Freestyle vs Claude Managed Agents

Freestyle rents you full Linux VMs that pause with their memory, fork and wake on the next request, and you bring the agent. Claude Managed Agents is Anthropic's hosted agent. You send Claude a task, and it works in a container that Anthropic runs, or on a worker that you host.

The companies and products

Freestyle

Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.

Each Freestyle VM is a KVM virtual machine with its own kernel, booted from a base snapshot. The default Ubuntu image has systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request. Every VM starts behind a default-deny firewall. You drive it from a TypeScript SDK, a CLI or an API.

Claude Managed Agents

Claude Managed Agents is Anthropic's ready-made agent harness: Claude runs as an autonomous agent, 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 in Anthropic's cloud, or runs its tools on a worker that you host. It is built for teams that want Claude to do long tasks without building their own agent loop or sandbox.

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. “31st cheapest of 365” means 30 of the other 364 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 workloadFreestyle: price rankClaude Managed Agents: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
Freestyle gives a coding agent a full VM with Docker and systemd. A Managed Agents cloud sandbox has up to 8 GB of memory, and Docker there is in limited availability; a self-hosted worker can run on a bigger host that you operate.
31st cheapest of 365
$3,311 a month
139th of 365, with limits
$964 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
Managed Agents sessions sleep between messages with no runtime charge. Cloud sandbox files are kept 30 days after the sandbox is created. A Freestyle disk stays until you delete the VM. A boat disk is kept at least 14 days after a stop, and a saved snapshot has no scheduled expiry.
49th cheapest of 361
$4,195 a month
259th of 361, with limits
$2,511 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
Freestyle suits short code runs: VMs pause with their memory and wake on the next request with the same processes still running. Managed Agents bills runtime only while the agent works.
46th cheapest of 336
$482 a month
167th of 336, with limits
$756 a month
189th of 336, 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
Freestyle can give each of your users a VM with HTTPS on its own domain. A Managed Agents cloud sandbox has no documented inbound ports; with a self-hosted worker, you open ports on your own host. boat gives each sandbox up to 50 HTTPS URLs, token-gated by default.
26th cheapest of 349
$1,358 a month
227th of 349, with limits
$823 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
Freestyle can snapshot a running VM with its memory and boot copies from it, which suits rollouts that branch from one state. Managed Agents documents no fork.
116th of 349, with limits
$6,600 a month
247th of 349, with limits
$3,978 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
68th cheapest of 359
$1,046 a month
247th of 359, with limits
$320 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
CI jobs that build Android apps or VM images need /dev/kvm and full Docker. Freestyle and boat have both. The Managed Agents cloud sandbox lists Docker as limited availability and documents no /dev/kvm.
169th of 374, with limits
$625 a month
228th of 374, with limits
$96 a month
2nd cheapest of 374
$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. Freestyle and boat have both. A Managed Agents cloud sandbox is reached through the session API; a self-hosted worker host can have SSH, which you run.
102nd cheapest of 371
$151 a month
238th of 371, with limits
$48 a month
19th cheapest of 371
$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; you add a desktop through custom tools, MCP or a self-hosted worker. On Freestyle you install the desktop and VNC from its guides. boat streams a Linux desktop at 60 fps with computer tools.
51st cheapest of 367
$940 a month
166th of 367, with limits
$288 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
99th of 356, with limits
$482 a month
181st of 356, with limits
$288 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
110th cheapest of 343
$482 a month
194th of 343, with limits
$390 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
183rd of 327, with limits
$6,560 a month
153rd of 327, with limits
$4,798 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
28th cheapest of 351
$482 a month
219th of 351, with limits
$160 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement

