Docker Cloud Sandboxes vs AWS AgentCore

Docker Cloud Sandboxes puts the same sbx coding-agent microVM you run on your laptop into the cloud, for up to 24 hours at a time. AWS AgentCore is an AWS platform that hosts your agent code in 2 vCPU microVM sessions and adds managed Code Interpreter and Browser tools inside your AWS account.

The companies and products

Docker Cloud Sandboxes

Docker Cloud Sandboxes runs Docker's sbx coding-agent microVMs on Docker-managed compute instead of your laptop.

Each sandbox is a microVM with its own Linux kernel and its own Docker Engine, started from the same sbx CLI you use locally, with Claude Code, Codex and other agents ready to run. You can move a sandbox from your laptop to the cloud and back, publish HTTPS ports and SSH in. It launched on September 24, 2026, is billed pay-as-you-go on a personal Docker account, and is built for developers who want their local agent sandboxes to keep going off their machine.

Isolation: MicroVM per sandbox with its own Linux kernel and its own Docker Engine
Launched: September 24, 2026
Machine sizes: 1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, CPU only, amd64 or arm64 by account
Session length: 1 hour by default, extendable to 24 hours from creation
Default quota: 10 concurrent and 50 stored sandboxes per account
Account: Pay-as-you-go plan on a personal Docker account, even inside an organization
Regions: Not published

AWS AgentCore

Amazon Bedrock AgentCore is a set of AWS services to deploy and run AI agents: a Runtime that hosts your agent code, plus built-in Code Interpreter and Browser tools.

AgentCore is not a sandbox product first. It is a hyperscaler's agent platform: you push a container image or code, and each Runtime session gets its own Firecracker microVM that you reach through AgentCore APIs. Around it sit managed tools (Code Interpreter, Browser) and services for memory, identity, gateways and evaluations, and an Instances compute type runs longer sessions on EC2 in your own account. It is built for teams who already build on AWS and want agents to stay inside their account, IAM and VPC.

Isolation: Runtime: a dedicated microVM per session; Code Interpreter and Browser run in a containerized environment
Session size: Runtime and Code Interpreter up to 2 vCPU / 8 GB, Browser 1 vCPU / 4 GB, not adjustable
Session length: Up to 8 hours per lifecycle on microVMs, 15 minutes idle by default; up to 14 days on Instances
Compute types: Serverless microVMs (arm64 Linux containers) or Instances: AWS-managed EC2 in your account, x86_64 or arm64, GPUs available
Regions: 17 commercial AWS regions across the US, EU, Asia Pacific, Canada and South America, plus GovCloud
Compliance: Listed as a HIPAA eligible AWS service

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. “280th cheapest of 367” means 279 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	Docker Cloud Sandboxes: price rank	AWS AgentCore: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Coding agents that run for days hit Docker's 24-hour cap and 10-at-once quota, and AgentCore's 8-hour, 2 vCPU microVM sessions; bochka ranks 3rd here with no session cap.	280th of 367, with limits $4,928 a month	100th of 367, with limits $888 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on its machine all month outlasts both Docker's 24-hour sessions and AgentCore's 8-hour microVMs, so on AgentCore it needs the Instances type on EC2.	276th of 366, with limits $5,110 a month	64th of 366, with limits $1,300 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 AWS AgentCore ranks 7th here: Code Interpreter is built for short code runs and bills only for CPU actually used.	119th of 345, with limits $233 a month	7th cheapest of 345 $114 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 Serving your users needs more than Docker's default 10 at once, and AgentCore sessions have no open ports for users to see their app; bochka ranks 1st here.	136th of 361, with limits $1,628 a month	210th of 361, with limits $506 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	114th of 360, with limits $7,000 a month	125th of 360, with limits $8,075 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	167th of 364, with limits $1,400 a month	33rd cheapest of 364 $650 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 CI that builds Android apps or VM images needs /dev/kvm, which bochka exposes and neither Docker nor AgentCore documents.	172nd of 377, with limits $672 a month	52nd cheapest of 377 $399 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box that stays on all month needs no session cap and a disk that keeps installed packages, which neither Docker's 24-hour sessions nor AgentCore's 1 GB storage mount gives.	127th of 368, with limits $204 a month	228th of 368, with limits $52 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 Computer-use agents need a screen: Docker's sandboxes are terminal only, AgentCore Browser drives a browser but not a desktop, and bochka streams a full Linux desktop at 60fps.	268th of 369, with limits $1,400 a month	104th of 369, with limits $202 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 AWS AgentCore ranks 4th here with a managed Chromium that has live view and replay, while Docker's sandboxes have no browser at all.	277th of 367, with limits $700 a month	4th cheapest of 367 $144 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	262nd of 346, with limits $350 a month	27th cheapest of 346 $287 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	190th of 338, with limits $7,000 a month	165th of 338, with limits $5,458 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	248th of 360, with limits $350 a month	62nd of 360, with limits $294 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 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	Can't run it	Can't run it	Can't run it

