AWS AgentCore vs Islo

AgentCore is an AWS platform that hosts agents in short microVM sessions, with a managed Code Interpreter and Browser, inside your AWS account. Islo gives each coding agent its own VM that keeps running, with Docker, SSH and a gateway that controls and logs every outbound call.

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

Islo

Islo is an agent sandbox from Incredibuild: each coding agent gets its own microVM, with network rules and credentials handled at a gateway.

An Islo sandbox is a Linux microVM with its own kernel, built from a container image, with Claude Code, Cursor CLI and Codex preinstalled. Outbound traffic can pass through a gateway that allows or blocks hosts, injects credentials and logs every request. It is built for teams that run coding agents, evals and RL rollouts in the background, on Islo's cloud or in their own cloud account.

Maker: Incredibuild, a build acceleration company based in Tel Aviv
Launched: May 4, 2026
Isolation: A microVM with its own kernel for each agent computer
Regions: US West on Islo's cloud; BYOC puts the control plane and sandboxes in your own cloud account
Billing: CPU per core, memory per GB and disk per GB while a sandbox runs, billed per hour; signup credits with no card
Compliance: No certification named on its site; compliance documents on request from support

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	Islo: 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 on AgentCore stops after 8 hours and keeps only its storage mount, while Islo keeps a VM with Docker running; bochka adds /dev/kvm and a desktop on a full machine.	100th of 367, with limits $888 a month	326th of 367, with limits $7,402 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Islo fits an assistant that lives on one machine all month and can pause it with its memory; AgentCore needs the Instances type on EC2 for that, and bochka simply keeps running.	64th of 366, with limits $1,300 a month	30th cheapest of 366 $9,928 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 AgentCore Code Interpreter is built for short code runs and bills only CPU actually used, which suits this better than Islo or bochka.	7th cheapest of 345 $114 a month	153rd of 345, with limits $503 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 300 sandboxes for your users is more than the 50 reported for Islo's Team plan, AgentCore sessions have no open ports for users, and bochka gives each one HTTPS URLs on up to 50 ports.	210th of 361, with limits $506 a month	171st of 361, with limits $3,160 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	167th of 360, with limits $15,265 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 Islo has a Harbor integration and gateway rules that stop trials from looking up answers; AgentCore fits short eval runs in its managed sessions, and bochka runs more sandboxes at once.	33rd cheapest of 364 $650 a month	198th of 364, with limits $2,456 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	119th cheapest of 377 $1,507 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Islo gives a dev box SSH and a VM that keeps running; AgentCore has no SSH and resets everything outside its storage mount after a stop.	228th of 368, with limits $52 a month	112th cheapest of 368 $402 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 Neither gives an agent a full desktop: AgentCore Browser drives only a browser and Islo is headless, while bochka streams a 60fps Linux desktop with a computer-use API.	104th of 369, with limits $202 a month	310th of 369, with limits $2,210 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, Islo has a browser only for testing inside the sandbox, and bochka runs Chromium on a full machine.	4th cheapest of 367 $144 a month	113th of 367, with limits $1,105 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	66th cheapest of 346 $748 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	265th of 338, with limits $14,966 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	62nd of 360, with limits $294 a month	47th of 360, with limits $746 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	Islo	bochka
What it is	An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools	An agent sandbox from Incredibuild: a microVM per coding agent with a network gateway	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	A microVM with its own kernel for each sandbox	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Session length	Up to 8 hours per microVM lifecycle, stopped after 15 idle minutes by default; up to 14 days on Instances	No published cap; a sandbox runs until you stop it or its pause timer fires	No cap on paid plans; you set the time to live
Session size	2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances	You choose CPU cores, memory and disk per sandbox, billed per unit	Up to 16 vCPU / 32 GB on the $100 plan and above
What survives a stop	Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances; the rest resets	Pause keeps files, processes and memory; snapshots of a sandbox's files	The whole disk, saved every minute and on stop; a stopped sandbox costs nothing
Fork	No user snapshots or fork of a session	Snapshot a running sandbox's files, then start new sandboxes from it	Fork a running sandbox with its disk
Docker and /dev/kvm	Root inside the microVM; arm64 container images; Docker and /dev/kvm not documented	Docker inside and sudo; no /dev/kvm or nested virtualization documented	Root, Docker, systemd and /dev/kvm on every machine
Reaching the sandbox	No open ports or SSH; reached only through AgentCore APIs with IAM or JWT	SSH and port-forward through the CLI; HTTPS share links that expire after 24 hours by default	HTTPS URLs for up to 50 ports, token-protected; raw TCP; SSH
Outbound internet rules	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP	Gateway rules by host, path and HTTP method, with default deny, rate limits and a log of every request	Open internet, no provider-side allowlist
Keeping keys out of the sandbox	AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code	Gateway injects stored credentials into outbound requests; keys never reach the sandbox	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Browser and desktop	Managed Chromium with live view, session recording and replay; no full desktop	A browser inside the sandbox for testing; no desktop or computer-use API	Full Linux desktop streamed at 60fps, with Chromium and computer use
Coding agents	AWS's own managed harness built on Strands Agents, or your own agent code	Claude Code, Cursor CLI and Codex preinstalled, with automations on schedules, webhooks and GitHub, Slack and Linear events	Claude Code, Codex and more preinstalled, with a prompt, steer and events API
GPUs	NVIDIA G-series and Inferentia2 on the Instances type	No	No
Regions	17 commercial AWS regions plus GovCloud	US West, or your own cloud account with BYOC	EU only (Germany, Finland, France), with EU data residency