Key features

FeatureFreestyleClaude Managed Agentsboat
What it isFull Linux VMs for agents, driven from a TypeScript SDK, a CLI or an APIA hosted Claude agent: Anthropic's harness runs Claude, and tools run in a cloud sandbox or on a worker you hostA sandbox platform: each agent gets its own full Linux VM, with coding agents installed
IsolationFull KVM VM with its own kernel; Freestyle says it oversubscribes host resourcesCloud sandbox: isolated Linux container per session. Self-hosted worker: the isolation of the host you runFull VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared
CPU benchmark (V8 Web Tooling, 4 vCPU / 8 GB, StarSling run of 3 October 2026)10.22 runs/s, 14th of 15Not in the public benchmarks we use; vCPU count not published28.06 runs/s, 2nd of 15 (rank shared), on a Ryzen 9 9950X host
Biggest machine32 vCPU / 64 GiB on Pro, 64 / 128 with Enterprise custom limitsCloud sandbox: up to 8 GB memory and 10 GB disk, not configurable. Self-hosted worker: whatever your host has16 vCPU / 32 GB on the $100 plan and above; 8 vCPU / 16 GB on the $20 plan
Root, Docker, systemd and /dev/kvmYes; systemd is pid 1, Docker runs from boot, full KVM supportCloud sandbox: Docker listed as limited availability; root, systemd and /dev/kvm not documentedYes, with /dev/kvm for Android emulators and VMs
Pause and resumePause saves memory and disk; the same processes resume where they left offAn idle session's sandbox is checkpointed with its files and resumes on the next messageDisk is saved every minute and at each stop; memory is not saved, so a resume is like a reboot
Wake on next requestYes; a VM paused by idle timeout resumes on the next trafficYes; an idle session resumes on the next message, and idle time is not billedNo; a stopped sandbox is started by API
ForkClone a running VM without pausing it; snapshots capture memory and diskNo documented fork or clone of a session or sandboxFork a running sandbox's disk from its last 1-minute snapshot
How long files lastUntil you delete the VM. A paused VM bills only storage ($0.000086 per GiB-hour after 60,000 free GiB-hours a month), so one default VM paused all month costs about $0Cloud sandbox files are kept 30 days after the sandbox is created; history, memory stores and outputs persist until you delete themKept at least 14 days after a stop; saved snapshots have no scheduled expiry. A stopped sandbox has no compute charge; saved snapshots above the included count and the AI proxy still charge
Inbound accessHTTPS on free style.dev names or your own domain, forward auth, firewall ingress rules, a public IPv6 per VM, SSHCloud sandbox: no documented inbound ports or SSH; reached through the sessions and events API. Self-hosted worker: the ports you open on your hostUp to 50 HTTPS URLs per sandbox, token-protected by default; SSH through a shared IPv4 host and port; raw ports over IPv6 when the sandbox has no IPv4 of its own
Desktop, browser and computer useYou set it up: official guides install GNOME or headed Chromium with TigerVNC and noVNCHeadless Chromium with Playwright; add a desktop through custom tools, MCP or a self-hosted workerLinux desktop and Chrome streamed at 1920x1080 and 60 fps, with computer tools for agents, preinstalled
Agentsclaude, codex, opencode and openclaw preinstalled; you drive them through exec, a PTY or the Claude Agent SDKAnthropic's harness with Claude models: events, steering, memory stores, session budgets, webhooksClaude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Keeping API keys out of the sandboxCredentials injected at the edge for HTTPS headers, Postgres and S3; the VM must trust the Freestyle CAVault secrets live in the sandbox as placeholders and are swapped in at egress, per host; not yet on self-hosted workersOptional AI credentials proxy ($1 per UTC day on, plus $1 per 1,000 requests) for supported AI providers and HTTPS APIs you register; other secrets still enter the sandbox
Outbound rulesDefault-deny firewall with allow rules by IP, VM, VPC or exact domainUnrestricted, or limited to listed hosts plus optional package registries and MCP serversOpen internet, no provider-side allowlist
Where data livesRegions are not publishedUS workspace geo only; inference can be global or US; not eligible for Zero Data RetentionGermany, Finland and France; you cannot pick a region, and snapshot copies can be stored outside the EU
Every feature Battleships tracks (43)
FeatureFreestyleClaude Managed Agentsboat
Full VM (own kernel)YesNo documented wayYes
Docker insideYesNot publishedYes
Nested virtualizationYesNo documented wayYes
RootYesNot publishedYes
SystemdYesNot publishedYes
Desktop GUIWith your own setupNo documented wayYes
BrowserWith your own setupYesYes
Computer-use APIWith your own setupNo documented wayYes
SSHYesNo documented wayYes
Persistent diskYesYesYes
Pause/resumeYesYesYes
Automatic snapshotsYesYesYes
Fork/cloneYesNo documented wayYes
Live fork (no pause)YesNo documented wayYes
Memory forkYesNo documented wayNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsYesYesYes
Idle auto-stopYesYesNo documented way
Wake on requestYesYesNo documented way
HTTPS preview URLsYesNo documented wayYes
Raw TCP inboundYesNo documented wayYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistYesYesNo documented way
Secret proxyYesYesYes
Secret proxy for any APIYesYesYes
Preinstalled agentsYesYesYes
Agent harness APINo documented wayYesYes
MCP serverNo documented wayYesNo documented way
GPUYesNo documented wayNo documented way
WindowsNo documented wayNo documented wayNo documented way
Arm64No documented wayNo documented wayNo documented way
Self-hostingNo documented wayYesNo documented way
BYOCNo documented wayYesNo documented way
Open sourceNo documented wayNo documented wayNo documented way
Scoped API keysYesNot publishedYes
Spend limitsNot publishedYesYes
Usage per sandbox (API)No documented wayYesYes
Audit logsYesNot publishedNo documented way
SSOYesYesNo documented way
SOC 2Not publishedYesNo documented way
HIPAANot publishedNo documented wayNo documented way
EU data residencyNot publishedNo documented wayNo documented way
Zero data retentionNot publishedNo documented wayYes

Performance

Freestyle10.22 runs/s
Claude Managed AgentsNot measured
boat28.06 runs/s

StarSling ran the V8 Web Tooling Benchmark at 4 vCPU / 8 GB on 3 October 2026 (run 37073680030). Freestyle did 10.22 runs per second, 14th of 15. boat did 28.06, 2nd of 15 (a rank shared with four providers), about 2.7 times the work. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Providers ran on different hardware in different regions. Claude Managed Agents is not in the public benchmarks we use, and Anthropic does not publish how many vCPUs a cloud sandbox gets.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Claude Managed Agents is not in the public benchmarks we use, so we cannot say which is faster.

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. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioFreestyle, a monthClaude Managed Agents, a monthboat, 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
$27 · Free$13 · Claude API (pay-as-you-go, usage tiers) · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$159 · Free$53 · Claude API (pay-as-you-go, usage tiers) · 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
$2,139 · Pro$634 · Claude API (pay-as-you-go, usage tiers) · 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
$581 · Pro$360 · Claude API (pay-as-you-go, usage tiers) · 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
$1,305 · Pro · with limits$796 · Claude API (pay-as-you-go, usage tiers) · with limits$8,800 · $2000/mo · with limits

Freestyle: Freestyle bills per second for the vCPU ($0.04032 per hour), RAM ($0.0129 per GiB-hour) and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. On Free those allowances are hard stops and no card is needed. Hobby and Pro set a $50 or $500 monthly minimum that counts as usage. A paused VM bills only for storage.

Claude Managed Agents: Managed Agents bills model tokens at API list rates plus $0.08 per session-hour of runtime, measured to the millisecond only while the session is running, including time spent waiting on the model. The table shows runtime only, and the cloud sandbox size is not published, so it is not a like-for-like machine. Tokens come on top. A self-hosted worker adds the cost of your own host.

Claude Managed Agents: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. Included VM time expires at the end of the billing period. A default 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs, busy or idle. A stopped sandbox has no compute charge and keeps its disk for at least 14 days. Saved snapshots above the included count and the AI credentials proxy still charge while sandboxes are stopped. A card is required, also for the 7-day trial. Model tokens for the built-in agents are paid to your model provider.

Limits in those scenarios

Freestyle has no idle timeout by default, so a VM bills until you pause it or set one. On Free the monthly allowances are hard stops. Freestyle allows 10 VMs at once on Free, 40 on Hobby and 400 on Pro, so it does not fit 1,000 short jobs at once. A Managed Agents cloud sandbox has up to 8 GB of memory and 10 GB of disk, an unpublished vCPU count and Docker in limited availability, so no scenario counts as a like-for-like fit. Anthropic publishes no concurrent-session cap, only 300 creates a minute per organization and usage-tier spend caps that pause all API use. boat's $20 plan includes 12 starts a minute, 60 an hour and 200 a day, with 100 sandboxes at once; the $2,000 plan includes 90, 600 and 2,400. An extra start costs $0.03 to $0.07. Above 6 times the included number (3 times per minute), a start fails with 429, and boat never queues it.

