bochka vs Intuned
Intuned runs your Playwright scrapers and browser automations on its own machines, with an AI agent that writes and fixes them. bochka gives your agent a whole Linux machine with Chromium inside, where it can also run code, Docker and servers, keep its files and work for as long as it needs.
Where bochka stands out
A whole machine around the browser
A bochka sandbox is a full Linux VM with root, a shell, Docker, systemd and /dev/kvm, with Chromium and a 60fps desktop already inside. Your agent can browse a site, save what it found, process it with any tool, build an app and serve it, all on one machine.
Runs for as long as the work takes, and keeps its files
bochka has no session cap on paid plans. The whole disk is saved every minute and when the sandbox stops, a stopped sandbox costs nothing, and you can fork a running one to try several paths at once.
Coding agents you drive, with keys kept outside
Claude Code, Codex and other coding agents come preinstalled, and you prompt, steer and follow them through one API. A credentials proxy keeps real API keys outside the sandbox for any HTTPS API, and switches 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
Intuned
Intuned is a code-first browser automation platform: you write scrapers and automations in Python or TypeScript with Playwright, and it runs them for you.
Intuned is a different kind of product from bochka. You deploy a Project of Playwright functions, and Intuned exposes each one as an API, runs it on a pool of its machines with queues, retries, schedules and logins handled, and bills only while a Run executes. Its Intuned Agent writes and repairs scrapers from a prompt and a schema, and it is built for teams that need reliable integrations with sites that have no API.
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 | Intuned: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs a shell, Docker and a place to build and test, and an Intuned machine only runs your Playwright functions. | 3rd cheapest of 367 $634 a month | 307th of 367, with limits $6,102 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that runs all month needs a machine that keeps going; Intuned Runs stop at 6 hours and keep only a key-value store between them. | 5th cheapest of 366 $657 a month | 320th of 366, with limits $7,918 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 | 275th of 345, with limits $403 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Sandboxes for your users need a general machine per user, and Intuned's pool is sized for running your own automations. | Cheapest of 361 $209 a month | 303rd of 361, with limits $2,695 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 | 299th of 360, with limits $12,570 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 | 307th of 364, with limits $2,070 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI runners need Docker, root and a disk for build caches, which Intuned's browser machines do not offer. | 4th cheapest of 377 $86 a month | 329th of 377, with limits $1,270 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 18th cheapest of 368 $26 a month | 341st of 368, with limits $384 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, while Intuned drives a browser through code. | 6th cheapest of 369 $200 a month | 300th of 369, with limits $1,903 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Intuned is built for this: browser tasks written as Playwright code or sent in plain English, with logins, retries and stealth handled; bochka fits too when the agent also needs a shell and files. | 7th cheapest of 367 $200 a month | 39th cheapest of 367 $1,070 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month Both fit startup-scale scrapers; Intuned schedules, retries and repairs them for you, while bochka gives each bot a whole machine whose disk keeps its files. | 6th cheapest of 346 $90 a month | 58th cheapest of 346 $558 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month Mass scraping of sites with strong bot checks needs stealth, CAPTCHA solving and proxies, which Intuned includes and bochka does not. | 71st of 338, with limits $1,800 a month | 14th of 338, with limits $9,820 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 | 77th of 360, with limits $674 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 | Intuned |
|---|---|---|
| What you get | A full Linux VM with its own kernel and root, on dedicated AMD Ryzen 9 9950X hosts | A managed machine that runs your Playwright functions, called through Intuned's API |
| Shell, code and Docker | SSH, any language, Docker, systemd and nested virtualization (/dev/kvm) | Python or TypeScript Playwright code only; no shell, SSH or Docker |
| Desktop and computer use | A full Linux desktop streamed at 60fps, or Chromium alone; embed it in your app | Headless or headful Chromium driven by code, with traces and logs |
| State between runs | The whole disk is saved every minute and on stop; fork a running sandbox | Each Run gets a fresh machine; a key-value store and AuthSessions carry data across Runs |
| Run length | No cap on paid plans; you set the time to live | 10 minutes per attempt by default, extendable to 6 hours per Run; longer through support |
| Machine sizes | Up to 16 vCPU / 32 GB on the $100 plan and above | 6 shared vCPU / 2 GB, 8 shared vCPU / 4 GB, or 1 performance vCPU / 8 GB |
| Starting on demand | A stopped sandbox is started by API and keeps its disk | Each API call is queued and picked up by a pool machine; idle machines are not billed |
| Stealth and CAPTCHAs | Chromium on datacenter IPs; no fingerprint rotation or CAPTCHA solving | Stealth Chromium, headful mode and CAPTCHA solving (stealth and CAPTCHA solving are experimental) |
| Proxies | None managed; you can run your own proxy client inside the VM | A managed proxy pool, or your own residential, datacenter or ISP proxies with URL rules |
| Logging in to sites | Your agent logs in itself; bochka switches AI credentials to another account when credits run out | AuthSessions check and recreate logins before Runs, with a 1Password integration |
| Agents | Claude Code, Codex and other coding agents preinstalled, with a prompt, steer and events API | Intuned Agent writes and fixes scrapers from a prompt; Web Tasks run a task described in plain English |
| Keeping secrets from the agent | Credentials proxy: real keys never enter the sandbox, for any HTTPS API | Environment variables and secrets passed to your automation code |
| Hosting | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP | No ports of your own; your functions are called through Intuned's API |
| Regions | EU only (Germany, Finland, France) | 17 regions including the US, Canada, Europe, India, Singapore, Japan and Australia |
| Compliance and transparency | SOC 2 is in progress. We're open about where we stand: live status and data retention policy. | Not published |
Every feature Battleships tracks (43)
| Feature | bochka | Intuned |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | No |
| Nested virtualization | Yes | No |
| Root | Yes | Not published |
| Systemd | Yes | Not published |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | No |
| SSH | Yes | No |
| Persistent disk | Yes | No |
| 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 | Not published |
| ≥24 h sessions | Yes | No |
| Idle auto-stop | No | Yes |
| Wake on request | No | Yes |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | Not published |
| Public IPv4 | No | No |
| Egress allowlist | No | No |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | No |
| 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 | Yes |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Not published |
| SSO | No | Yes |
| SOC 2 | No | Not published |
| HIPAA | No | Not published |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement. Intuned sells fixed browser machine sizes and is not in the CPU benchmark. bochka scored 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Intuned 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 | Intuned, 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 | $149 · Startup · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $399 · Startup · 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 | $4,030 · Startup · 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 | $1,195 · Startup · 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 | $2,570 · Startup · 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.
Intuned: Intuned bills compute in minutes, only while a machine executes a Run or JobRun. Developer costs $25 a month with 100 hours included and $0.12 an hour after that, Startup costs $120 a month with 500 hours and $0.10 an hour, Large and X-Large machines add a surcharge per hour, and JobRuns past the plan's allowance and AI usage are billed on top.
Limits in those scenarios
Intuned fits no scenario on this page as written, because each one asks for a general machine and Intuned runs browser automations with no shell or Docker. Its Runs stop at 6 hours, no machine keeps a disk, and the only size with 8 GB has a single vCPU, so the scenarios use its Large machine with 4 GB. Startup allows 100 machines per workspace and 15 per project, so 300 sandboxes for your users and 1,000 short jobs at once go into Enterprise. bochka fits every scenario except 1,000 short jobs at once, where its $2,000 plan queues the starts.
| Scenario | bochka | Intuned |
|---|---|---|
| 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 Intuned when
you want scrapers and browser automations written, scheduled, retried and repaired for you, on sites that need logins, stealth or CAPTCHAs, outside the EU as well.
- Scrapers built, run and repaired for you. For teams that want working scrapers without running them: an agent writes and fixes the code, and the platform schedules, queues and retries it.
- Built to get past bot checks. For sites with bot checks: a stealth Chromium, headful mode, CAPTCHA solving and a managed proxy pool.
- Many regions, billed only while running. Runs in 17 regions, from the US to Japan, and bills compute only while a machine is executing a Run.
Use bochka when
your agent does more than run a browser script: it needs a shell, Docker, a desktop or a server next to Chromium, runs for hours, and has to keep its work between runs.
- A whole machine around the browser. An Intuned machine runs Playwright functions in Python or TypeScript and nothing else. An agent that also needs to install tools, run Docker or use a desktop app has to do that work on a second service.
- Runs for as long as the work takes, and keeps its files. An Intuned Run stops at 6 hours unless support raises it, and each Run starts on a fresh machine. Only a key-value store and saved logins carry over, so installed tools and files start over every time.
- Coding agents you drive, with keys kept outside. Intuned's agent builds scrapers inside its own platform, and secrets reach your code as environment variables. An agent that writes code and calls APIs on its own needs its keys kept somewhere it cannot read.
Questions people ask
Is Intuned a sandbox like bochka?
No. Intuned is a platform that runs your Playwright functions as APIs on its own machines, with scheduling, retries and logins built in. You do not get a shell on the machine. bochka gives you a whole Linux VM with Chromium, a desktop, Docker and root, so the browser is one tool among many.
Is bochka cheaper than Intuned?
In all five scenarios on this page, yes: one coding agent on workdays costs $20 on bochka against $149, one agent running all month $26 against $399, 50 agents in parallel $317 against $4,030, 300 sandboxes for your users $200 against $1,195, and 1,000 short jobs at once $2,000 against $2,570. Intuned fits none of them as a general machine, and for short scrapers it bills only the minutes they run.
How long can an Intuned Run last?
Each attempt times out after 10 minutes by default, and your code can extend it up to 6 hours per Run. For longer automations Intuned asks you to contact support. A bochka sandbox has no session cap on paid plans.
Can I run Playwright scrapers on bochka?
Yes. Each bochka sandbox has Chromium and a full Linux system, so you can install Playwright in Python or Node and run scrapers on a schedule you set up yourself. You handle retries and logins in your own code, and the disk keeps your caches and browser profiles between runs.
Which one is better at getting past bot checks?
Intuned. It has a stealth Chromium, headful mode, CAPTCHA solving and a managed proxy pool, though it calls stealth and CAPTCHA solving experimental. bochka runs Chromium on datacenter IPs.
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