bochka vs Depot

Depot is build and CI infrastructure: fast GitHub Actions runners on Linux, Windows and macOS, a new machine for every job. bochka gives each agent a full VM that keeps its disk between runs, serves apps on HTTPS ports and comes with coding agents you drive from outside.

Where bochka stands out

A machine that stays

A bochka sandbox is a full VM that runs until you stop it on paid plans. Its disk is snapshotted every minute and on stop, a stopped sandbox costs nothing, and you can fork a running one into a copy. Depot's runners are thrown away after each job, and its Sandbox SDK sandboxes end after at most 24 hours with snapshots still listed as coming soon.

Apps your agents can serve

bochka gives each sandbox HTTPS URLs on up to 50 ports, token-protected, plus raw TCP and its own IP. An agent can start a dev server, a database or an API and you, your users or a test suite can reach it. Depot documents SSH for debugging a CI job, but no way to expose a port to outside traffic.

Coding agents you drive from outside

bochka ships Claude Code, Codex, OpenCode and other agents inside each sandbox, and you drive agents inside from outside with a prompt, steer and events API. The AI credentials proxy keeps real keys out of the sandbox and can switch a credential to another account when credits run out. Depot runs only Claude Code, started with its CLI, and passes secrets in as environment variables.

The companies and products

bochka

bochka.xyz runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.

You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.

Isolation: Full VM per sandbox, own kernel
Hardware: Dedicated AMD Ryzen 9 9950X (Zen 5) hosts
Regions: EU: Germany, Finland, France
Plans: From $20 a month, all of it usage credit, 7-day trial

Depot

Depot is a build and CI platform: faster Docker builds, drop-in GitHub Actions runners, its own Depot CI, and newer sandboxes for coding agents.

Depot's main product is GitHub Actions runners: you change one runs-on label and each job runs on a fresh AWS EC2 instance that is thrown away when the job ends, with Linux, Arm, Windows and macOS sizes and a shared fast cache. It also sells remote agent sandboxes that run Claude Code in a container, and a Sandbox SDK in public beta whose sandboxes live at most 24 hours. It is built for engineering teams that want CI and builds to finish sooner, so it is a different kind of product than an agent sandbox, and this page compares where the two overlap.

Founded: Incorporated January 2022; Y Combinator in 2023; $10M Series A in March 2026
Isolation: Each GitHub Actions job runs on a new EC2 instance that is destroyed after the job; agent sessions run in an isolated container
Runner types: Linux x64 and Arm from 2 to 64 CPUs, Windows Server 2025 and 2022, and macOS 26, 15 and 14 at 8 CPU / 24 GB
Regions: United States, and the European Union if a project chooses the EU
Concurrency: Says its runners have no concurrency limits
Compliance: Announced SOC 2 Type I
Billing: Plans from $20 a month with included build and CI minutes, then per-minute or per-second usage; 7-day trial

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. “3rd cheapest of 367” means 2 of the other 366 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	bochka: price rank	Depot: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A Depot runner lives for one CI job, so an agent that builds an app over days fits better on bochka, where the disk, Docker and /dev/kvm stay on one VM.	3rd cheapest of 367 $634 a month	331st of 367, with limits $8,688 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An always-on assistant needs a machine that never ends; Depot's runners end with the job and its Sandbox SDK caps a sandbox at 24 hours.	5th cheapest of 366 $657 a month	86th of 366, with limits $13,148 a month
Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month	186th of 345, with limits $2,000 a month	311th of 345, with limits $1,188 a month
Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Your users' sandboxes need a URL to reach them; bochka serves HTTPS ports and raw TCP, while Depot documents no inbound access.	Cheapest of 361 $209 a month	318th of 361, with limits $3,713 a month
RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month	34th of 360, with limits $2,000 a month	311th of 360, with limits $17,908 a month
Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month	10th cheapest of 364 $200 a month	319th of 364, with limits $2,888 a month
CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Both fit; Depot is made for this, a one-line change to your GitHub Actions workflow with a shared fast cache, while bochka gives you a full VM you run your own runner or scripts on.	4th cheapest of 377 $86 a month	125th cheapest of 377 $1,736 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Depot machines are made to start, run a job and disappear, so a dev box that keeps its state all month fits bochka.	18th cheapest of 368 $26 a month	199th of 368, with limits $534 a month
Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month bochka ships a 60fps desktop with Chromium and computer use; Depot has no desktop product.	6th cheapest of 369 $200 a month	321st of 369, with limits $2,600 a month
Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month	7th cheapest of 367 $200 a month	139th of 367, with limits $1,304 a month
Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month	6th cheapest of 346 $90 a month	139th of 346, with limits $1,763 a month
Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month	71st of 338, with limits $1,800 a month	312th of 338, with limits $35,108 a month
Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month	2nd cheapest of 360 $200 a month	81st of 360, with limits $863 a month
GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month	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 Depot fits: it rents macOS runners by the minute, and bochka runs Linux only.	Can't run it	10th of 36, with limits $248 a month

Key features

Feature	bochka	Depot
What it is	VMs for AI agents that you keep, stop, fork and host from	CI runners and build machines for GitHub Actions, plus agent sandboxes and a beta Sandbox SDK
Isolation	Every sandbox is a full VM with its own kernel	A fresh EC2 instance per CI job; agent sessions in an isolated container
How long a machine lives	No session cap on paid plans; runs until you stop it	Runners end with the job; Sandbox SDK default 120 minutes, at most 24 hours
Files after a stop	Snapshots every minute and on stop; a stopped sandbox costs nothing and keeps its disk	Runners are never reused; agent sandboxes keep files and the Claude Code conversation; SDK snapshots are coming soon
Fork	Fork a running sandbox into a copy	No fork or clone API
Docker and nested virtualization	Docker, root, systemd and /dev/kvm on every machine	Docker on Linux runners; /dev/kvm only on Depot CI sandboxes, not on GitHub Actions runners; no Hyper-V on Windows
Reaching the machine	HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4	SSH into a running Depot CI job for debugging; no documented inbound ports or URLs
Coding agents	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API	Claude Code only, started and resumed with the depot claude command
Keeping keys out of the machine	AI credentials proxy for model providers and any HTTPS API; real keys never enter the sandbox	Secrets are passed into the job or sandbox as environment variables
Desktop and computer use	60fps desktop and Chromium, computer use and browser control	No desktop or computer-use product
macOS and Windows	Linux only; Wine for Windows apps	macOS 26, 15 and 14 runners and Windows Server 2025 and 2022 runners
Outbound network rules	Open internet on every plan; no provider-side allowlist	Egress filtering on Linux runners by IP, CIDR or hostname, with a default allow or deny
CI integration	A VM you can register as your own runner; no managed CI cache	Drop-in GitHub Actions runners with a shared cache up to 1000 MiB/s, plus fast Docker builds
Regions and CPUs	EU only: Germany, Finland, France; AMD Ryzen 9 9950X hosts	US and EU regions; x64 and Graviton4 Arm runners; GPU runners on the Business plan
Compliance and transparency	SOC 2 is in progress. We're open about where we stand: live status and data retention policy.	SOC 2

Every feature Battleships tracks (43)

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

Performance

bochka26.69 runs/s

DepotNot measured

There is no comparable measurement. Depot was not in the public StarSling benchmark run where bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB, so we do not compare CPU speed here.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Depot 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.

Scenario	bochka, a month	Depot, 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	$20 · $20/mo	$122 · Developer · with limits
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$26 · $20/mo	$534 · Developer · with limits
50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside	$317 · $20/mo × 3 seats	$5,710 · Developer · with limits
Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once	$200 · $100/mo × 2 seats	$1,628 · Developer · with limits
1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month	$2,000 · $2000/mo · with limits	$3,588 · Developer · with limits

bochka: 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.

