Morph Cloud vs Claude Managed Agents
Morph Cloud rents you full virtual machines that you can snapshot, branch and wake with their memory, and you bring the agent. Claude Managed Agents is the agent itself: Anthropic runs Claude in a small container and you talk to it through an events API.
The companies and products
Morph Cloud
Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.
You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state, and it also sells managed GitHub Actions runners and a shared filesystem.
- Regions
- Not published
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.
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. “16th cheapest of 345” means 15 of the other 344 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 | Morph Cloud: 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 Morph gives the build a full VM with Docker but you install and drive the agent through tmux; Managed Agents brings the agent but only a container with up to 8 GB of memory and Docker in limited availability. | 198th of 367, with limits $2,288 a month | 106th of 367, with limits $964 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 235th of 366, with limits $3,014 a month | 219th of 366, with limits $2,511 a month | 5th cheapest of 366 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Morph Cloud ranks 16th here and fits fully, because a machine can pause with its memory and wake on the next request; Managed Agents bills runtime only while working but its container counts only as a compromise. | 16th cheapest of 345 $154 a month | 163rd of 345, with limits $756 a month | 186th of 345, with limits $2,000 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month Morph can pause each user's machine and wake it on request, while a Managed Agents sandbox has no inbound ports for users to open; boat ranks first, with HTTPS on up to 50 ports per sandbox. | 12th cheapest of 361 $905 a month | 231st of 361, with limits $823 a month | Cheapest of 361 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month Morph's memory branching suits rollouts that all start from one running state; Managed Agents has no fork at all, and boat forks a running sandbox with its disk. | 86th of 360, with limits $4,847 a month | 252nd of 360, with limits $3,978 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 Morph Cloud ranks 38th with a full fit, since each eval can branch from the same saved VM; Managed Agents runs only Claude through its own harness, so other agents cannot be compared there. | 38th cheapest of 364 $675 a month | 244th of 364, with limits $320 a month | 10th cheapest of 364 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Morph also sells managed GitHub Actions runners; Managed Agents does not document Docker beyond limited availability or /dev/kvm, which builds of Android apps and VM images need. | 39th cheapest of 377 $355 a month | 227th of 377, with limits $96 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Morph gives a dev box SSH and a disk that lasts while paused; Managed Agents has no SSH and keeps sandbox state only 30 days after the sandbox is created. | 85th cheapest of 368 $116 a month | 224th of 368, with limits $48 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 Neither ships computer use: Morph has a remote desktop you fill yourself and Managed Agents has headless Chromium only, while boat streams a 60fps desktop with Chromium and a computer use API. | 182nd of 369, with limits $595 a month | 127th of 369, with limits $288 a month | 6th cheapest of 369 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 214th of 367, with limits $250 a month | 126th of 367, with limits $288 a month | 7th cheapest of 367 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 239th of 346, with limits $234 a month | 127th of 346, with limits $390 a month | 6th cheapest of 346 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 154th of 338, with limits $4,750 a month | 155th of 338, with limits $4,798 a month | 71st of 338, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 214th of 360, with limits $228 a month | 179th of 360, with limits $160 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 | Morph Cloud | Claude Managed Agents | boat |
|---|---|---|---|
| Isolation | Full VM with its own kernel | Isolated Linux container per session | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | Sized as you choose, within an account pool of 64 vCPU / 256 GB on Developer up to 1,024 vCPU / 4,096 GB on Scale | Up to 8 GB memory and 10 GB disk; vCPU not published; not configurable | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Root, Docker and /dev/kvm | Root, Docker, systemd and Kubernetes inside; nested virtualization is experimental | Docker listed as limited availability; root, systemd and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Fork a running machine | Yes, with its memory, as many copies as you ask for, in under 250 ms | No fork or clone of a session or sandbox | Yes, with its disk |
| Sleep and wake | A paused VM keeps its memory, bills only its snapshot and wakes on the next HTTP request, SSH or exec call | An idle session is checkpointed, not billed, and resumes on the next message | No wake on request; a stopped sandbox is free and is started by API |
| What persists | Saved when you pause or snapshot; a plain stop deletes the instance | Checkpointed when idle; state kept only 30 days after the sandbox is created | The whole disk, saved every minute and on every stop, for as long as you keep the sandbox |
| Agents | You install the agent, then drive it through a tmux API that sends keys and reads the screen | Anthropic's harness with Claude models only, with events, steering, memory stores and webhooks | Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API |
| Desktop and browser | Browser-based remote desktop; you install the browser and any computer use agent yourself | Headless Chromium with Playwright; no desktop or computer use tool | Linux desktop streamed at 60fps, with Chromium and a computer use API |
| Inbound access | Named HTTP services with optional API key auth; SSH through Morph's gateway; no raw TCP | No inbound ports or SSH; reached only through the sessions and events API | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; SSH |
| Keeping API keys out of the sandbox | Responses Proxy for model APIs; other secrets are handed to the machine | Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host | Credentials proxy for model providers and any HTTPS API; a credential can switch to another account when credits run out |
| Outbound rules | Open internet; no allowlist documented | Unrestricted, or limited to listed hosts plus optional package registries and MCP servers | Open internet, no provider-side allowlist |
| Self-hosting | Hosted only; the Python and TypeScript SDKs are open source | Self-hosted sandboxes run tools on your own workers while Anthropic keeps the orchestration | No |
| Guest systems | Linux, with experimental Windows and macOS (x86) | Ubuntu 24.04 container | Linux |
| Where data lives | Regions not published | US workspace geo only; not eligible for Zero Data Retention | EU only (Germany, Finland, France), with zero data retention |
Every feature Battleships tracks (43)
| Feature | Morph Cloud | Claude Managed Agents | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Yes | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | No | Yes | No |
| GPU | No | No | No |
| Windows | Yes | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Yes | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Not published | Yes | No |
| SOC 2 | Not published | Yes | No |
| HIPAA | Not published | No | No |
| EU data residency | Not published | No | Yes |
| Zero data retention | Not published | No | Yes |
Performance
There is no comparable CPU measurement for either Morph Cloud or Claude Managed Agents: neither is in the hpc-sandbox-benchmarks run, and Anthropic does not publish how many vCPUs a sandbox gets. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB. Morph's under 250 ms figure is snapshot restore 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. Morph Cloud and Claude Managed Agents 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 | Morph Cloud, 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 | $32 · Developer | $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 | $121 · Team | $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 | $1,459 · Scale | $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 | $325 · Scale | $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 | $869 · Scale | $796 · Claude API (pay-as-you-go, usage tiers) · with limits | $2,000 · $2000/mo · with limits |
Morph Cloud: Morph bills MCUs at $0.05 each: per hour, a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. Team ($40 a month) and Scale ($250 a month) are prepaid MCU bundles at a discount, and a paused VM bills only its snapshot.
Claude Managed Agents: Managed Agents bills model tokens at API rates plus a flat session runtime fee, measured only while the session runs, including time spent waiting on the model. The tables show runtime only; tokens come on top and usually cost more.
Claude Managed Agents: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, a stopped sandbox costs nothing and keeps its disk, and model tokens for the built-in agents are paid to your model provider.
Limits in those scenarios
Morph prices each machine by its largest resource, so more than 16 GiB of disk per vCPU raises the bill, egress prices are not published, and the Developer pool of 64 vCPU holds only 16 machines at 4 vCPU. A Managed Agents sandbox has up to 8 GB of memory and 10 GB of disk with Docker in limited availability, which is why no scenario counts as a clean fit for it; Anthropic publishes no concurrent-session cap, only 300 creates per minute and usage-tier spend limits that pause all API use. boat has no session cap, but at 1,000 short jobs at once its $2,000 plan queues starts, while Morph Scale fits.
| Scenario | Morph Cloud | Claude Managed Agents | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None that bite |
| One agent that never stops |
|
| None that bite |
| 50 agents in parallel |
|
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Morph Cloud when
you bring your own agent and want full VMs that branch with their memory, sleep cheaply and wake on the next request.
- Branch a running VM with its memory. For agents that fan out from one running state: Morph copies a live VM with its memory into many branches in under 250 ms.
- A full machine that sleeps and wakes. For agents that need root and Docker but sit idle: a paused VM bills only its snapshot and wakes on the next request.
- Windows and macOS guests. For agents that must test software on other systems, Morph lists experimental Windows and macOS (x86) guests next to Linux.
Use Claude Managed Agents when
you want Claude itself to run long text and code tasks with no harness to build, idle time that costs nothing, and tools that can run on your own workers.
- No agent loop to build. For teams that want Claude doing long tasks: the harness, caching, compaction, memory stores and webhooks come ready to use.
- Idle time costs nothing. For agents that wait long between messages: runtime accrues only while the session runs, and the next message resumes it.
- Host allowlists and your own workers. For teams with strict network rules: limit a sandbox to listed hosts, or run every tool call on workers you host.
Where boat fits
Morph gives you a strong machine but no agent, and Managed Agents gives you an agent but a small, closed container. If you want both at once, a full VM with the agents already inside and ports you can open, look at boat.
Agents ready inside, driven from outside
On Morph you install Claude Code or Codex yourself and drive it by sending keystrokes to tmux and reading the screen. Managed Agents runs only Anthropic's harness with Claude, so Claude Code or Codex has to run somewhere else. boat has seven agents preinstalled with a prompt, steer and events API.
Open what the agent builds
A Managed Agents sandbox has no inbound ports or SSH, so a dev server the agent starts cannot be clicked. Morph offers named HTTP services but no raw TCP, and you assemble the desktop yourself. boat gives HTTPS on 50 ports, raw TCP and a 60fps desktop.
A disk that lasts on its own
On Morph a plain stop deletes the instance, so you must pause or snapshot to keep work. On Managed Agents sandbox state ends 30 days after creation. boat saves the whole disk every minute and on every stop, and a stopped sandbox is free.
Use boat when your agents need a real machine and arrive ready: Claude Code, Codex and more driven by API, Docker and /dev/kvm, a 60fps desktop, ports you can open, and a disk saved every minute in the EU. Compare it one to one: boat vs Morph Cloud and boat vs Claude Managed Agents.
Questions people ask
Is Morph Cloud cheaper than Claude Managed Agents?
On runtime alone, Managed Agents costs less in four of the five scenarios on this page, for example $53 a month against $121 for one agent that never stops. Morph costs less for sandboxes for your users, $325 a month against $360. Managed Agents adds model tokens on top, and its small container is not a clean fit for any scenario.
Which is faster, Morph Cloud or Claude Managed Agents?
Neither has a comparable CPU measurement, and Anthropic does not publish a sandbox's vCPU count. Morph restores a snapshot in under 250 ms, which is start time, not CPU speed. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB.
Can Claude Managed Agents run Docker?
Anthropic lists Docker in the cloud sandbox as limited availability, and root, systemd and /dev/kvm are not documented. Morph runs Docker, Docker in Docker and local Kubernetes inside a full VM. boat runs Docker, systemd and /dev/kvm in every sandbox.
Can I run Claude Code on Morph Cloud or Claude Managed Agents?
On Morph, yes: you install it in a Devbox and drive it through a tmux API that sends keystrokes and reads the screen. Managed Agents runs Anthropic's own harness with Claude models, not Claude Code. On boat, Claude Code, Codex and five other agents come preinstalled with a prompt, steer and events API.
Can I fork or branch a session?
Morph branches a running VM with its memory into many copies in under 250 ms, each continuing from the same point. Managed Agents has no fork or clone of a session or sandbox. boat forks a running sandbox with its disk, so the copy boots fresh.
Where does my data live?
Morph does not publish its regions. Managed Agents stores data and runs code in its US workspace geo only. boat runs only in the EU, in Germany, Finland and France, with zero data retention.
Try boat
Install the CLI, then run boat new.
7-day free trial