Claude Managed Agents vs Modal VM Sandboxes

Claude Managed Agents is a ready-made agent: you send Claude a task and it works in a small container that Anthropic runs. Modal VM Sandboxes are plain machines with their own Linux kernel and Docker, which you create from code, run your own agent in, and end within 24 hours.

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

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. “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	Modal VM Sandboxes: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Modal gives a coding agent a real VM with Docker but ends it within 24 hours; Managed Agents has Docker only in limited availability; boat keeps a full VM and its disk with a desktop to check the app.	106th of 367, with limits $964 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 Managed Agents sessions sleep between messages for free, but sandbox state is kept only 30 days after creation; Modal VMs stop at 24 hours; a boat disk lasts as long as you keep the sandbox.	219th of 366, with limits $2,511 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 Short code runs suit Managed Agents, which bills runtime only while the agent works, and Modal, which bills by the second and starts many sandboxes at once.	163rd of 345, with limits $756 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 Modal can open tunnels into each user's VM, Managed Agents has no inbound ports, and boat gives each sandbox HTTPS URLs on up to 50 ports and a disk that waits for free.	231st of 361, with limits $823 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 Huge bursts of short rollouts are what Modal is built for, with 5,000 containers at once on Team; boat's per-plan start limits queue large bursts.	252nd of 360, with limits $3,978 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	244th of 364, with limits $320 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 VM and offers /dev/kvm on Team and Enterprise on request; Managed Agents does not document it; boat has /dev/kvm on every plan.	227th of 377, with limits $96 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 A dev box needs SSH and a disk that lasts: Managed Agents has no SSH, Modal ends the VM within 24 hours, and boat keeps both.	224th of 368, with limits $48 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 Managed Agents ships headless Chromium with Playwright, Modal leaves you to set up Xvfb and VNC, and boat streams a full Linux desktop at 60fps with a computer-use API.	127th of 369, with limits $288 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	126th of 367, with limits $288 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	127th of 346, with limits $390 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	155th of 338, with limits $4,798 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	179th of 360, with limits $160 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	Claude Managed Agents	Modal VM Sandboxes	boat
What it is	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	A VM you create from Python, TypeScript or Go code, run commands in and terminate	A sandbox platform: each agent gets its own full Linux machine, with coding agents built in
Isolation	Isolated Linux container per session	VM with its own Linux kernel on Cloud Hypervisor	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	The CPU cores and memory you request in code	Up to 16 vCPU / 32 GB on the $100 plan and above
Docker, systemd and root	Docker listed as limited availability; root and systemd not documented	Yes; start dockerd yourself as the entrypoint	Yes, in every sandbox
Nested virtualization (/dev/kvm)	Not documented	Team and Enterprise plans only, on request	Yes, on every plan
CPU benchmark (4 vCPU / 8 GB)	Not measured; vCPU count not published	15.54 runs/s	26.69 runs/s
Longest session and files	No published session cap; sandbox state is kept only 30 days after the sandbox is created	24 hours (default 5 minutes); the root disk goes when it ends, only Volumes and snapshots keep files	No cap on paid plans; the whole disk is saved every minute and on stop
Idle and wake	An idle session is checkpointed, not billed, and resumes on the next message	No paused state; a finished sandbox is gone	Stop for free and start again by API with the whole disk
Fork and snapshots	No fork or clone of a session or sandbox	Filesystem snapshots boot any number of new sandboxes; memory snapshots in alpha	Fork a running sandbox with its disk
Inbound access	No inbound ports or SSH; reached only through the sessions and events API	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
Browser and desktop	Headless Chromium with Playwright; no desktop or computer-use tool	Not offered; an example shows how to set up Xvfb and VNC yourself	60fps Linux desktop, Chromium and a computer-use API built in
Agents and API keys	Anthropic's harness with Claude models only; vault secrets swapped in at egress, per host	Examples only; secrets are environment variables, or you run your own proxy in a sidecar	Claude Code, Codex and five more preinstalled, driven from outside; a credentials proxy for any HTTPS API
Outbound rules and regions	Unrestricted or listed hosts only; US workspace geo only	Block all, IP-range or domain allowlist (beta); US, EU and Asia-Pacific	Open internet, no provider-side allowlist; EU only (Germany, Finland, France)
Self-hosted workers	Tools can run on your own workers while Anthropic keeps the orchestration	No	No

Every feature Battleships tracks (43)

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

Performance

Claude Managed AgentsNot measured

Modal VM Sandboxes15.54 runs/s

boat26.69 runs/s

In the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, boat did 26.69 runs per second and Modal's VM runtime did 15.54, so boat did about 1.7 times the CPU work in the same time. Claude Managed Agents has no comparable measurement: it was not in the run, and Anthropic does not publish how many vCPUs a sandbox gets. On Managed Agents much of a session's time is often spent waiting on the model rather than the CPU.

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. Claude Managed Agents 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	Claude Managed Agents, a month	Modal VM Sandboxes, a month	boat, 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	$15 · Starter · with limits	$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	$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	$634 · Claude API (pay-as-you-go, usage tiers) · 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	$360 · Claude API (pay-as-you-go, usage tiers) · 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	$796 · Claude API (pay-as-you-go, usage tiers) · with limits	$3,193 · Team · with limits	$2,000 · $2000/mo · with limits

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

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 is terminated. Starter is free with $30 of monthly credit, and Team is $250 a month with $100 of credit.

Modal VM Sandboxes: boat charges one hourly rate per machine size, by the second, only while the sandbox runs. Plans start at $20 a month and the whole fee becomes usage credit; 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 counts as a clean fit; Anthropic publishes no concurrent-session cap, only 300 creates per minute and usage-tier spend limits. A Modal VM Sandbox lives at most 24 hours and keeps only files in a Volume or snapshot, so the workday, always-on and fleet scenarios do not fit, and the 1,000-job burst relies on shared CPU above its request. On boat the limit that bites is start speed: even the $2,000 plan starts 90 sandboxes a minute, so 1,000 jobs at once queue.

Scenario	Claude Managed Agents	Modal VM Sandboxes	boat
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	files survive a stop only in Volumes: packages installed elsewhere reset	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	Starter: sessions capped at 24 h files survive a stop only in Volumes: packages installed elsewhere reset	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	files survive a stop only in Volumes: packages installed elsewhere reset	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)	None that bite	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)	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 Claude Managed Agents when

you want Claude itself to do long, mostly text and code 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 sessions sleep for free. Agents that wait a long time between messages pay runtime only while working, and resume on the next message.
Your own workers. Teams with strict network rules can run every tool call on their own infrastructure while Anthropic keeps the orchestration.

Use Modal VM Sandboxes when

you run your own agent code in huge bursts of short jobs that finish within a day, need regions outside Europe or strict outbound rules, or already run your models on Modal.

A real VM you control. Teams running their own agent get a Linux kernel with Docker, systemd and root, created and sized from code.
Very large bursts. Useful for huge bursts of short jobs: Modal runs 5,000 containers at once on Team.
Regions and outbound rules. Modal runs in the US, EU and Asia-Pacific, and can block outbound traffic or allow only chosen IP ranges or domains.

Where boat fits

Look at boat when your agents work for days on a machine they come back to. Managed Agents gives you Claude but a small container you cannot open, and Modal gives you a VM but ends it within a day. boat gives each agent a full VM that keeps its disk, with a desktop, open ports and the agents already installed.

A machine that keeps its work

Managed Agents keeps sandbox state only 30 days after creation, and a Modal VM ends within 24 hours, so you write snapshot code or use Volumes. A boat disk is saved every minute, with no session cap.

Desktop, ports and any agent

Managed Agents runs only Claude, headless, with no inbound ports. Modal gives you a kernel, then you install VNC, a browser and the agent. boat has a 60fps desktop, 50 HTTPS ports and Claude Code or Codex driven from outside.

A faster full VM

Managed Agents has up to 8 GB of memory, Docker in limited availability and no documented /dev/kvm. Modal did 15.54 runs/s and gives /dev/kvm only on request. boat did 26.69 runs/s with /dev/kvm on every plan.

Use boat when your agents need a real machine they come back to: Docker, emulators, a desktop and browser, ports you can open, a faster VM whose disk lasts, and the choice of Claude Code, Codex or other agents. Compare it one to one: boat vs Claude Managed Agents and boat vs Modal VM Sandboxes.

Questions people ask

Is Claude Managed Agents cheaper than Modal VM Sandboxes?

For runtime alone, Managed Agents costs less in all five scenarios, for example $53 against $178 a month for one agent that never stops. But Managed Agents also bills model tokens on top, and its small container does not fit any scenario cleanly. boat costs $26 a month for the same always-on agent.

Which is faster, Claude Managed Agents or Modal VM Sandboxes?

Only Modal was measured: its VM runtime did 15.54 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and boat did 26.69. Anthropic does not publish how many vCPUs a Managed Agents sandbox gets.

Can Claude Managed Agents or Modal VM Sandboxes run Docker?

Modal VM Sandboxes run Docker inside a real VM once you start dockerd as the entrypoint. Managed Agents lists Docker as limited availability. boat runs Docker, systemd and /dev/kvm in every sandbox.

How long can a session run on each?

A Modal VM Sandbox runs 5 minutes by default and 24 hours at most. Managed Agents publishes no session cap and resumes idle sessions on the next message, but keeps sandbox state only 30 days after the sandbox is created. boat has no session cap on paid plans.

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

Managed Agents runs Anthropic's own harness with Claude models, not Claude Code. On a Modal VM you install and run any agent yourself; Modal offers examples only. On boat, Claude Code, Codex and five other agents come preinstalled.

Is boat SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial