namespace's main product, with caches for Docker, Bazel and more, so it fits where Modal VM Sandboxes are a compromise; bochka also fits, with Docker and /dev/kvm on every machine.	80th cheapest of 377 $765 a month	188th of 377, with limits $1,064 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB	126th of 368, with limits $168 a month	Can't run it	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 Modal has no desktop at all; bochka streams a 60fps Linux desktop with Chromium.	67th of 369, with limits $982 a month	Can't run it	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	285th of 367, with limits $789 a month	Can't run it	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	259th of 346, with limits $332 a month	Can't run it	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	226th of 338, with limits $9,012 a month	Can't run it	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 Both are a compromise for many parallel attack machines; bochka ranks 2nd here, with forks of a running sandbox and open internet on every plan.	242nd of 360, with limits $339 a month	294th of 360, with limits $642 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 None of the three fits: Namespace and bochka are CPU only, and Modal's GPUs need its gVisor sandboxes, not the VM runtime.	Can't run it	Can't run it	Can't run it
macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month Only Namespace fits: it runs macOS on Apple Silicon, and neither Modal VM Sandboxes nor bochka have macOS.	6th cheapest of 36 $1,205 a month	Can't run it	Can't run it

Key features

Feature	Namespace	Modal VM Sandboxes	bochka
Isolation	Linux Devboxes run from a container image on Namespace's own hardware; the docs do not say if each has its own kernel	VM with its own Linux kernel on Cloud Hypervisor	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
CPU speed (Node.js build-and-test, 4 vCPU / 8 GB)	21.79 runs/s	15.54 runs/s	26.69 runs/s
Docker and nested virtualization	Docker in Linux Devboxes; /dev/kvm on Linux compute instances	Docker and systemd (start dockerd yourself); /dev/kvm on Team and Enterprise only, on request	Docker, root, systemd and /dev/kvm on every machine
Longest session	Devboxes stop after 4, 5 or 24 hours by plan, raisable to 24 at most	24 hours (default 5 minutes)	No session cap on paid plans
Files after a stop	A stopped Devbox keeps its storage, billed at $0.20 per GB-month used	No paused state; only Volumes and filesystem snapshots keep files	Disk saved every minute and on stop; a stopped sandbox costs nothing
Idle stop and wake	Devboxes stop after an idle timeout and start again when you connect	No wake on connect; you create a new sandbox	Machines run until you stop them
Fork and snapshots	No fork; compute instances can suspend and resume with RAM kept	Filesystem snapshots boot many new sandboxes; memory snapshots in alpha	Fork a running sandbox with its disk; resume reboots from disk
Desktop and computer use	Screenshot and click API on macOS Devboxes only; VNC and RDP for compute instances	Not offered; an example shows how to set up Xvfb and VNC yourself	60fps Linux desktop, Chromium, computer use and browser control
Coding agents	Hosts Claude Managed Agents, Cursor and Devin sessions; an MCP server lets your agent create Devboxes	Examples only; you install the agent harness yourself	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping keys out of the sandbox	Egress rules inject a header from Namespace Vault, outside the workload	Secrets are environment variables, or you run your own proxy in a sidecar	AI credentials proxy for model providers and any HTTPS API you register
Reaching the sandbox	HTTPS URLs that need a Namespace login; TCP through a CLI port-forward; no public IP	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS URLs for up to 50 ports, token-protected, plus raw TCP
Outbound network rules	Block, advisory or allow by domain, per Devbox blueprint, runner or instance	Block all, IP-range allowlist, domain allowlist (beta)	Open internet, no provider-side allowlist
Operating systems	Linux, macOS on Apple Silicon, and Windows on Team plans and up	Linux only	Linux only; Wine for Windows apps
Regions	Several regions; keeping a workload inside one region needs Enterprise	US, EU and Asia-Pacific; pinning a region costs 1.15x to 1.75x	EU only: Germany, Finland, France, with EU data residency

Every feature Battleships tracks (43)

Feature	Namespace	Modal VM Sandboxes	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Yes	Yes	Yes
Nested virtualization	Yes	Yes	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Yes	Yes
Desktop GUI	Yes	No	Yes
Browser	No	No	Yes
Computer-use API	Yes	No	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	Yes	No	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	No	Yes	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	Yes	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	Yes	No	No
HTTPS preview URLs	Yes	Yes	Yes
Raw TCP inbound	Yes	Yes	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	Yes	No	Yes
Secret proxy for any API	Yes	No	Yes
Preinstalled agents	Yes	No	Yes
Agent harness API	No	No	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	Yes	No	No
Arm64	Yes	No	No
Self-hosting	No	No	No
BYOC	No	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	No	Not published	Yes
Audit logs	Yes	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Yes	No
HIPAA	No	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

Namespace21.79 runs/s

Modal VM Sandboxes15.54 runs/s

bochka26.69 runs/s

In StarSling's public run of 29 September 2026, at 4 vCPU / 8 GB, bochka did 26.69 Node.js build-and-test runs per second, Namespace 21.79 and Modal's VM runtime 15.54. So Namespace did about 1.4 times the CPU work of Modal VM Sandboxes, and bochka about 1.2 times Namespace and 1.7 times Modal. This measures CPU speed only, not start time.

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). Modal VM Sandboxes measured on: VM Sandbox, request = size.

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.

Scenario	Namespace, a month	Modal VM Sandboxes, a month	bochka, 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	$50 · Devbox (pay as you go)	$15 · Starter · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$176 · Devbox (pay as you go) · with limits	$178 · Starter · 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	$2,198 · Devbox (pay as you go)	$2,229 · Starter · with limits	$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	$1,214 · Devbox (pay as you go)	$792 · Team	$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	$3,237 · Devbox (pay as you go)	$3,193 · Team · with limits	$2,000 · $2000/mo · with limits

Namespace: Devboxes are billed in Devbox Minutes at $0.004 each, pay as you go on every plan: a 4 vCPU / 8 GB Devbox uses one a minute. The minutes in the Team ($100) and Business ($250) plans cover runners and instances, not Devboxes, and stored files cost $0.20 per GB-month.

Modal VM Sandboxes: Modal bills by the second for the higher of the CPU and memory you request or what you use, until the sandbox ends. Starter is free with $30 of monthly credit, Team is $250 a month with $100 of credit, and egress above the free allowance costs $0.04 per GiB.

Modal VM Sandboxes: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Time is the limit that bites on both: the agent that never stops comes to $176 a month on Namespace and $178 on Modal, and neither fits, because each machine ends within 24 hours. On Modal, the workday and 50-agent scenarios also lose installed packages between sessions unless files live in a Volume, and the 1,000-job burst runs on shared vCPUs. Namespace fits the burst and the fleet but does not publish an egress price or a Devbox concurrency limit; bochka's start limits queue the 1,000-job burst.

Scenario	Namespace	Modal VM Sandboxes	bochka
One coding agent, workdays	egress price not published	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
One agent that never stops	sessions end after 24 h: needs restarts to run 24/7 egress price not published	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
50 agents in parallel	egress price not published	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
Sandboxes for your users	egress price not published	None that bite	None that bite
1,000 short jobs at once	egress price not published	shared vCPUs on this tier (Modal (VM Sandboxes) sells dedicated cores separately as “VM Sandbox, request = size”): heavy, sustained CPU use can be slowed by other tenants	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 Namespace when

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

macOS and Windows. Useful if your agents build iOS or Mac apps or test on Windows: Namespace runs macOS on Apple Silicon and Windows machines.
CI runners and build caches. Useful if you want faster GitHub Actions: Namespace is a drop-in runner with Docker, Bazel, Turborepo and Nix caching.
Devboxes that sleep and wake. Useful for people's dev machines: a Devbox stops when idle, keeps its storage and starts again when you connect.

Use Modal VM Sandboxes when

you run large bursts of short jobs that finish within a day, need regions outside Europe, or already run your models on Modal.

Huge bursts of short jobs. Useful for evals and rollouts that finish fast: Modal runs 5,000 containers at once on Team and bills by the second.
Snapshots that fan out. Useful when one prepared machine should become many: a filesystem snapshot boots any number of new sandboxes.
Next to your models. Useful if you already serve or train models on Modal: sandboxes, GPUs and models sit on one account and one bill.

Where bochka fits

If what you are really running is agents that work for hours or days on Linux, both Namespace and Modal VM Sandboxes cut the machine off within 24 hours. bochka gives each agent a full VM that keeps its disk, has no session cap on paid plans and comes with a desktop and coding agents built in.

No clock on the session

A Namespace Devbox is shut down after 4, 5 or 24 hours even while it works, and a Modal VM Sandbox ends within 24 hours. Your code has to notice, snapshot or restart, and resume the task every day.

A disk that survives the stop

On Modal everything outside a Volume or snapshot is gone when the sandbox ends, so packages reset. Namespace keeps Devbox storage but bills it per GB-month. bochka saves the disk every minute and a stopped sandbox costs nothing.

Desktop and agents ready to go

Namespace's computer-use API works on macOS Devboxes only and Modal has no desktop, so a Linux browser agent means installing VNC yourself. bochka ships a 60fps desktop, Chromium and coding agents you drive from outside.

Use bochka when your agents work on Linux for hours or days: a full, faster VM with no session cap on paid plans, a disk that survives free stops, Docker and /dev/kvm, a 60fps desktop and coding agents you drive from outside. Compare it one to one: bochka vs Namespace and bochka vs Modal VM Sandboxes.

Questions people ask

Is Namespace cheaper than Modal VM Sandboxes?

It depends on the job. For one coding agent on workdays Modal comes to $15 a month and Namespace $50, but Modal's files reset between days unless you use a Volume. For sandboxes for your users Modal is $792 against $1,214, and for 50 parallel agents they are close at $2,198 on Namespace against $2,229 on Modal.

Which is faster, Namespace or Modal VM Sandboxes?

On the same CPU test at 4 vCPU / 8 GB, Namespace did 21.79 runs per second and Modal's VM runtime 15.54, about 1.4 times the CPU work. bochka did 26.69 in the same run.

Can Namespace and Modal VM Sandboxes run Docker?

Yes. Namespace's Linux Devboxes include Docker, and Modal VM Sandboxes run Docker once you start dockerd as the entrypoint. For /dev/kvm, Namespace offers it on Linux compute instances and Modal on Team and Enterprise after you ask support; bochka has Docker and /dev/kvm on every machine.

How long can a session run on each?

A Namespace Devbox runs up to 4 hours on Developer, 5 on Team and 24 on Business, even while you work. A Modal VM Sandbox defaults to 5 minutes and runs 24 hours at most. bochka has no session cap on paid plans.

Does either run macOS or GPUs?

Namespace runs macOS on Apple Silicon and Windows on Team plans and up, while Modal VM Sandboxes and bochka run Linux only. None of the three has GPUs on these machines; Modal's GPUs need its gVisor sandboxes.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview