Claude Managed Agents vs Islo

Claude Managed Agents is Anthropic's hosted agent: you send Claude a task and it works in a small container that Anthropic runs. Islo is a sandbox you rent: each coding agent, such as Claude Code, Cursor CLI or Codex, gets its own microVM, with a gateway that controls and logs what it reaches.

The companies and products

Claude Managed Agents

Claude Managed Agents is Anthropic's ready-made agent harness: Claude runs as an autonomous agent in a cloud sandbox that Anthropic manages, and you talk to it through an events API.

This is an agent platform, not a sandbox you rent. You define an agent (model, prompt, tools, MCP servers, skills) and an environment, then start sessions, send messages as events and stream back what Claude does; the harness handles tool calls, prompt caching and compaction. Each session gets its own Ubuntu container, or runs its tools on a worker you host yourself. It is built for teams that want Claude doing long tasks without building their own agent loop or sandbox.

Isolation: Each session gets its own isolated Linux container on Anthropic-managed infrastructure
Sandbox size: Ubuntu 24.04, x86_64, up to 8 GB memory and 10 GB disk; vCPU count not published
Models: Claude models only, through Anthropic's own harness
Billing: Model tokens at API rates, plus a session runtime fee that accrues only while a session is running
Self-hosted sandboxes: Tools can run on a worker in your own infrastructure while Anthropic keeps the orchestration
Data location: Workspace geo, which sets where data is stored and code runs, is US only today; inference can be global or US
Status: Beta, behind the managed-agents-2026-04-01 header; not eligible for Zero Data Retention or a HIPAA BAA

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. “106th cheapest of 367” means 105 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	Claude Managed Agents: 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 Islo runs Docker inside a microVM while Managed Agents lists Docker only in limited availability; neither documents /dev/kvm or a desktop, which bochka has on every sandbox.	106th of 367, with limits $964 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 Both suit agents that wait between tasks: Managed Agents bills nothing while a session is idle, and Islo can pause a sandbox with its memory and wake it on the next request.	219th of 366, with limits $2,511 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 Managed Agents bills runtime only while the agent works, so short bursts with long gaps cost little runtime, though model tokens come on top.	163rd of 345, with limits $756 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 Neither lets your users open what their sandbox runs on a stable private address: Managed Agents has no inbound ports and Islo share links are public and expire, while bochka gives token-protected HTTPS on up to 50 ports.	231st of 361, with limits $823 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	252nd of 360, with limits $3,978 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 built-in Harbor integration and gateway rules that stop trials from looking up answers; Managed Agents runs only Claude models, so it cannot evaluate other agents.	244th of 364, with limits $320 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 Islo gives a VM with Docker and sudo for CI jobs, Managed Agents is reached only through its sessions API, and bochka adds /dev/kvm for Android and VM image builds.	227th of 377, with limits $96 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 has SSH through its CLI and a disk that lasts; Managed Agents has no SSH and keeps sandbox state only 30 days after the sandbox is created.	224th of 368, with limits $48 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 Managed Agents ships headless Chromium and Islo a browser for testing, but neither has a desktop or a computer-use API; bochka streams a 60fps desktop agents can see and click.	127th of 369, with limits $288 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	126th of 367, with limits $288 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	127th of 346, with limits $390 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	155th of 338, with limits $4,798 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	179th of 360, with limits $160 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	Claude Managed Agents	Islo	bochka
What it is	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	An agent sandbox: each coding agent gets its own microVM, with network rules at a gateway	A sandbox platform: each agent gets its own full Linux machine, with coding agents built in
Isolation	Isolated Linux container per session	A microVM with its own kernel per sandbox	A full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Machine size	Up to 8 GB memory and 10 GB disk; vCPU not published; not configurable	You choose CPU cores, memory and disk, and pay for each while it runs	Up to 16 vCPU / 32 GB on the $100 plan and above
Docker, systemd and /dev/kvm	Docker listed as limited availability; root, systemd and /dev/kvm not documented	Docker inside and sudo; no /dev/kvm or nested virtualization documented	Root, Docker, systemd and /dev/kvm for Android emulators and VMs
Agents and models	Anthropic's harness with Claude models only, with caching, compaction, memory stores, multiagent threads and webhooks	Claude Code, Cursor CLI and Codex preinstalled; factory lines run agent steps on a schedule, a webhook or GitHub, Slack and Linear events	Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Idle time	An idle session is checkpointed, not billed, and resumes on the next message	Pause keeps files, processes and memory, and resumes on the next exec, file access or webhook; the idle timer is set at creation	A stopped sandbox costs nothing and keeps its disk; it is started again by API and reboots from disk
What persists	Sandbox state is kept only 30 days after the sandbox is created	Files and processes survive pauses; named snapshots of a sandbox's files	The whole disk, saved every minute and on stop, for as long as you keep the sandbox
Fork	No fork or clone of a session or sandbox	Snapshot a running sandbox's files, then start new sandboxes from it	Fork a running sandbox with its disk
Reaching the sandbox	No inbound ports or SSH; only the sessions and events API	HTTPS share links anyone with the URL can open, expiring after 24 hours by default; SSH and port-forward through the CLI	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; SSH
Browser and desktop	Headless Chromium with Playwright; no desktop or computer-use tool	A browser inside the sandbox for testing; no desktop or computer-use API	Full Linux desktop streamed at 60fps, with Chromium and computer use
Outbound rules	Unrestricted, or limited to listed hosts plus optional package registries and MCP servers	Gateway rules by host, path and HTTP method, with default deny, rate limits, content filters and per-request logs	Open internet, no provider-side allowlist
Keeping API keys out of the sandbox	Vault secrets live in the sandbox as placeholders and are swapped in at egress, per host	The gateway injects stored credentials into outbound requests for any host	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Sandboxes at once	No concurrent-session cap published; 300 creates per minute per organization	Free 5 and Team 50 running sandboxes per launch coverage; paused ones do not count	100 to 2,000 running sandboxes by plan, with no session cap
Where it runs	US workspace geo only; tools can also run on workers you host	US West, or inside your own cloud account with BYOC	EU only (Germany, Finland, France), with zero data retention

