AWS AgentCore vs Modal VM Sandboxes

AgentCore is the part of AWS that hosts agents and gives them a managed code interpreter and browser, inside your own AWS account. Modal VM Sandboxes are real Linux VMs with Docker and systemd that you start from code and that end within 24 hours.

The companies and products

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

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. “7th cheapest of 345” means 6 of the other 344 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	AWS AgentCore: 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 A coding agent gets 2 vCPU and 8 hours per AgentCore microVM session and a full VM with Docker for up to 24 hours on Modal; bochka gives it a VM that keeps its whole disk with no session cap.	100th of 367, with limits $888 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 lives on one machine all month outlasts both: AgentCore needs its Instances type on EC2 in your account, Modal stops at 24 hours, and bochka simply keeps running.	64th of 366, with limits $1,300 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 AgentCore Code Interpreter is built for short code runs and bills only for CPU actually used, which makes it a strong fit here.	7th cheapest of 345 $114 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	210th of 361, with limits $506 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 Large bursts of short rollouts suit both platforms better than long sessions; bochka's per-plan start limits queue very large bursts.	125th of 360, with limits $8,075 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	33rd cheapest of 364 $650 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 Modal runs Docker builds in a real VM, while AgentCore does not document Docker inside a session; bochka runs Docker and exposes /dev/kvm on every plan.	52nd cheapest of 377 $399 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	228th of 368, with limits $52 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 AgentCore Browser drives a managed Chromium, Modal offers no desktop or browser, and bochka streams a full Linux desktop at 60fps.	104th of 369, with limits $202 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 AgentCore Browser is a managed Chromium with live view and session replay; Modal VM Sandboxes ship no browser, and bochka runs Chromium on a full machine.	4th cheapest of 367 $144 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	27th cheapest of 346 $287 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	165th of 338, with limits $5,458 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 Many parallel agents that need their own machine fit bochka best; both AgentCore and Modal only reach a compromise here.	62nd of 360, with limits $294 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	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	AWS AgentCore	Modal VM Sandboxes	bochka
What it is	An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools	Sandboxes inside Modal's serverless AI cloud, run as real VMs with runtime="vm"	A sandbox platform: each agent gets its own full Linux machine
Isolation	Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment	VM with its own Linux kernel on Cloud Hypervisor	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Biggest machine	2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances	Sized by the CPU and memory you request	Up to 16 vCPU / 32 GB on the $100 plan and above
CPU benchmark (4 vCPU / 8 GB)	Not measured	15.54 runs/s	26.69 runs/s
Longest session	8 hours per microVM lifecycle, 15 idle minutes by default; up to 14 days on Instances	24 hours (default 5 minutes)	No cap on paid plans; you set the time to live
What survives a stop	One storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances	Only Volumes and filesystem snapshots; a finished sandbox is gone	The whole disk, saved every minute and on stop
Snapshots and fork	No user snapshots or fork of a session	Filesystem snapshots boot new sandboxes; memory snapshots in alpha	Automatic snapshots every minute; fork a running sandbox with its disk
Docker, systemd and /dev/kvm	Root in the microVM; Docker and /dev/kvm not documented	Docker and systemd yes; nested virtualization on Team and Enterprise, on request	Root, Docker, systemd and /dev/kvm on every plan
Inbound access	No open ports or SSH; reached only through AgentCore APIs with IAM or JWT	Encrypted and raw TCP tunnels, connect tokens, inbound IP allowlist	HTTPS URLs for up to 50 ports, token-protected by default, plus raw TCP and SSH
Outbound network rules	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed IP	Block all, IP-range allowlist, domain allowlist (beta)	Open internet, no provider-side allowlist
Browser and desktop	Managed Chromium with live view, recording and replay; no full desktop	Not offered; an example shows how to set up Xvfb and VNC yourself	Full Linux desktop streamed at 60fps, with Chromium and computer use
Coding agents and API keys	Managed harness on Strands Agents; AgentCore Identity hands keys to your agent code	Examples only; secrets are environment variables or your own sidecar proxy	Claude Code, Codex and more preinstalled; credentials proxy keeps real keys out of the sandbox
GPUs	NVIDIA G-series and Inferentia2 on the Instances type	None on the VM runtime; GPU sandboxes need gVisor	None
Regions	17 commercial AWS regions plus GovCloud	US, EU and Asia-Pacific; pinning costs 1.15x to 1.75x	EU only (Germany, Finland, France)

Every feature Battleships tracks (43)

Feature	AWS AgentCore	Modal VM Sandboxes	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	Yes	Yes
Root	Yes	Yes	Yes
Systemd	No	Yes	Yes
Desktop GUI	No	No	Yes
Browser	Yes	No	Yes
Computer-use API	Yes	No	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	No	No	Yes
Automatic snapshots	No	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	No	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	Yes	No	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	No	Yes	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	No	No	Yes
Secret proxy for any API	No	No	Yes
Preinstalled agents	No	No	Yes
Agent harness API	No	No	Yes
MCP server	Yes	No	No
GPU	Yes	No	No
Windows	No	No	No
Arm64	Yes	No	No
Self-hosting	No	No	No
BYOC	Yes	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	Yes	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