Key features

Feature	Docker Cloud Sandboxes	AWS AgentCore	bochka
What it is	Docker's sbx coding-agent microVMs, run on Docker-managed compute	An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools	A sandbox platform: each agent gets its own full Linux machine
Isolation	MicroVM per sandbox with its own Linux kernel and Docker Engine; hypervisor not named	Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Biggest machine	1 vCPU / 2 GiB up to 16 vCPU / 32 GiB, CPU only	2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances	Up to 16 vCPU / 32 GB on the $100 plan and above
Session length	1 hour by default, at most 24 hours from creation	Up to 8 hours per microVM lifecycle, stopped after 15 idle minutes by default; up to 14 days on Instances	No cap on paid plans; you set the time to live
Sandboxes at once	10 by default; no published way to raise it	1,000 Code Interpreter or Browser sessions, adjustable by support ticket; 5,000 active Runtime sessions in us-east-1 and us-west-2	100 on the $20 plan, up to 2,000 on higher plans, self-serve
Stop, resume and fork	Stop keeps memory and files; snapshot a running sandbox with its memory and restore it as a new one	No pause, snapshot or fork; only a storage mount under /mnt, up to 1 GB, survives a stop	Whole disk saved every minute and on stop; fork a running sandbox with its disk
Docker, systemd and /dev/kvm	Its own Docker Engine inside; nested virtualization not documented	Root inside the microVM with arm64 container images; Docker and /dev/kvm not documented	Root, Docker, systemd and /dev/kvm for Android emulators and VMs
Inbound access	Public HTTPS URL per published port; SSH with Docker-issued certificates	No open ports or SSH; sessions are reached only through AgentCore APIs	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; SSH
Network controls	Allow and deny rules by host, with allow-all, balanced and deny-all presets	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP	Open internet, no provider-side allowlist
Browser and desktop	Terminal sessions only	Managed Chromium with live view, session recording and replay; no full desktop	Full Linux desktop streamed at 60fps, with Chromium and computer use
Coding agents	Claude Code, Codex, Copilot, OpenCode and more, attached to from the sbx CLI	AWS's managed harness built on Strands Agents, or your own agent code	Claude Code, Codex and five more preinstalled, with a prompt, steer and events API
Keeping API keys out of the sandbox	Cloud proxy sets the auth header for built-in AI services and custom hosts	AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
GPUs	No, CPU only	NVIDIA G-series and Inferentia2 on the Instances type	No
Regions	Not published	17 commercial AWS regions plus GovCloud	EU only (Germany, Finland, France)

Every feature Battleships tracks (43)

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

Performance

Docker Cloud SandboxesNot measured

AWS AgentCoreNot measured

bochka26.69 runs/s

Neither Docker Cloud Sandboxes nor AWS AgentCore has a comparable measurement: neither was part of the hpc-sandbox-benchmarks runs, and Docker does not say what hardware it uses. bochka did 26.69 runs per second on the Node.js build-and-test benchmark at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Docker Cloud Sandboxes and AWS AgentCore have 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	Docker Cloud Sandboxes, a month	AWS AgentCore, 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	$49 · Docker Agentic Platform (pay-as-you-go)	$26 · Pay-as-you-go (Instances) · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$204 · Docker Agentic Platform (pay-as-you-go) · with limits	$107 · Pay-as-you-go (Instances) · 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	$2,464 · Docker Agentic Platform (pay-as-you-go) · with limits	$1,286 · Pay-as-you-go (Instances) · 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	$700 · Docker Agentic Platform (pay-as-you-go) · with limits	$423 · Pay-as-you-go · with limits	$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	$1,400 · Docker Agentic Platform (pay-as-you-go) · with limits	$1,615 · Pay-as-you-go (Instances)	$2,000 · $2000/mo · with limits

Docker Cloud Sandboxes: Docker bills per second for the size you pick, from $0.07 an hour for 1 vCPU / 2 GiB to $1.12 an hour for 16 vCPU / 32 GiB, with no monthly fee. A stopped sandbox costs nothing, and volumes and egress are free.

AWS AgentCore: Runtime microVMs, Code Interpreter and Browser bill per second for CPU actually used and for peak memory. The 4 vCPU shape in these scenarios is the Instances type: the EC2 on-demand price plus a 12% management fee, with storage and data transfer on top.

AWS AgentCore: 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.