ScenarioFreestyleClaude Managed Agentsboat
One coding agent, workdaysNone for this scenario
  • adjacent product, not a like-for-like sandbox
  • machine size not published
  • different kind of product: agent-platform
  • machine size per session not published
None for this scenario
One agent that never stopsNone for this scenario
  • adjacent product, not a like-for-like sandbox
  • machine size not published
  • different kind of product: agent-platform
  • machine size per session not published
None for this scenario
50 agents in parallelNone for this scenario
  • adjacent product, not a like-for-like sandbox
  • not confirmed: Docker inside
  • machine size not published
  • different kind of product: agent-platform
None for this scenario
Sandboxes for your usersNone for this scenario
  • 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 for this scenario
1,000 short jobs at once
  • Pro: max 400 concurrent
  • shared vCPUs on this tier”): heavy, sustained CPU use can be slowed by other tenants
  • 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)
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use Freestyle when

you want your own VMs that pause with their memory, fork while running and wake on the next request, with a default-deny firewall or more than 8 GB in one machine.

  • Memory pause, live fork and wake on request. For VMs that sleep between requests: they resume the same processes, wake on new traffic and can be cloned while running.
  • Bigger machines. Teams with heavy jobs get up to 32 vCPU / 64 GiB on Pro, against a cloud sandbox with up to 8 GB on Managed Agents.
  • Any agent, and links you can open. Freestyle preinstalls several agent CLIs, and each VM serves HTTPS on its own domain.

Use Claude Managed Agents when

you want Claude itself to do long tasks with no agent loop to build, idle time that costs no runtime, 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, budgets 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.
  • Run tools on your own workers. Teams with strict rules can run every tool call on their own infrastructure while Anthropic keeps the orchestration.

Where boat fits

Look at boat when your agents spend hours on builds, tests, Docker, emulators and web pages. It gives each agent a full VM with a desktop, links you can open, and an API to drive Claude Code, Codex or other agents from outside. boat does not keep memory across a stop and bills a running sandbox at full rate, busy or idle.

A full machine, with more CPU work in one run

In StarSling's run of 3 October 2026, boat did 28.06 runs per second and Freestyle 10.22. That boat sandbox ran on a Ryzen 9 9950X host; boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. A Managed Agents cloud sandbox has up to 8 GB of memory and Docker in limited availability.

A desktop and links you can open

A Managed Agents cloud sandbox has no documented inbound ports, SSH or desktop. On Freestyle you install and maintain GNOME or Xvfb, VNC and Chromium from its guides. boat ships a 60 fps desktop and HTTPS on up to 50 ports.

Any agent, driven from outside

Managed Agents runs Claude in Anthropic's harness. Freestyle preinstalls agent CLIs, and you start them through exec and parse their output. boat has one API to prompt and steer seven agents, and an optional paid credentials proxy that can switch accounts when credits run out.

Use boat when your agents need a full machine for hours: Docker, emulators, a desktop and browser, ports you can open, and the choice of Claude Code, Codex or other agents driven from outside. Compare it one to one: boat vs Freestyle and boat vs Claude Managed Agents.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is Freestyle cheaper than Claude Managed Agents?

For runtime alone, Managed Agents costs less in every scenario in the table above. For example, an agent that never stops is $53 of runtime against $159 on Freestyle. Managed Agents adds model tokens on top, and its cloud sandbox is not a like-for-like machine. boat runs the same always-on agent for $26 a month, and tokens for its agents are paid to your model provider.

Which is faster, Freestyle or Claude Managed Agents?

We cannot say: Managed Agents is not in the public benchmarks we use, and Anthropic does not publish its vCPU count. In StarSling's V8 Web Tooling run of 3 October 2026 at 4 vCPU / 8 GB, Freestyle did 10.22 runs per second and boat did 28.06 on a Ryzen 9 9950X host.

Can Claude Managed Agents or Freestyle run Docker?

Freestyle runs Docker from boot in a full VM with systemd and KVM, so Android emulators work too. The Managed Agents cloud sandbox lists Docker as limited availability and does not document root, systemd or /dev/kvm. boat has all of them in every sandbox.

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

Freestyle's base image has the claude CLI on PATH, and you start it through exec, a PTY or the Claude Agent SDK. Managed Agents runs Anthropic's own harness with Claude models. boat preinstalls Claude Code, Codex and five other agents with an API to drive them from outside.

Can I open a web app my agent built?

On Freestyle, yes: VMs get HTTPS on free style.dev names or your own domain. A Managed Agents cloud sandbox has no documented inbound ports; with a self-hosted worker, you open ports on your own host. boat gives each sandbox up to 50 HTTPS URLs, token-gated by default, and SSH.

Is boat SOC 2 compliant?

SOC 2 is in progress, so boat has no SOC 2 report today. No HIPAA BAA and no SAML SSO are documented. Live status is at status.ascii.dev and the data retention policy is at docs.boat.dev/data-retention.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons