AWS AgentCore vs Agent 37

AWS AgentCore is the part of AWS that hosts agents in short microVM sessions, with a managed code interpreter and browser. Agent 37 gives each user an always-on sandbox that sleeps when idle, keeps its memory and wakes on the next message.

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

Agent 37

Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.

You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor; a VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.

Isolation: gVisor by default; opt-in full VM type with its own kernel and KVM
Where it runs: Dedicated servers in the United States
Billing: Prepaid wallet, metered per minute, no plan fee or seat charge
Instance types: Default (shared), Performance (dedicated cores), VM
Compliance: SOC 2 Type I, Type II in progress
Company: Y Combinator company based in New York

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	Agent 37: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month AgentCore microVM sessions stop at 2 vCPU and 8 hours and keep only a storage mount; Agent 37 needs its VM type for Docker, and bochka gives every agent Docker and systemd on a full VM.	100th of 367, with limits $888 a month	2nd cheapest of 367 $551 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 all month outlasts AgentCore's 8-hour microVM lifecycle, while Agent 37 is built for it: it sleeps when idle and wakes on the next message, and bochka keeps a full VM running.	64th of 366, with limits $1,300 a month	Cheapest of 366 $279 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 Both fit short code runs well: AgentCore Code Interpreter bills only for CPU used, and Agent 37's small default sandboxes cost little; bochka's start limits make large bursts a poor fit.	7th cheapest of 345 $114 a month	Cheapest of 345 $22 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 AgentCore sessions have no open ports, and Agent 37 caps self-serve accounts at 200 instances counting sleeping ones; bochka gives each user HTTPS URLs on up to 50 ports.	210th of 361, with limits $506 a month	30th of 361, with limits $79 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	125th of 360, with limits $8,075 a month	6th of 360, with limits $363 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	90th of 364, with limits $58 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	52nd cheapest of 377 $399 a month	2nd cheapest of 377 $84 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB AgentCore has no SSH and resets files outside its storage mount after a stop; Agent 37 and bochka both keep a machine and its disk around the clock.	228th of 368, with limits $52 a month	3rd cheapest of 368 $12 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 AgentCore Browser drives a browser, not a whole desktop; Agent 37 adds a noVNC desktop through a template build, and bochka streams a 60fps desktop out of the box.	104th of 369, with limits $202 a month	Cheapest of 369 $53 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 AgentCore Browser is a managed Chromium with live view and session replay, which suits this work; bochka runs Chromium on a full machine you control.	4th cheapest of 367 $144 a month	48th of 367, with limits $29 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	27th cheapest of 346 $287 a month	Cheapest of 346 $32 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	165th of 338, with limits $5,458 a month	36th of 338, with limits $648 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 Neither AgentCore nor Agent 37 can fork a session; bochka can fork a running sandbox to try many attack paths from the same state.	62nd of 360, with limits $294 a month	Cheapest of 360 $43 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	Agent 37	bochka
What it is	An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools	One isolated, always-on sandbox per user, behind one API	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	gVisor by default; full VM as an opt-in instance type	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	Shapes up to 16 vCPU / 32 GB after the first top-up	Up to 16 vCPU / 32 GB on the $100 plan and above
Session length	Up to 8 hours per microVM lifecycle, 15 idle minutes by default; up to 14 days on Instances	No time limit; runs until you stop it or it sleeps on idle	No cap on paid plans; you set the time to live
What survives a stop	Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances	The disk, plus memory checkpointed on auto-sleep	The whole disk, saved every minute and on stop; a resume reboots
Snapshots and fork	No user snapshots or fork of a session	No fork; daily backups plus one on-demand backup, restored in place only	Snapshots every minute; fork a running sandbox; named snapshots as templates
Docker and /dev/kvm	Root inside the microVM; Docker and /dev/kvm not documented	Only on the VM type, at 2.5x the default compute rate	Docker, systemd and /dev/kvm in every sandbox
Inbound access	No open ports or SSH; reached only through AgentCore APIs with IAM or JWT	HTTPS URL per port, custom domains; SSH through a WebSocket tunnel	HTTPS URLs for up to 50 ports, raw TCP and SSH
Network controls	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP	Open internet, no egress allowlist	Open internet, no provider-side allowlist
Browser and desktop	Managed Chromium with live view, recording and replay; no full desktop	noVNC desktop through a template build or the Ubuntu VM template	60fps desktop and Chromium in every sandbox, embeddable stream
Coding agents	AWS's managed harness built on Strands Agents, or your own agent code	Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API	Claude Code, Codex and five more, with a prompt, steer and events API
Keeping API keys out of the sandbox	AgentCore Identity stores tokens and keys and hands them to your agent code	Managed LLM, search and Composio through a token; your own keys go in as env vars	Credentials proxy for model providers and any HTTPS API, with account switching
GPUs	NVIDIA G-series and Inferentia2 on the Instances type	No	No
Regions	17 commercial AWS regions plus GovCloud	United States	EU only (Germany, Finland, France), EU data residency

Every feature Battleships tracks (43)

Feature	AWS AgentCore	Agent 37	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	Not published	No	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	No	Not published	Yes
Desktop GUI	No	Yes	Yes
Browser	Yes	Yes	Yes
Computer-use API	Yes	Yes	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	No	Yes	Yes
Automatic snapshots	No	Yes	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	No	No	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	Yes	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	No	Not published	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	No	No
Secret proxy	No	Yes	Yes
Secret proxy for any API	No	No	Yes
Preinstalled agents	No	Yes	Yes
Agent harness API	No	Yes	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	Yes	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Yes	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	Yes	No	No
EU data residency	Yes	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

AWS AgentCoreNot measured

Agent 37Not measured

bochka26.69 runs/s

There is no comparable measurement for either: neither AWS AgentCore nor Agent 37 was part of the hpc-sandbox-benchmarks run. bochka did 26.69 runs per second on its Node.js build-and-test loop at 4 vCPU / 8 GB. Agent 37 says its default instances share host resources, and an AgentCore microVM stops 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. AWS AgentCore and Agent 37 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	AWS AgentCore, a month	Agent 37, 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	$6 · Wallet (any top-up)	$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	$12 · Wallet (any top-up)	$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	$329 · Wallet ($100 lifetime top-ups)	$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	$33 · Wallet ($250 lifetime top-ups) · 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	$1,615 · Pay-as-you-go (Instances)	$73 · Wallet ($250 lifetime top-ups) · 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 storage and data transfer on top.

Agent 37: A prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while asleep. Performance compute costs 4x and VM compute 2.5x the default rate.

Agent 37: 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

AgentCore's microVM sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU scenarios run on the Instances type, and files outside the storage mount reset after a stop, so it does not fit the coding, always-on and fleet scenarios. Agent 37 caps self-serve accounts at 200 instances, counting sleeping and stopped ones, which stops it at 300 user sandboxes and 1,000 jobs at once. The fleet scenario needs Docker, so Agent 37 is priced on its VM type there. bochka fits all but the 1,000-job burst, where its plans queue starts above 90 per minute.

Scenario	AWS AgentCore	Agent 37	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	egress price not published	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	egress price not published	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	egress price not published	None that bite
Sandboxes for your users	different kind of product: code interpreter	max 200 concurrent egress price not published	None that bite
1,000 short jobs at once	disk beyond 0 GiB: price unknown	max 200 concurrent shared vCPUs on this tier: heavy, sustained CPU use can be slowed by other tenants egress price not published	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.
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 that bill only for what they use. For short code runs and browser tasks, Code Interpreter and Browser charge only for CPU used, with live view and replay.

Use Agent 37 when

you host one mostly idle assistant per customer in the US that should sleep with its memory kept and wake on the next message.

Sleeps when idle and keeps its memory. Useful for assistants that sit idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
A persistent machine per user. Each user gets an always-on sandbox with SSH, HTTPS URLs and a chat API, with no session time limit.
Bring a Dockerfile, pick dedicated cores. Agent 37 builds templates from your own Docker image, and sells a Performance type on dedicated cores.

Where bochka fits

If your agents do real work on a machine for hours, look at bochka. Every sandbox is a full VM with Docker, systemd and /dev/kvm, a disk saved every minute, forks of running machines and URLs you can open. It runs in the EU.

A full VM by default, not an add-on

AgentCore does not document Docker or /dev/kvm in its microVMs, and Agent 37's default gVisor type cannot run Docker. Its VM type can, at 2.5 times the compute rate and with no init system.

Fork a machine while it runs

Neither AgentCore nor Agent 37 can fork a session, so trying three fixes from one half-done state means rebuilding that state three times. Agent 37 backups only restore onto the same instance.

Open the app, keep the keys outside

AgentCore sessions have no open ports, so you proxy a dev server through your own code. On Agent 37 your own API keys sit inside the machine; bochka's proxy keeps them out for any HTTPS API.

Use bochka when your agents do real work for hours: installs, builds, tests, Docker and emulators on a full VM, with forks of running machines, URLs you can open and keys kept outside. Compare it one to one: bochka vs AWS AgentCore and bochka vs Agent 37.

Questions people ask

Is AWS AgentCore cheaper than Agent 37?

No, Agent 37 costs less in every scenario on this page: one agent that never stops is $107 a month on AgentCore against $12 on Agent 37. AgentCore is the only one of the two that fits 1,000 short jobs at once, at $1615 a month.

Which is faster, AWS AgentCore or Agent 37?

Neither has a result on the hpc-sandbox-benchmarks run, so there is no fair comparison. An AgentCore microVM session tops out at 2 vCPU, and Agent 37 sells dedicated cores on its Performance type. bochka did 26.69 runs per second at 4 vCPU / 8 GB.

Can AWS AgentCore or Agent 37 run Docker?

AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker works inside a session. Agent 37 runs Docker only on its VM type, at 2.5x the default compute rate. bochka runs Docker in every sandbox.

How long can a session run on AWS AgentCore and Agent 37?

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. Agent 37 has no time limit and can sleep on idle. bochka has no session cap on paid plans.

Where do AWS AgentCore and Agent 37 run?

AgentCore runs in 17 commercial AWS regions plus GovCloud. Agent 37 runs on dedicated servers in the United States. bochka runs only in the EU, in Germany, Finland and France.

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