Every feature Battleships tracks (43)

Feature	Claude Managed Agents	Islo	bochka
Full VM (own kernel)	No	Yes	Yes
Docker inside	Not published	Yes	Yes
Nested virtualization	No	No	Yes
Root	Not published	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	Yes	Yes	Yes
Computer-use API	No	No	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	Yes	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	Yes	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	Yes	Yes	Yes
Secret proxy for any API	Yes	Yes	Yes
Preinstalled agents	Yes	Yes	Yes
Agent harness API	Yes	Yes	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	Yes	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)	Yes	Yes	Yes
Audit logs	Not published	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Not published	No
HIPAA	No	Not published	No
EU data residency	No	No	Yes
Zero data retention	No	Not published	Yes

Performance

Claude Managed AgentsNot measured

IsloNot measured

bochka26.69 runs/s

There is no comparable measurement for either: neither Managed Agents nor Islo was part of StarSling's public sandbox benchmark run, and Anthropic does not publish how many vCPUs a cloud sandbox gets. In that 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. Claude Managed Agents 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	Claude Managed Agents, 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	$13 · Claude API (pay-as-you-go, usage tiers) · with limits	$101 · Free	$20 · $20/mo
One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month	$53 · Claude API (pay-as-you-go, usage tiers) · 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	$634 · Claude API (pay-as-you-go, usage tiers) · 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	$360 · Claude API (pay-as-you-go, usage tiers) · 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	$796 · Claude API (pay-as-you-go, usage tiers) · with limits	$3,053 · Team · with limits	$2,000 · $2000/mo · with limits

Claude Managed Agents: Managed Agents bills model tokens at API rates plus a flat session runtime fee, measured only while a session is running, including time spent waiting on the model. The tables show runtime only; tokens come on top and usually cost more.

Islo: Islo bills each CPU core and each GB of memory and disk while a sandbox runs, billed per hour, with no plan fee. An idle sandbox keeps billing until its pause-after-idle timer fires, and egress has no published price.

Islo: bochka plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

A Managed Agents sandbox has up to 8 GB of memory and 10 GB of disk, an unpublished vCPU count and Docker only in limited availability, so no scenario here counts as a clean fit for it, and its usage-tier spend limits pause all API use when reached. Islo's Team plan is reported at 50 running sandboxes, so 300 sandboxes for your users and 1,000 short jobs at once need a custom contract. bochka has no session cap, but at 1,000 short jobs at once the $2,000 plan queues starts above 90 per minute and allows 2,400 starts a day.

