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 workload | Freestyle: price rank | Claude Managed Agents: price rank | boat: 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 requirement | Not ranked: misses a requirement | Not 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 requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Freestyle | Claude Managed Agents | boat |
|---|---|---|---|
| What it is | Full Linux VMs for agents, driven from a TypeScript SDK, a CLI or an API | A hosted Claude agent: Anthropic's harness runs Claude, and tools run in a cloud sandbox or on a worker you host | A sandbox platform: each agent gets its own full Linux VM, with coding agents installed |
| Isolation | Full KVM VM with its own kernel; Freestyle says it oversubscribes host resources | Cloud sandbox: isolated Linux container per session. Self-hosted worker: the isolation of the host you run | Full 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 15 | Not in the public benchmarks we use; vCPU count not published | 28.06 runs/s, 2nd of 15 (rank shared), on a Ryzen 9 9950X host |
| Biggest machine | 32 vCPU / 64 GiB on Pro, 64 / 128 with Enterprise custom limits | Cloud sandbox: up to 8 GB memory and 10 GB disk, not configurable. Self-hosted worker: whatever your host has | 16 vCPU / 32 GB on the $100 plan and above; 8 vCPU / 16 GB on the $20 plan |
| Root, Docker, systemd and /dev/kvm | Yes; systemd is pid 1, Docker runs from boot, full KVM support | Cloud sandbox: Docker listed as limited availability; root, systemd and /dev/kvm not documented | Yes, with /dev/kvm for Android emulators and VMs |
| Pause and resume | Pause saves memory and disk; the same processes resume where they left off | An idle session's sandbox is checkpointed with its files and resumes on the next message | Disk is saved every minute and at each stop; memory is not saved, so a resume is like a reboot |
| Wake on next request | Yes; a VM paused by idle timeout resumes on the next traffic | Yes; an idle session resumes on the next message, and idle time is not billed | No; a stopped sandbox is started by API |
| Fork | Clone a running VM without pausing it; snapshots capture memory and disk | No documented fork or clone of a session or sandbox | Fork a running sandbox's disk from its last 1-minute snapshot |
| How long files last | Until 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 $0 | Cloud sandbox files are kept 30 days after the sandbox is created; history, memory stores and outputs persist until you delete them | Kept 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 access | HTTPS on free style.dev names or your own domain, forward auth, firewall ingress rules, a public IPv6 per VM, SSH | Cloud sandbox: no documented inbound ports or SSH; reached through the sessions and events API. Self-hosted worker: the ports you open on your host | Up 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 use | You set it up: official guides install GNOME or headed Chromium with TigerVNC and noVNC | Headless Chromium with Playwright; add a desktop through custom tools, MCP or a self-hosted worker | Linux desktop and Chrome streamed at 1920x1080 and 60 fps, with computer tools for agents, preinstalled |
| Agents | claude, codex, opencode and openclaw preinstalled; you drive them through exec, a PTY or the Claude Agent SDK | Anthropic's harness with Claude models: events, steering, memory stores, session budgets, webhooks | Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Credentials injected at the edge for HTTPS headers, Postgres and S3; the VM must trust the Freestyle CA | Vault secrets live in the sandbox as placeholders and are swapped in at egress, per host; not yet on self-hosted workers | Optional 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 rules | Default-deny firewall with allow rules by IP, VM, VPC or exact domain | Unrestricted, or limited to listed hosts plus optional package registries and MCP servers | Open internet, no provider-side allowlist |
| Where data lives | Regions are not published | US workspace geo only; inference can be global or US; not eligible for Zero Data Retention | Germany, Finland and France; you cannot pick a region, and snapshot copies can be stored outside the EU |
Every feature Battleships tracks (43)
| Feature | Freestyle | Claude Managed Agents | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No documented way | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | Yes | No documented way | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | With your own setup | No documented way | Yes |
| Browser | With your own setup | Yes | Yes |
| Computer-use API | With your own setup | No documented way | Yes |
| SSH | Yes | No documented way | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | No documented way | Yes |
| Live fork (no pause) | Yes | No documented way | Yes |
| Memory fork | Yes | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | Yes | No documented way |
| HTTPS preview URLs | Yes | No documented way | Yes |
| Raw TCP inbound | Yes | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | Yes | No documented way |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | No documented way | Yes | Yes |
| MCP server | No documented way | Yes | No documented way |
| GPU | Yes | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | No documented way | No documented way | No documented way |
| Self-hosting | No documented way | Yes | No documented way |
| BYOC | No documented way | Yes | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No documented way | Yes | Yes |
| Audit logs | Yes | Not published | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Not published | Yes | No documented way |
| HIPAA | Not published | No documented way | No documented way |
| EU data residency | Not published | No documented way | No documented way |
| Zero data retention | Not published | No documented way | Yes |
Performance
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.
| Scenario | Freestyle, a month | Claude Managed Agents, 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 | $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.
| Scenario | Freestyle | Claude Managed Agents | boat |
|---|---|---|---|
| One coding agent, workdays | None for this scenario |
| None for this scenario |
| One agent that never stops | None for this scenario |
| None for this scenario |
| 50 agents in parallel | None for this scenario |
| None for this scenario |
| Sandboxes for your users | None for this scenario |
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
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