exe.dev vs Claude Managed Agents
exe.dev rents you Linux VMs with root, Docker and SSH that run until you stop them, and you bring the agent. Claude Managed Agents is Anthropic's hosted agent: you send Claude a task and it works in a small container that Anthropic runs and you never log into.
The companies and products
exe.dev
exe.dev, made by Bold Software, Inc., rents Linux VMs for developers and AI agents that you reach over SSH and HTTPS.
You reserve a pool of vCPUs and memory, and your VMs share it; you can also start standalone VMs billed by the second. Each VM is KVM-isolated (they use Cloud Hypervisor), boots from a container image in about two seconds, and has root, systemd and Docker. It comes with Claude Code, Codex, Pi and exe.dev's own Shelley agent, and is aimed at developers who want a persistent dev box or a sandbox for their agents.
- Company
- Bold Software, Inc.
- Preinstalled agents
- claude, codex, pi and the Shelley web agent
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. “15th cheapest of 366” means 14 of the other 365 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 | exe.dev: 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 Managed Agents does better than exe.dev here, but its container has up to 8 GB of memory and Docker only in limited availability; boat gives each agent a full VM with Docker and a desktop. | 253rd of 367, with limits $3,701 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 exe.dev fits always-on assistants fully, with a VM and disk that last; Managed Agents sleeps between messages for free, but its sandbox state is kept only 30 days after creation. | 15th cheapest of 366 $3,833 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 Neither is built as a code interpreter; Managed Agents bills runtime only while the agent works, which helps short bursts with long gaps. | 235th of 345, with limits $175 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 exe.dev Personal stops at 50 VMs at once and Managed Agents has no inbound ports for users to open; boat fits fully with token-protected URLs. | 257th of 361, with limits $1,226 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 | 265th of 360, with limits $5,250 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 | 283rd of 364, with limits $1,050 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 CI jobs that need /dev/kvm get it on exe.dev only on Enterprise and not at all on Managed Agents; boat has it on every plan. | 288th of 377, with limits $504 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 exe.dev makes a solid 24/7 dev box with SSH and a lasting disk; Managed Agents has no SSH at all, and boat adds a desktop in the browser. | 25th cheapest of 368 $35 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 exe.dev nor Managed Agents has a desktop or computer-use tool; boat streams a 60fps Linux desktop. | 240th of 369, with limits $1,055 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 | 130th of 367, with limits $530 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 | 124th of 346, with limits $278 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 | 166th of 338, with limits $5,490 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 exe.dev does better than Managed Agents for parallel red teaming, since each attacker gets a real VM; boat fits fully with forks of a running sandbox. | 60th of 360, with limits $263 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 | exe.dev | Claude Managed Agents | boat |
|---|---|---|---|
| What it is | Linux VMs for developers and agents, reached over SSH and HTTPS | A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events | A sandbox platform: each agent gets its own full Linux VM, with coding agents built in |
| Isolation | KVM VM with Cloud Hypervisor; you can't choose the kernel | Isolated Linux container per session | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | Pools up to 16 vCPU on Personal; standalone VMs capped at 2 GiB memory per vCPU | 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 |
| Docker, systemd and /dev/kvm | Root, systemd and Docker; nested virtualization on Enterprise only | Docker listed as limited availability; root, systemd and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm on every plan |
| Desktop and computer use | Headless; no desktop or screen streaming | Headless Chromium with Playwright; no desktop or computer-use tool | 60fps desktop with Chromium, computer use and browser control |
| Saved state | Disk persists and is streamed to a second server; no snapshots | Checkpointed when a session goes idle; kept only 30 days after the sandbox is created | Snapshots every minute and on stop, kept as long as you keep the sandbox |
| Fork | cp copies a VM's disk and config into a new VM | No fork or clone of a session or sandbox | Fork a running sandbox; named snapshots as templates |
| Wake on next message | No; VMs run until you stop them | Yes; an idle session resumes on the next message, and idle time is not billed | No; a stopped sandbox is started by API |
| Inbound access | HTTPS proxy for ports 3000 to 9999, one of them public; SSH; no public IP or 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 |
| Agents | Claude Code, Codex, Pi and Shelley; only Shelley takes prompts through the API | Anthropic's harness with Claude models, events, steering, multiagent threads, memory and webhooks | Claude Code, Codex and five more, driven from outside with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Integrations inject secrets at the network edge for any HTTP host | Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host | Credentials proxy for any HTTPS API; switch to another account when credits run out |
| Outbound rules | Open internet | Unrestricted, or limited to listed hosts plus package registries and MCP servers | Open internet, no provider-side allowlist |
| Run on your own infrastructure | BYOC on AWS or GCP and dedicated hardware on Enterprise | Self-hosted sandboxes run tools on your own workers | No |
| Regions | 9 regions in the US, Europe, Asia and Australia | US workspace geo only | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | exe.dev | 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 | No | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | Yes | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | No | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | No | Yes | No |
| Wake on request | No | 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 | Yes | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | Yes | Yes | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | 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 | Not published | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | No | Yes | No |
| HIPAA | No | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | No | Yes |
Performance
Neither exe.dev nor Claude Managed Agents was part of the hpc-sandbox-benchmarks run, and Anthropic does not publish how many vCPUs a Managed Agents sandbox gets, so there is no comparable measurement for either. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB. We don't guess how the other two would score.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. exe.dev 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 | exe.dev, 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 | $35 · Personal | $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 | $35 · Personal | $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 | $1,848 · Personal | $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 | $530 · Personal · with limits | $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 | $1,050 · Personal · with limits | $796 · Claude API (pay-as-you-go, usage tiers) · with limits | $2,000 · $2000/mo · with limits |
exe.dev: exe.dev sells pools of reserved vCPU and memory that your VMs share, billed the same whether busy or idle. Standalone VMs bill per second at $0.105 per 2 vCPU / 4 GiB per hour and pay nothing for CPU and memory while stopped.