Scenario	Claude Managed Agents	Islo	bochka
One coding agent, workdays	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform machine size per session not published	egress price not published	None that bite
One agent that never stops	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform machine size per session not published	egress price not published	None that bite
50 agents in parallel	adjacent product, not a like-for-like sandbox not confirmed: Docker inside machine size not published different kind of product: agent-platform	egress price not published	None that bite
Sandboxes for your users	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	Team: max 50 concurrent egress price not published	None that bite
1,000 short jobs at once	adjacent product, not a like-for-like sandbox machine size not published different kind of product: agent-platform not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	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 Claude Managed Agents when

you want Claude itself to do long tasks with no harness to build, idle time that costs nothing, and the option to run tools on your own workers.

No agent loop to build. Teams that want Claude doing long tasks get the harness, caching, compaction, memory and webhooks ready to use.
Idle time costs nothing. Agents that wait long between messages pay runtime only while working, and resume on the next message with no start call.
Tools on your own workers. Teams that must keep files and traffic in-house can run every tool call on their own workers while Anthropic runs the agent.

Use Islo when

you want your own coding agents in a microVM with Docker, per-host egress rules with a log of every call, and sandboxes that pause with memory, in US West or your own cloud.

Any coding agent in a real VM. Teams already using Claude Code, Cursor CLI or Codex get a microVM with Docker, sudo and SSH for each agent.
Egress rules and request logs. Teams that must control what agents reach can allow or block each host, path and method, and log every call.
Pause with memory, wake on request. Agents that sit idle between tasks can pause with memory kept and resume on the next exec, file access or webhook.

Where bochka fits

If your agents need a whole machine rather than a hosted Claude loop or a headless microVM, look at bochka. Each sandbox is a full VM with /dev/kvm, a 60fps desktop, ports you can host on and a disk that lasts, with Claude Code, Codex and other agents you drive from outside. It runs only in the EU.

Emulators and a screen agents can use

Managed Agents gives an 8 GB container with Docker in limited availability, and Islo a microVM with no /dev/kvm. Neither has a desktop, so Android emulators and computer use stall, unless you build a VNC stack into every Islo image.

Ports you can host on

A Managed Agents sandbox has no inbound ports, so you copy the code elsewhere to try it. Islo share links are public and expire after 24 hours by default. bochka gives token-protected HTTPS on up to 50 ports and raw TCP.

A disk that lasts and room to scale

Managed Agents drops sandbox state 30 days after creation, so setup runs again, and Islo's Team plan is reported at 50 running sandboxes. bochka saves the disk every minute, forks running sandboxes and runs 100 to 2,000 at once.

Use bochka when your agents need a real machine: /dev/kvm for emulators, a desktop for computer use, ports you can host on, a disk that lasts and up to 2,000 sandboxes at once in the EU. Compare it one to one: bochka vs Claude Managed Agents and bochka vs Islo.

Questions people ask

Is Claude Managed Agents cheaper than Islo?

For runtime alone, yes in every scenario we priced: one agent running all month comes to $53 a month on Managed Agents against $420 on Islo. But Managed Agents also bills model tokens on top, which usually cost more than the runtime, and its small fixed container is not a clean fit for any scenario here.

Which is faster, Claude Managed Agents or Islo?

Neither has a public CPU benchmark, and Anthropic does not publish how many vCPUs its sandbox gets, so there is no fair speed comparison. On Managed Agents, much of a session's time is often spent waiting on the model. bochka did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB.

Can Claude Managed Agents or Islo run Docker?

Islo runs Docker inside its microVMs, with sudo. Managed Agents lists Docker only in limited availability. Neither documents /dev/kvm, which bochka has on every sandbox along with Docker and systemd.

Can I run Claude Code on Claude Managed Agents or Islo?

On Islo, yes: Claude Code, Cursor CLI and Codex come preinstalled. Managed Agents runs Anthropic's own harness with Claude models, not Claude Code. bochka also has Claude Code, Codex and five other agents preinstalled.

Can I open a web app my agent built?

Not on Managed Agents, which has no inbound ports. Islo shares a port through an HTTPS link that anyone with the URL can open, expiring after 24 hours by default. bochka gives token-protected HTTPS URLs on up to 50 ports, raw TCP and SSH.

Where does my data run?

Managed Agents keeps data and runs code in its US workspace geo only, and Islo runs in US West or inside your own cloud account. bochka runs only in the EU (Germany, Finland and France), with zero data retention.

Try bochka

Install the CLI, then run bochka new.

Product preview