Every feature Battleships tracks (43)

Feature	AWS AgentCore	Islo	bochka
Full VM (own kernel)	Yes	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	No	Not published	Yes
Desktop GUI	No	No	Yes
Browser	Yes	Yes	Yes
Computer-use API	Yes	No	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	No	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	No	Yes	Yes
Secret proxy for any API	No	Yes	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	Yes	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	Yes	Yes
Audit logs	Yes	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Not published	No
HIPAA	Yes	Not published	No
EU data residency	Yes	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

AWS AgentCoreNot measured

IsloNot measured

bochka26.69 runs/s

There is no comparable measurement for either: AgentCore and Islo were not part of the public sandbox benchmark run we use. In StarSling's run of 2026-09-29, bochka did 26.69 Node.js build-and-test runs per second 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. AWS AgentCore and Islo 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	Islo, 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	$101 · Free	$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	$420 · Free	$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	$4,863 · Team	$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	$1,382 · Team · 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)	$3,053 · 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 billed by AWS on top.

Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, with no plan fee. An idle sandbox keeps billing until a pause-after-idle timer fires, that timer is set only at creation, and egress has no published price.

Islo: Plans start at $20 a month, and the whole fee is usage credit spent per second while a sandbox runs. 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, which still resets packages installed outside the storage mount and caps a session at 14 days. Islo's Team plan is reported at 50 running sandboxes at once, so 300 sandboxes for your users and 1,000 short jobs at once do not fit without a custom contract. AgentCore is the only one of the three that fits the 1,000-job burst; bochka queues starts above 90 per minute there.

Scenario	AWS AgentCore	Islo	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	Team: max 50 concurrent egress price not published	None that bite
1,000 short jobs at once	disk beyond 0 GiB: price unknown	Team: max 50 concurrent 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 and PrivateLink, in 17 commercial regions plus GovCloud.
Managed tools for short tasks. For quick code runs and browser tasks, Code Interpreter and Browser bill only CPU actually used, with live view and replay.
GPUs and two-week sessions. Agents that need a GPU or a session of up to 14 days can run on the Instances type, on EC2 in your account.

Use Islo when

your coding agents run for hours and you need per-host egress rules with a log of every call, pause with memory, or a US region or your own cloud account.

A VM that keeps running. Coding agents get a VM with Docker and SSH that runs as long as the work takes, with no 8-hour stop.
Egress rules and request logs. Useful if you must control what agents reach: the gateway allows or blocks each host, path and method, and logs every call.
Pause with memory, wake on request. Idle agents pause with files, processes and memory kept, and resume on the next exec, file access or webhook.

Where bochka fits

If your agents do long, real work on a machine, such as installs, builds, emulators and a running app you want to open, look at bochka. It gives each agent a full VM with no session cap, a disk that keeps everything, a desktop and ports you can host on, which neither AgentCore nor Islo covers in full.

Emulators and VMs inside the sandbox

Neither AgentCore nor Islo documents /dev/kvm, so Android emulators and tools that start their own VMs stop at the first boot. bochka gives every machine root, Docker, systemd and /dev/kvm.

A desktop agents can see and use

AgentCore Browser drives only Chromium and Islo sandboxes are headless, so an agent cannot use other apps on a screen. On Islo you would install a VNC stack yourself; bochka streams a 60fps desktop with a computer-use API.

Open the app your agent is building

AgentCore sessions have no open ports, so you proxy traffic through your own code, and Islo share links expire after 24 hours by default. bochka gives each sandbox token-protected HTTPS URLs on up to 50 ports, plus raw TCP.

Use bochka when your agents need a whole machine for as long as the work takes: Docker, /dev/kvm, a 60fps desktop, ports you can host on and a disk that keeps everything, in the EU. Compare it one to one: bochka vs AWS AgentCore and bochka vs Islo.

Questions people ask

Is AWS AgentCore cheaper than Islo?

In the table, yes in every scenario, but AgentCore does not fit most of them: one coding agent on workdays is $26 on AgentCore against $101 on Islo, yet AgentCore resets installed packages after each stop. bochka comes to $20 for the same agent, and AgentCore is the only one that fits 1,000 short jobs at once, at $1,615 a month.

Which is faster, AgentCore or Islo?

We cannot say: neither was part of the public benchmark run we use. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run.

How long can a session run on AgentCore and on Islo?

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 in your account. Islo publishes no cap, so a sandbox runs until you stop it. bochka has no session cap on paid plans.

Can AgentCore or Islo run Docker?

Islo runs Docker inside its microVMs. AgentCore runs your arm64 container image as root, but its docs do not say Docker works inside a session. Neither documents /dev/kvm, which bochka exposes for Android emulators and VMs.

Can I control what an agent reaches on the internet?

Both can. AgentCore runs sessions in your VPC with security groups and a NAT gateway for a fixed outbound IP. Islo's gateway allows or blocks requests by host, path and HTTP method and logs each one. bochka has open internet with no provider-side allowlist.

Where do AgentCore and Islo run?

AgentCore runs in 17 commercial AWS regions plus GovCloud. Islo runs in US West, or inside your own cloud account with BYOC. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview