Claude Managed Agents vs Unikraft Cloud

Claude Managed Agents is a finished agent: Anthropic runs Claude and its harness in a container, and you send it tasks. Unikraft Cloud is raw compute: it turns your Dockerfile into a tiny microVM that sleeps when idle and wakes in milliseconds, and you bring the agent yourself.

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

Unikraft Cloud

Unikraft Cloud is a microVM cloud from Unikraft Inc. that runs any Dockerfile-based workload as a minimal Linux microVM with millisecond cold starts and scale-to-zero.

Your Dockerfile becomes the VM image at build time, and each instance runs on a heavily customized Firecracker VMM, so it boots in milliseconds and can go into standby when no traffic arrives. It is a general compute platform built for dense, bursty work such as HTTP services, headless browsers and agent fleets, sold as flat self-serve plans plus Enterprise dedicated hosts, on-prem and bring your own cloud. It is not a dev machine you log into: instances are reached through services, the CLI and a sandbox plugin for commands and files.

Isolation: Linux microVM per instance on a customized Firecracker VMM; full VMs on Enterprise
Plans: Hobby free, Team $39/mo, Pro $199/mo, Enterprise custom; each caps running instances, vCPUs and memory
Running capacity: 2 / 8 / 24 running instances with 4 / 8 / 32 GiB memory in total on Hobby / Team / Pro
Regions: Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default; more metros on request
Self-hosting: Dedicated host fleet, on-prem and BYOC on Enterprise
Compliance: SOC2, HIPAA and audit logs listed on Enterprise
Open source: The unikraft CLI is open source; the cloud platform is commercial

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	Unikraft Cloud: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Managed Agents gives a coding agent a container with up to 8 GB of memory and Docker only in limited availability, and Unikraft documents no container runtime inside an instance; boat gives it a full VM with Docker and systemd.	106th of 367, with limits $964 a month	Can't run it	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Managed Agents sessions sleep for free between messages but keep sandbox state only 30 days after creation; Unikraft's Team pool is 8 GiB of memory shared by every running instance.	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 Both fit short bursts with long gaps: Managed Agents bills runtime only while the agent works, and Unikraft instances go into standby after a second of idle and wake on the next request.	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 Managed Agents sandboxes have no inbound ports, and Unikraft Pro runs only 24 instances at once, so hundreds of active users need an Enterprise contract; boat gives each sandbox HTTPS URLs on up to 50 ports.	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	252nd of 360, with limits $3,978 a month	Can't run it	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 CI jobs that build images or run Android emulators need Docker and /dev/kvm; Managed Agents does not document /dev/kvm, Unikraft keeps nested virtualization for Enterprise, and boat has both on every plan.	227th of 377, with limits $96 a month	Can't run it	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither Managed Agents nor Unikraft has SSH today, so a dev box there is reached through an API or CLI; boat ranks 18th here with SSH and a disk saved every minute.	224th of 368, with limits $48 a month	219th of 368, with limits $39 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 Computer-use agents need a desktop to see and click; Managed Agents ships only headless Chromium, Unikraft has none built in, and boat streams a Linux desktop at 60fps.	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	Can't run it	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	Unikraft Cloud	boat
What it is	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	A microVM cloud: your Dockerfile becomes a minimal Linux VM image that boots in milliseconds	A sandbox platform: each agent gets its own full Linux machine, with coding agents built in
Isolation	Isolated Linux container per session	Minimal Linux microVM per instance on a customized Firecracker VMM	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	Plan pool shared by all running instances: 2 vCPU / 4 GiB, 8 vCPU / 8 GiB or 24 vCPU / 32 GiB	4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB per sandbox on the $100 plan and above
Docker, systemd and /dev/kvm	Docker listed as limited availability; root, systemd and /dev/kvm not documented	Runs as root; no container runtime inside documented; nested virtualization on Enterprise only	Root, Docker, systemd and /dev/kvm for Android emulators and VMs on every plan
SSH	No; the sandbox is reached only through the sessions and events API	Not yet; commands and files go through the sandbox plugin and CLI	Yes, into every sandbox
Inbound access	No inbound ports	Services on its load balancer: HTTP on 80, HTTPS on 443, TLS-wrapped TCP on other ports	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6
Browser and desktop	Headless Chromium with Playwright; no desktop or computer-use tool	None built in; you can run your own headless browser from a Dockerfile	Linux desktop streamed at 60fps, with Chromium and computer use
Idle and wake	An idle session is checkpointed, not billed, and resumes on the next message	Standby after a 1 second idle cooldown by default; traffic wakes it in milliseconds, with memory kept in stateful mode	A stopped sandbox costs nothing and keeps its disk; it is started again by API
What persists	Sandbox state is kept only 30 days after the sandbox is created	Volumes, plus standby snapshots within the plan's standby storage	The whole disk, saved every minute and on stop, for as long as you keep the sandbox
Fork and checkpoints	No fork or clone of a session or sandbox	Checkpoint memory and volumes of a running microVM, then start new instances from it	Fork a running sandbox with its disk; snapshots every minute
Agents	Anthropic's harness with Claude models, steering, multiagent threads, memory stores and webhooks	None preinstalled; you bring the agent in your own image	Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Keeping API keys out of the sandbox	Vault secrets live in the sandbox as placeholders and are swapped in at egress, per host	Network shield can inject secrets into traffic, Enterprise only, limited access	Credentials proxy for model providers and any HTTPS API, on every plan; switch a credential to another account when credits run out
Outbound rules	Unrestricted, or limited to listed hosts plus optional package registries and MCP servers	Network shield filters traffic, Enterprise only, limited access	Open internet, no provider-side allowlist
Regions	US workspace geo only	Dallas, Frankfurt, San Francisco, Singapore and Washington DC, more on request	EU only (Germany, Finland, France)

Every feature Battleships tracks (43)

Feature	Claude Managed Agents	Unikraft Cloud	boat
Full VM (own kernel)	No	Yes	Yes
Docker inside	Not published	No	Yes
Nested virtualization	No	Yes	Yes
Root	Not published	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	No	Yes
Browser	Yes	No	Yes
Computer-use API	No	No	Yes
SSH	No	No	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	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	Yes	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	No	Not published	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	No	Yes
Agent harness API	Yes	No	Yes
MCP server	Yes	No	No
GPU	No	Yes	No
Windows	No	No	No
Arm64	No	Yes	No
Self-hosting	Yes	Yes	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	No	Yes
Audit logs	Not published	Yes	No
SSO	Yes	No	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

Unikraft CloudNot measured

boat26.69 runs/s

There is no comparable measurement for either: neither Claude Managed Agents nor Unikraft Cloud was in the hpc-sandbox-benchmarks run, and Anthropic does not publish how many vCPUs its sandbox gets. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB. Unikraft states cold starts under 10 ms, which is its own figure and measures start time, not CPU speed.

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 Unikraft Cloud 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	Unikraft Cloud, 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	$39 · Hobby	$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	$39 · Hobby	$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	Can't run it	$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	Can't run it	$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	Can't run it	$2,000 · $2000/mo · with limits

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

Unikraft Cloud: Unikraft charges a flat monthly fee for a pool of running capacity: free for 2 vCPU / 4 GiB, $39 for 8 vCPU / 8 GiB, $199 for 24 vCPU / 32 GiB, with sleeping instances not counted. Anything bigger is an Enterprise quote.

Unikraft Cloud: 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

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; there is no published session cap, but usage-tier spend limits pause all API use when reached. Unikraft's limits are shared pools: Team's 8 vCPU and 8 GiB hold one 4 vCPU / 8 GB agent, so 50 agents, sandboxes for your users and 1,000 short jobs need Enterprise. boat fits every scenario but the 1,000-job burst, where its $2,000 plan queues starts above 90 per minute.

Scenario	Claude Managed Agents	Unikraft Cloud	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	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown 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	flat pool: the tier is billed whether used or not disk beyond 0 GiB: price unknown 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	no pool tier with 200 vCPU / 400 GiB for 50 VMs no published per-resource rate	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)	no pool tier with 600 vCPU / 1,200 GiB for 300 VMs no published per-resource rate	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)	no pool tier with 2,000 vCPU / 4,000 GiB for 1,000 VMs no published per-resource rate	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, host allowlists, 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.
Host allowlists and your own workers. Teams with strict network rules can limit sandboxes to listed hosts, or run every tool call on their own workers.

Use Unikraft Cloud when

you run many small services or headless browsers that sleep most of the time and must wake in milliseconds, need US or Asia regions, or want GPUs or on-prem under Enterprise.

Millisecond starts and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
Any workload, any model. Teams that want raw compute can run any Dockerfile, with whatever agent or model they choose, not one vendor's harness.
Regions and your own hardware. Unikraft runs in the US, Frankfurt and Singapore, and Enterprise adds GPUs, arm64, on-prem or your own cloud.

Where boat fits

If what you are really running is coding agents, neither option gives the agent a machine it can fully work in: Managed Agents is a small container behind an API, and Unikraft is a microVM built for short, sleepy services. boat gives each agent a whole Linux VM with Docker, SSH, open ports and a desktop, and lets you drive Claude Code, Codex or other agents inside from outside.

A whole machine with Docker and /dev/kvm

Managed Agents has Docker only in limited availability and up to 8 GB of memory; Unikraft documents no container runtime inside and keeps nested virtualization for Enterprise. On boat, docker compose and Android emulators just run.

Open and log into what the agent builds

Managed Agents has no inbound ports or SSH, and Unikraft has no SSH yet and no desktop. boat gives each sandbox SSH, HTTPS URLs on up to 50 ports, raw TCP and a desktop streamed at 60fps.

Any agent, keys kept outside

Managed Agents runs only Claude through Anthropic's harness, and Unikraft ships no agent, with secret injection on Enterprise only. boat has seven agents preinstalled and a credentials proxy for any HTTPS API on every plan.

Use boat when your agents need a real machine: Docker, emulators, SSH, a desktop and browser, open ports, a disk that lasts, and Claude Code, Codex or other agents driven from outside. Compare it one to one: boat vs Claude Managed Agents and boat vs Unikraft Cloud.

Questions people ask

Is Claude Managed Agents cheaper than Unikraft Cloud?

For one coding agent on workdays, Managed Agents runtime is $13 a month against Unikraft's $39 Team pool, but model tokens come on top. For an agent that never stops, Unikraft's $39 is below Managed Agents' $53 of runtime. boat costs $20 and $26 for the same two scenarios.

Which is faster?

Neither has a comparable CPU measurement. Unikraft is built to start fast: its microVMs cold boot in milliseconds and wake on the next request. Managed Agents resumes an idle session on the next message, and much of a session's time is spent waiting on the model.

Can Claude Managed Agents or Unikraft Cloud run Docker?

Managed Agents lists Docker as limited availability. Unikraft builds your Dockerfile into the VM image and does not document a container runtime inside a running instance. A boat sandbox is a full Ubuntu VM with Docker, systemd and /dev/kvm.

Can I SSH into either one?

No. Managed Agents sandboxes are reached only through the sessions and events API, and Unikraft has announced SSH as coming soon, with commands and files going through its sandbox plugin and CLI today. Every boat sandbox has SSH.

Can I run my own agent on them?

Managed Agents runs Anthropic's own harness with Claude models only. Unikraft runs whatever agent you put in your image, but nothing is preinstalled. boat comes with Claude Code, Codex and five other agents that you drive from outside.

Where do they run?

Managed Agents stores data and runs code in the US workspace geo only. Unikraft runs in Dallas, Frankfurt, San Francisco, Singapore and Washington DC by default. boat runs only in the EU, in Germany, Finland and France.

Try boat

Install the CLI, then run boat new.

7-day free trial