bochka vs Zo Computer
Zo Computer gives one person an always-on cloud computer with an AI assistant living on it. bochka gives your code as many full virtual machines as it needs, each with Docker, coding agents and a desktop, made and driven through an API.
Where bochka stands out
A full VM with Docker and its own kernel
Every bochka sandbox is a full virtual machine on dedicated AMD Ryzen 9 9950X hosts, with root, systemd, Docker and /dev/kvm for Android emulators and nested VMs. Zo gives you root on a Linux computer, but does not say how it is isolated and does not document Docker or nested virtualization.
Many machines, made and forked from code
bochka's API creates, stops and forks sandboxes, up to 100 running at once on the $20 plan and more above it. The disk is saved every minute, and you can fork a running sandbox to try two paths from the same state. Zo sells one computer per workspace, with no fork.
Agents you drive from outside
Claude Code, Codex and five other agents come preinstalled, and you prompt, steer and follow them through one API. Real API keys stay outside the sandbox in a credentials proxy that works with any HTTPS API, and a credential can switch to another account when one runs out of credits.
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
- Regions
- EU: Germany, Finland, France
Zo Computer
Zo Computer calls itself an intelligent cloud computer: a personal Linux server with an AI assistant that works on it for you.
Each workspace gets one always-on Linux computer with root, 100 GB of storage, a Chromium browser and an AI that can use its files, tools and apps. You talk to it in the app, by API or over MCP, host sites and services on it, and run prompts on a schedule. It is built for one person or a small team who want their own server and assistant, not for creating many sandboxes from code.
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 | Zo Computer: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs many machines with Docker that appear, fork and stop on demand, which is what bochka's API does and Zo's one computer per workspace does not. | 3rd cheapest of 367 $634 a month | 171st of 367, with limits $1,800 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Zo's assistant can run prompts on a schedule on its own computer, but each assistant needs its own workspace, while bochka runs many agents side by side in one account. | 5th cheapest of 366 $657 a month | 132nd of 366, with limits $900 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 | 318th of 345, with limits $1,800 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Giving each of your users a sandbox means creating hundreds of machines from code; Zo sells one computer per workspace, so it is not built for this. | Cheapest of 361 $209 a month | 329th of 361, with limits $5,400 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 | 312th of 360, with limits $18,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month Evals run the same task on many fresh machines at once, which needs a sandbox API like bochka's rather than one long-lived computer. | 10th cheapest of 364 $200 a month | 328th of 364, with limits $4,500 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI runners need fresh machines per job and often Docker or nested virtualization, which bochka has and Zo does not document. | 4th cheapest of 377 $86 a month | 303rd of 377, with limits $720 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Zo fits a single always-on dev box well: a big machine with root, SSH and hosting that never sleeps on paid plans. | 18th cheapest of 368 $26 a month | 8th cheapest of 368 $18 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month bochka streams a full Linux desktop at 60fps for computer-use agents; Zo has a Chromium browser but no desktop. | 6th cheapest of 369 $200 a month | 229th of 369, with limits $900 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Zo's browser keeps your own signed-in sessions for its assistant, while bochka gives each agent its own Chromium you can run in parallel. | 7th cheapest of 367 $200 a month | 134th of 367, with limits $900 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 | 132nd of 346, with limits $900 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 | 277th of 338, with limits $18,000 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 | 349th of 360, with limits $3,600 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 | Can't run it | Can't run it |
Key features
| Feature | bochka | Zo Computer |
|---|---|---|
| What you get | An API that creates full virtual machines for your code and agents | One always-on personal cloud computer with an AI assistant on it |
| Isolation | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts | Not stated; compute comes from Modal and Daytona |
| Docker and nested virtualization | Docker, systemd and /dev/kvm for Android emulators and VMs | Not documented |
| Root and SSH | Root and SSH in every sandbox | Root and SSH into your Zo server |
| Biggest machine | Up to 16 vCPU / 32 GB on the $100 plan and above | Up to 64 cores / 512 GB on Ultra |
| Machines at once | Up to 100 running sandboxes on the $20 plan, more on higher plans | One computer per workspace |
| Uptime | Runs as long as you want on paid plans; stop it and the disk stays | Always on for paid plans, with periodic restarts for updates |
| Snapshots and fork | Disk saved every minute and on stop; fork a running sandbox | Regular filesystem snapshots for recovery; no fork |
| Hosting | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 | 5 to 50 hosted services by plan, HTTP public or behind sign-in, TCP always public; custom domains |
| Browser and desktop | Chromium and a 60fps Linux desktop with computer use | Chromium that keeps your signed-in sessions; no desktop |
| Coding agents | Seven agents preinstalled, driven from outside with a prompt, steer and events API | One endpoint that messages Zo's own assistant; Claude Code or Codex can be its model provider |