Depot: Depot plans cost $20 or $200 a month and include GitHub Actions, Depot CI and Docker build minutes; after that a 2-CPU Linux runner costs $0.006 a minute and bigger sizes multiply it. Depot CI bills per second per vCPU, and agent sandboxes cost $0.01 a minute with no included usage. We priced the scenarios on Depot's 4-CPU / 16 GB Linux runner, since that is its main product.

Limits in those scenarios

Depot says its runners have no concurrency limits, so the number of machines is not what bites. What bites is the shape of the product: a runner lives for one CI job started by a GitHub webhook, and a Sandbox SDK sandbox ends after at most 24 hours, so an agent that never stops needs restarts and loses its machine each time. On bochka, the 1,000 short jobs burst is the hard one: starts are capped per minute, per hour and per day, so the jobs queue and need more starts per day than the $2,000 plan allows.

Scenario	bochka	Depot
One coding agent, workdays	None that bite	different kind of product: CI runner egress price not published
One agent that never stops	None that bite	different kind of product: CI runner sessions end after 24 h: needs restarts to run 24/7 egress price not published
50 agents in parallel	None that bite	different kind of product: CI runner egress price not published how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)
Sandboxes for your users	None that bite	different kind of product: CI runner not confirmed: how many machines can run at once (you need 300; the typical published limit is 50) egress price not published
1,000 short jobs at once	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)	different kind of product: CI runner not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50) egress price not published

Which one should you use?

Use Depot when

you want faster GitHub Actions and Docker builds, or need macOS or Windows runners for CI.

macOS and Windows runners. Useful if you build or test for Apple or Windows: Depot rents macOS and Windows runners by the minute.
Drop-in CI with a fast cache. Useful if your goal is faster GitHub Actions: change one runs-on label and jobs use Depot's runners and cache.
US region, Arm, egress rules. Useful if jobs must run in the US, on Arm, or with outbound traffic limited to chosen hosts.

Use bochka when

your agents need a machine that stays: a full VM that keeps its disk, forks, serves apps on HTTPS ports and comes with coding agents you drive from outside.

A machine that stays. An agent that installs tools, clones repos and builds for days loses all of it when a Depot runner ends. You pay again to rebuild the environment on every run, or keep your own cache and image pipeline.
Apps your agents can serve. Without inbound access, an agent that builds a web app cannot show it to anyone. On Depot you would add your own tunnel to each short-lived machine, and it disappears when the job ends.
Coding agents you drive from outside. When keys sit in environment variables, any code the agent runs can read and leak them. With only a start and resume command, you write the code that steers and watches each agent yourself.

Questions people ask

Is Depot an agent sandbox?

Mostly not. Depot is build and CI infrastructure: GitHub Actions runners, Depot CI and Docker builds. It also sells remote agent sandboxes for Claude Code and a Sandbox SDK in public beta, but those sandboxes end after at most 24 hours and have no snapshots or inbound access yet.

Is bochka cheaper than Depot?

In every scenario we priced, yes, though Depot is a CI runner and was not made for these jobs. One coding agent on workdays comes to $20 a month on bochka and $122 on Depot, and one agent running all month comes to $26 versus $534. 50 agents in parallel come to $317 versus $5,710, and 1,000 short jobs at once come to $2,000 versus $3,588.

Can I run GitHub Actions on bochka?

Yes, a bochka sandbox is a full Linux VM, so you can register it as a self-hosted runner or run your build scripts in it, with Docker and /dev/kvm ready. Depot does this for you with a one-line runs-on change and a managed cache, which is simpler if CI speed is all you need.

Does bochka have macOS or Windows like Depot?

No. bochka runs Linux VMs on dedicated AMD Ryzen 9 9950X hosts and has Wine docs for Windows apps. If you need macOS runners for Xcode or Windows Server runners, Depot has both.

Where does my data run?

bochka runs only in the EU (Germany, Finland and France), with EU data residency and a zero data retention option. Depot runs in the United States, and in the European Union if a project chooses the EU region.

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. Depot has announced SOC 2 Type I.

Start a sandbox

Install the CLI, then run bochka new.

Product preview