AWS AgentCoreNot measured

Modal VM Sandboxes15.54 runs/s

bochka26.69 runs/s

In the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB on 29 September 2026, bochka did 26.69 runs per second and Modal's VM runtime 15.54, so bochka did about 1.7 times the CPU work in the same time. AgentCore has no comparable measurement: it was not part of that run, and its microVM sessions stop at 2 vCPU.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Modal VM Sandboxes measured on: VM Sandbox, request = size. AWS AgentCore 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	AWS AgentCore, 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	$26 · Pay-as-you-go (Instances) · with limits	$15 · Starter · with limits	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$107 · Pay-as-you-go (Instances) · 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	$1,286 · Pay-as-you-go (Instances) · with limits	$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	$423 · Pay-as-you-go · with limits	$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	$1,615 · Pay-as-you-go (Instances)	$3,193 · Team · with limits	$2,000 · $2000/mo · with limits

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 EBS storage and data transfer on top.

Modal VM Sandboxes: Modal bills by the second for whichever is higher, 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 pinning a region costs 1.15x to 1.75x.

Modal VM Sandboxes: Plans start at $20 a month and the whole fee becomes usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

AgentCore microVM sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU scenarios use the Instances type, and files outside the storage mount reset on a stop. Modal VMs end within 24 hours and keep only what is in a Volume, so the workday, always-on and fleet scenarios do not fit on either. For 1,000 short jobs at once AgentCore fits, Modal's small tier shares its vCPUs, and bochka's $2000 plan queues starts above 90 per minute.

Scenario	AWS AgentCore	Modal VM Sandboxes	bochka
One coding agent, workdays	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
One agent that never stops	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	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
50 agents in parallel	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	files survive a stop only in Volumes: packages installed elsewhere reset	None that bite
Sandboxes for your users	different kind of product: code interpreter	None that bite	None that bite
1,000 short jobs at once	disk beyond 0 GiB: price unknown	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 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 the managed tools.

It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC, security groups and PrivateLink, in 17 commercial regions.
Managed tools that bill only for use. For short code runs and browser tasks, Code Interpreter and Browser charge only for CPU used, with live view and replay.
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 own account.

Use Modal VM Sandboxes when

you need Docker in a real VM for jobs that finish within a day, run huge bursts of short sandboxes, or already run your models on Modal.

A real VM with Docker. Each sandbox has its own Linux kernel, so Docker, FUSE and systemd work, which AgentCore does not document.
Very large bursts of short jobs. Modal runs 5,000 containers at once on Team, with filesystem snapshots to boot many sandboxes from one state.
One platform with inference and training. Teams that already serve or train models on Modal can put agent sandboxes on the same account and bill.

Where bochka fits

If your agents work on a machine for hours or days, installing, building, testing and coming back to the same state, both AgentCore and Modal cut them off and wipe most of the disk. bochka gives each agent a full VM that keeps its whole disk, runs as long as you want and can serve a URL you open.

No session cap, and the disk stays

AgentCore microVMs stop after 8 hours and keep only a 1 GB mount; Modal VMs end within 24 hours and keep only Volumes. Each restart repeats setup, unless you run EC2 on Instances or write snapshot code.

Docker, /dev/kvm and a faster CPU

AgentCore does not document Docker or /dev/kvm in a session, and Modal gives nested virtualization only on Team on request. In the same benchmark, bochka did 26.69 runs per second against Modal's 15.54.

Desktop, ports and agents ready to go

AgentCore has no open ports or SSH, and Modal has no desktop or browser. bochka ships a 60fps desktop, HTTPS on 50 ports, preinstalled coding agents you drive from outside, and a proxy that keeps API keys out.

Use bochka when your agents do real work on a machine for hours or days: installs, builds, tests, Docker, emulators and a desktop, on a faster VM that keeps its disk and a URL you can open. Compare it one to one: bochka vs AWS AgentCore and bochka vs Modal VM Sandboxes.

Questions people ask

Is AWS AgentCore cheaper than Modal VM Sandboxes?

In most of our scenarios, yes: one always-on agent is $107 a month on AgentCore against $178 on Modal, and 50 parallel agents $1,286 against $2,229. For one agent on workdays Modal is cheaper ($15 against $26), and on bochka these three are $20, $26 and $317 a month.

Which is faster, AgentCore or Modal VM Sandboxes?

Only Modal has a measurement: its VM runtime did 15.54 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB. AgentCore was not part of that run. bochka did 26.69 runs per second in the same run.

Can AgentCore or Modal run Docker?

Modal VM Sandboxes run Docker and systemd in a real VM; you start dockerd yourself. AgentCore runs your container image as root in a microVM, but its docs do not say Docker works inside a session. bochka runs Docker in every sandbox.

How long can a session run on each?

An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default; the Instances type runs up to 14 days on EC2. A Modal VM Sandbox lasts 5 minutes by default and 24 hours at most. bochka has no session cap on paid plans.

Do files survive when a session ends?

On AgentCore only a storage mount under /mnt of up to 1 GB, or EBS volumes on Instances. On Modal only Volumes and filesystem snapshots. bochka keeps the whole disk and saves it every minute.

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