| Keeping API keys out of the machine | Credentials proxy for model providers and any HTTPS API; real keys never enter the sandbox | Bring your own API keys, stored and used by Zo |
| Built-in assistant and automations | No assistant of its own; you drive the agents | AI assistant with integrations, scheduled automations and sites |
| Regions | EU only (Germany, Finland, France) | Not published |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | No SOC 2 report published |
Every feature Battleships tracks (43)
| Feature | bochka | Zo Computer |
|---|---|---|
| Full VM (own kernel) | Yes | No |
| Docker inside | Yes | Not published |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | Not published |
| 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 | No |
| Wake on request | No | No |
| HTTPS preview URLs | Yes | Yes |
| Raw TCP inbound | Yes | Yes |
| Public IPv4 | No | No |
| Egress allowlist | No | No |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | Yes |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | No |
| Windows | No | No |
| Arm64 | No | No |
| Self-hosting | No | No |
| BYOC | No | No |
| Open source | No | No |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Not published |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Not published |
| SSO | No | No |
| SOC 2 | No | No |
| HIPAA | No | No |
| EU data residency | Yes | No |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. bochka did 26.69 runs per second on the StarSling hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB, but Zo Computer has not been run on that benchmark, and Zo does not say whether its cores are dedicated or shared.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Zo Computer 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 | Zo Computer, 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 | $18 · Paid workspace subscription (fee priced in modes) |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $18 · Paid workspace subscription (fee priced in modes) |
| 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 | $900 · Paid workspace subscription (fee priced in modes) · 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 | $5,400 · Paid workspace subscription (fee priced in modes) · 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 | $18,000 · Paid workspace subscription (fee priced in modes) · with limits |
bochka: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Zo Computer: Zo charges a flat monthly fee per workspace for one always-on computer, Basic, Pro or Ultra, whether you use it or not. The fee includes monthly AI credits that cover AI use only, not extra compute.
Limits in those scenarios
Zo gives one computer per workspace, so every scenario that needs many machines at once means buying one workspace per machine, a use Zo does not document. That is why it does not fit 50 agents, sandboxes for your users or 1,000 short jobs. bochka fits every scenario except 1,000 short jobs at once, where its start limits queue the burst. Zo also does not publish egress prices.
| Scenario | bochka | Zo Computer |
|---|---|---|
| One coding agent, workdays | None that bite |
|
| One agent that never stops | None that bite |
|
| 50 agents in parallel | None that bite |
|
| Sandboxes for your users | None that bite |
|
| 1,000 short jobs at once |
|
|
Which one should you use?
Use Zo Computer when
you want one personal always-on server with an AI assistant, integrations and hosted sites, and you would rather talk to it than program it.
- A personal assistant that is ready to use. For one person who wants an AI assistant with its own server, apps, schedules and sites, without writing code.
- Very large single machines. Useful when one always-on computer needs far more memory, up to 512 GB on Ultra.
- Works as an MCP server for your tools. Claude Code, Cursor, Codex and other MCP clients can use Zo's files and tools directly.
Use bochka when
your code needs to create, fork and drive many full machines for agents, with Docker, nested virtualization, a desktop and keys kept outside the sandbox.
- A full VM with Docker and its own kernel. Agents that build and test real projects reach for Docker compose, databases in containers or an Android emulator. On Zo none of that is documented, so you find out only when the agent tries.
- Many machines, made and forked from code. Running 50 agents, one sandbox per user, or many eval runs means 50 or more machines. On Zo that is one workspace subscription per machine, set up by hand, with no API to make them.
- Agents you drive from outside. Zo's API talks to Zo's own assistant, not to the coding agent you picked, and keys you bring are stored with Zo. A prompt injection on a machine that holds real keys can leak them.
Questions people ask
Is bochka cheaper than Zo Computer?
For one machine, no: Zo's Basic plan costs $18 a month for an always-on computer, a little less than bochka in the two single-agent scenarios. For many machines, yes: 50 agents in parallel come to $317 a month on bochka against $900 on Zo, and sandboxes for your users to $200 against $5,400.
Is Zo Computer a sandbox?
Not in the usual sense. Zo is a personal cloud computer with an AI assistant, one per workspace, and its API sends messages to that assistant. bochka is a sandbox API that creates full virtual machines on demand.
Can I run Docker on Zo Computer?
Zo's docs do not mention Docker, and they do not say how the computer is isolated. bochka sandboxes are full VMs where Docker, systemd and nested virtualization all work.
Can I use Claude Code with each?
Yes, in different ways. On Zo you can use a Claude Code or Codex subscription as the model behind Zo's assistant, or connect Claude Code to Zo over MCP. On bochka, Claude Code and six other agents are preinstalled in each sandbox, and you prompt and steer them through bochka's API.
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.
Start a sandbox
Install the CLI, then run bochka new.
Product preview