Claude Managed Agents: Managed Agents bills model tokens at API rates plus a flat session runtime fee, metered only while a session runs, including time waiting on the model. The table shows 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. Sandboxes bill per second while running, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
On exe.dev Personal you get one pool of up to 16 vCPU and 50 VMs, plus up to 50 standalone VMs, so the 300-at-once and 1,000-at-once scenarios don't fit. 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 for it; Anthropic publishes no session cap, only 300 creates per minute and usage-tier spend limits that pause all API use when reached. boat has no session cap, but at 1,000 short jobs at once even the $2,000 plan queues starts above 90 per minute.
| Scenario | exe.dev | 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 |
| None that bite |
| Sandboxes for your users |
|
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use exe.dev when
you want a lasting Linux VM you SSH into, booted from your own Docker image, in a region near your users.
- A VM you own and log into. Developers who want a lasting Linux box get root, Docker, SSH and a disk that stays until they delete it.
- Your own Docker image. Teams with a Dockerfile can boot each exe.dev VM straight from their own image in about two seconds.
- Regions around the world. Useful if your users are far from Europe or the US: exe.dev runs in nine regions, including Asia and Australia.
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.
- 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.
Where boat fits
If you are choosing between these two, you want an agent that does real work on a real machine. exe.dev gives you the machine but no screen, no snapshots and one agent you can prompt by API; Managed Agents gives you the agent but a small container you can't open. boat gives each agent a full VM with a desktop, state saved every minute and an API to drive agents inside from outside.
A full machine with a screen
Managed Agents runs in a container with up to 8 GB of memory and Docker in limited availability, and exe.dev puts /dev/kvm behind Enterprise. Both are headless, so a computer-use agent has no screen unless you build and stream one yourself.
State saved every minute
exe.dev has no snapshots, so one bad agent step can wreck a whole VM. Managed Agents keeps sandbox state only 30 days after creation, so a returning agent redoes its setup. boat snapshots every minute and keeps the disk.
Open what agents build, drive any agent
Managed Agents has no inbound ports and runs only Claude's harness. exe.dev has one public port and no raw TCP, and only Shelley takes API prompts. boat opens 50 ports and drives Claude Code, Codex and more by API.
Use boat when your agents need a real machine: Docker, emulators, a desktop and browser, ports you can open, state saved every minute, and the choice of Claude Code, Codex or other agents driven from outside. Compare it one to one: boat vs exe.dev and boat vs Claude Managed Agents.
Questions people ask
Is exe.dev cheaper than Claude Managed Agents?
For runtime alone, Managed Agents costs less in four of our five scenarios, because it bills only while the agent works. For one agent that never stops, exe.dev is lower at $35 against $53 a month. Managed Agents also bills model tokens on top, which usually cost more than the runtime.
Which is faster, exe.dev or Claude Managed Agents?
We can't say: neither was in the hpc-sandbox-benchmarks run, and Anthropic does not publish a Managed Agents sandbox's vCPU count. On Managed Agents much of a session's time is spent waiting on the model rather than the CPU.
Can exe.dev and Claude Managed Agents run Docker?
exe.dev VMs come with root, systemd and Docker, and can boot from your own Docker image. Managed Agents lists Docker only as limited availability inside its container. boat has Docker, systemd and /dev/kvm on every plan.
Can I run Claude Code on exe.dev or Claude Managed Agents?
exe.dev preinstalls Claude Code, Codex and Pi, though only its own Shelley agent takes prompts through the API. Managed Agents runs Anthropic's own harness with Claude models, not Claude Code. boat preinstalls Claude Code, Codex and five more agents, all driven by one API.
Can I open a web app my agent built?
On exe.dev, yes, through its HTTPS proxy on ports 3000 to 9999, with one port public. On Managed Agents, no: the sandbox has no inbound ports and is reached only through the sessions API. boat gives each sandbox HTTPS URLs on up to 50 ports, raw TCP and SSH.
Where do exe.dev and Claude Managed Agents run?
exe.dev has nine regions in the US, Europe, Asia and Australia. Managed Agents stores data and runs code in the US workspace geo only. boat runs only in the EU, in Germany, Finland and France.
Try boat
Install the CLI, then run boat new.
7-day free trial