Limits in those scenarios

Docker's default of 10 sandboxes at once rules it out for 50 agents in parallel, sandboxes for your users and 1,000 short jobs at once, and its 24-hour cap rules out one agent that never stops. AgentCore keeps files only in its storage mount, so installed packages reset after a stop, and its 4 vCPU shape needs the Instances type on EC2. AgentCore is the only one of the three that fits 1,000 short jobs at once; bochka queues starts above 90 per minute even on the $2,000 plan.

Scenario	Docker Cloud Sandboxes	AWS AgentCore	bochka
One coding agent, workdays	None that bite	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	None that bite
One agent that never stops	Docker Agentic Platform (pay-as-you-go): sessions capped at 24 h	Pay-as-you-go (Instances): sessions capped at 336 h files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	None that bite
50 agents in parallel	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	None that bite
Sandboxes for your users	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	different kind of product: code interpreter	None that bite
1,000 short jobs at once	Docker Agentic Platform (pay-as-you-go): max 10 concurrent	disk beyond 0 GiB: price unknown	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 Docker Cloud Sandboxes when

you already run agents in sbx on your laptop and want a few of them to keep going in the cloud for up to a day, with memory kept across stops and outbound rules by host.

Stop and fork with memory. For agents that pause between steps, a stopped sandbox comes back with its memory, and you can fork one with its memory.
The same sandbox on your laptop. If you already run sbx locally, the cloud is the same microVM and CLI, and you can move a sandbox either way.
Bigger machines with open ports. Agents that need up to 16 vCPU, Docker inside, a public HTTPS port or SSH get them without leaving the sandbox.

Use AWS AgentCore when

your agents must stay inside your AWS account and VPC, need a GPU, or are short code and browser tasks that fit its managed tools.

It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC and PrivateLink, in 17 commercial regions.
GPUs and two-week sessions on Instances. Agents that need a GPU or a session of up to 14 days can run on EC2 in your account.
Managed tools for short tasks. For quick code runs and browser tasks, Code Interpreter and Browser bill only for CPU used and run 1,000 sessions at once.

Where bochka fits

Both cap how long one agent can run: Docker at 24 hours, AgentCore's microVMs at 8. If your agents work for days, need a whole machine with Docker, emulators or a desktop, or have to be driven and opened from your own app, look at bochka instead.

Runs as long and as wide as the work

bochka has no session cap on paid plans and runs 100 at once on the $20 plan. Docker ends a sandbox at 24 hours and allows 10 at a time; AgentCore stops at 8 hours unless you move to Instances and run EC2 in your account.

A whole machine, screen included

bochka gives root, Docker, systemd, /dev/kvm and a 60fps desktop with Chromium. Docker's sandboxes are terminal only, and AgentCore keeps just a 1 GB mount across stops, so installed packages reset and every resume repeats the setup.

Drive agents inside from outside, and open their app

bochka runs seven agents behind a prompt, steer and events API, with HTTPS on 50 ports. On Docker you attach to an agent's terminal and parse its text; AgentCore has no open ports, so you proxy previews through your own code.

Use bochka when your agents do real work on a machine for days or by the dozen: installs, builds, Docker, emulators and a desktop, with a disk that keeps everything, a URL you can open and an API to drive them. Compare it one to one: bochka vs Docker Cloud Sandboxes and bochka vs AWS AgentCore.

Questions people ask

Is Docker Cloud Sandboxes cheaper than AWS AgentCore?

For one coding agent on workdays, AgentCore lists $26 a month against $49 on Docker, but AgentCore does not fit because packages outside its storage mount reset. For 1,000 short jobs at once, AgentCore fits at $1,615 a month, and Docker's 10-at-once quota rules it out. bochka runs the workday agent for $20 a month.

Which is faster, Docker Cloud Sandboxes or AWS AgentCore?

There is no comparable measurement for either one. bochka did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js test at 4 vCPU / 8 GB. An AgentCore microVM session stops at 2 vCPU, so a like-for-like test would need its Instances type.

How long can a session run on each?

A Docker cloud sandbox runs 1 hour by default and at most 24 hours from creation. An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default, or up to 14 days on the Instances type. bochka has no session cap on paid plans.

Can Docker Cloud Sandboxes or AgentCore run Docker inside?

Each Docker cloud sandbox has its own Docker Engine. AgentCore runs your arm64 container image as root, but its docs do not say Docker or /dev/kvm work inside a session. bochka runs Docker with systemd and exposes /dev/kvm for Android emulators and VMs.

Can I open a port or SSH into the sandbox?

Docker gives a public HTTPS URL per published port and SSH with Docker-issued certificates. AgentCore sessions have no open ports or SSH and are reached only through its APIs. bochka gives HTTPS URLs on up to 50 ports, raw TCP and SSH.

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