Claude Managed Agents vs Agent 37

Claude Managed Agents is Anthropic's hosted harness: you send events, and Claude works in a small container you never log into. Agent 37 hosts one sandbox per user with your choice of agent, reached through a chat API, SSH and HTTPS URLs, and it sleeps with its memory kept.

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

Agent 37

Agent 37 hosts AI agents, one isolated, always-on sandbox per user, behind one API.

You create an instance from a template (Hermes, OpenClaw, Claude Code, Codex, OpenCode, Pi, Grok or your own Docker image) and talk to it through a chat API, files, exec, SSH and HTTPS URLs. The default instance is a container enforced by gVisor; a VM type gives a full Linux machine with its own kernel for Docker, Kubernetes and Android emulators. It is built for companies that give each of their customers an agent.

Isolation: gVisor by default; opt-in full VM type with its own kernel and KVM
Where it runs: Dedicated servers in the United States
Billing: Prepaid wallet, metered per minute, no plan fee or seat charge
Instance types: Default (shared), Performance (dedicated cores), VM
Compliance: SOC 2 Type I, Type II in progress
Company: Y Combinator company based in New York

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	Agent 37: price rank	boat: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent needs Docker and room to build; Managed Agents caps the sandbox at 8 GB with Docker in limited availability, Agent 37 runs Docker only on its VM type, and boat has Docker and systemd in every VM.	106th of 367, with limits $964 a month	2nd cheapest of 367 $551 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 ranks 1st here: one always-on assistant per user that sleeps, keeps its memory and wakes on the next message; Managed Agents also wakes on the next message, but its sandbox state expires 30 days after creation.	219th of 366, with limits $2,511 a month	Cheapest of 366 $279 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 Agent 37's small default sandboxes suit short code runs; Managed Agents bills runtime only while the agent works, but model tokens come on top.	163rd of 345, with limits $756 a month	Cheapest of 345 $22 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 Managed Agents sandboxes have no inbound ports, so your users can't open what runs there; Agent 37 gives HTTPS URLs but caps self-serve at 200 instances, and boat ranks 1st with up to 50 ports per sandbox.	231st of 361, with limits $823 a month	30th of 361, with limits $79 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	252nd of 360, with limits $3,978 a month	6th of 360, with limits $363 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	244th of 364, with limits $320 a month	90th of 364, with limits $58 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 or full Docker fit Agent 37's VM type and every boat VM; Managed Agents documents neither.	227th of 377, with limits $96 a month	2nd cheapest of 377 $84 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Agent 37 and boat both keep a machine with SSH around the clock; Managed Agents has no SSH and reaches the sandbox only through the session API.	224th of 368, with limits $48 a month	3rd cheapest of 368 $12 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 Agent 37 ranks 1st with a noVNC desktop from a template build, Managed Agents has only headless Chromium, and boat streams a 60fps desktop in every sandbox.	127th of 369, with limits $288 a month	Cheapest of 369 $53 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	126th of 367, with limits $288 a month	48th of 367, with limits $29 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	127th of 346, with limits $390 a month	Cheapest of 346 $32 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	155th of 338, with limits $4,798 a month	36th of 338, with limits $648 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 Neither Managed Agents nor Agent 37 can fork a running machine; boat can copy one mid-task to try many paths at once.	179th of 360, with limits $160 a month	Cheapest of 360 $43 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	Claude Managed Agents	Agent 37	boat
What it is	A hosted Claude agent: Anthropic's harness runs Claude in a sandbox and you send it events	An agent host: one always-on sandbox per user, from a template such as Hermes, OpenClaw or Claude Code	A sandbox platform: each agent gets its own full Linux machine, with coding agents built in
Isolation	Isolated Linux container per session	gVisor by default; full VM with its own kernel as an opt-in type	Every sandbox is a 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	Shapes up to 16 vCPU / 32 GB after a first top-up; a 4 vCPU / 8 GB instance takes at most 20 GB disk	Up to 16 vCPU / 32 GB on the $100 plan and above
Docker inside	Listed as limited availability	Only on the VM type, at 2.5x the default compute rate	Yes, in every sandbox
systemd and /dev/kvm	Root, systemd and /dev/kvm not documented	/dev/kvm on the VM type; your entrypoint is PID 1 with no init system	systemd and /dev/kvm in every sandbox; Android emulators work
Agents	Anthropic's harness with Claude models only, with steering, memory stores, multiagent threads and webhooks	Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode and Pi, with a chat API per instance	Claude Code, Codex and five more preinstalled, driven from outside with a prompt, steer and events API
Idle and wake	An idle session is checkpointed, is not billed, and resumes on the next message	Opt-in auto-sleep (default 15 minutes) keeps memory and wakes on the next request; disk is still billed	No idle timer; a stopped sandbox costs nothing and keeps its disk, but reboots on resume
What persists	Sandbox state is kept only 30 days after the sandbox is created	The instance until you delete it, with daily backups plus one on-demand backup	The whole disk, saved every minute and on stop, for as long as you keep the sandbox
Fork	No fork or clone of a session or sandbox	No fork; backups restore in place only	Fork a running sandbox with its disk
Inbound access	No inbound ports or SSH; reached only through the sessions and events API	HTTPS URL per port, custom domains; no public IP, SSH through a WebSocket tunnel	HTTPS URLs for up to 50 ports, raw TCP, SSH, dedicated IPv6 or IPv4 per machine
Desktop and browser	Headless Chromium with Playwright; no desktop or computer-use tool	noVNC desktop through a template build or the Ubuntu VM template	60fps desktop and Chromium in every sandbox, with computer use
Keeping API keys out of the sandbox	Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host	Managed models, search and Composio go through a per-instance token; your own keys go in as env vars	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
Your own servers	Self-hosted sandboxes run tools on your own workers while Anthropic keeps the orchestration	No; Agent 37's servers only	No; boat's servers only
Where it runs	US workspace geo only	Dedicated servers in the United States	EU only (Germany, Finland, France), with EU data residency

Every feature Battleships tracks (43)

Feature	Claude Managed Agents	Agent 37	boat
Full VM (own kernel)	No	No	Yes
Docker inside	Not published	No	Yes
Nested virtualization	No	No	Yes
Root	Not published	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	No	Yes	Yes
Browser	Yes	Yes	Yes
Computer-use API	No	Yes	Yes
SSH	No	Yes	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	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	No	Yes	Yes
Raw TCP inbound	No	Not published	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	No	No
Secret proxy	Yes	Yes	Yes
Secret proxy for any API	Yes	No	Yes
Preinstalled agents	Yes	Yes	Yes
Agent harness API	Yes	Yes	Yes
MCP server	Yes	No	No
GPU	No	No	No
Windows	No	No	No
Arm64	No	No	No
Self-hosting	Yes	No	No
BYOC	Yes	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Yes	Yes
Usage per sandbox (API)	Yes	Yes	Yes
Audit logs	Not published	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	No	No	No
EU data residency	No	No	Yes
Zero data retention	No	Not published	Yes

Performance

Claude Managed AgentsNot measured

Agent 37Not measured

boat26.69 runs/s

There is no comparable measurement for either: neither Claude Managed Agents nor Agent 37 was part of the hpc-sandbox-benchmarks run, and Anthropic does not publish a sandbox's vCPU count. boat did 26.69 runs per second on the Node.js build-and-test loop at 4 vCPU / 8 GB. Agent 37 says its default instances share host resources and sells a Performance type on dedicated cores.

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 Agent 37 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	Agent 37, 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	$6 · Wallet (any top-up)	$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	$12 · Wallet (any top-up)	$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	$329 · Wallet ($100 lifetime top-ups)	$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	$33 · Wallet ($250 lifetime top-ups) · 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	$796 · Claude API (pay-as-you-go, usage tiers) · with limits	$73 · Wallet ($250 lifetime top-ups) · with limits	$2,000 · $2000/mo · with limits

Claude Managed Agents: Managed Agents bills model tokens at API list rates plus a flat session runtime fee, metered only while the session is running, including time spent waiting on the model. The table shows runtime only; tokens come on top and usually cost more.

Agent 37: A prepaid wallet with no plan fee, metered per minute: $0.80 per vCPU and $0.70 per GB of RAM per month while running, and $0.09 per GB of disk per month even while stopped or asleep. VM compute costs 2.5x and Performance compute 4x the default rate.

Agent 37: 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, no published vCPU count and Docker only in limited availability, so no scenario counts as a clean fit; it publishes no concurrency cap, only 300 creates per minute and usage-tier spend limits. Agent 37's cap is 10 instances after a first top-up, 50 at $100 and 200 at $250 of lifetime top-ups, counting sleeping and stopped ones, which is why it misses 300 user sandboxes and 1,000 jobs at once. boat has no session cap, but its $2,000 plan allows 2,400 starts a day, which stops it in the 1,000-at-once burst.

Scenario	Claude Managed Agents	Agent 37	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	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	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	egress price not published	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)	max 200 concurrent egress price not published	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)	max 200 concurrent shared vCPUs on this tier: heavy, sustained CPU use can be slowed by other tenants egress price not published	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 text and code tasks with no harness to build, free idle time, and the option of host allowlists or 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 time is 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 infrastructure.

Use Agent 37 when

you host one mostly idle assistant per customer in the US, with your choice of agent, that should sleep with its memory kept and wake on the next message.

Any agent, in a machine you can reach. Teams that want Hermes, OpenClaw, Codex or Claude Code get SSH, files, exec and HTTPS URLs on each instance.
Sleeps with its memory kept. Useful for assistants that sit idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
Your own image, dedicated cores. Agent 37 builds templates from your own Docker image, and sells a Performance type on dedicated cores.

Where boat fits

Look at boat when your agents do real machine work for hours: installs, builds, Docker, emulators and apps you want to open. Managed Agents gives Claude a small container with no way in, and Agent 37 saves its full VM for an opt-in type. boat makes every sandbox a full VM in the EU.

A full VM in every sandbox

Managed Agents caps a sandbox at 8 GB with Docker in limited availability. On Agent 37 Docker needs the VM type at 2.5x the compute rate, with no systemd. boat has root, Docker, systemd and /dev/kvm everywhere.

Fork a machine while it runs

Neither can copy a running sandbox, so every new try rebuilds its setup from scratch. Managed Agents state also expires after 30 days. boat forks a running sandbox and saves its disk every minute until you delete it.

Keys outside for any API, any agent

Managed Agents runs only Claude in Anthropic's harness. On Agent 37 your own API keys sit as env vars inside a machine the agent controls. boat's proxy keeps keys outside for any HTTPS API, for Claude Code, Codex and more.

Use boat when your agents need a real machine: Docker, emulators, a desktop, ports you can open, forks of running sandboxes, and keys kept outside for any API. Compare it one to one: boat vs Claude Managed Agents and boat vs Agent 37.

Questions people ask

Is Claude Managed Agents cheaper than Agent 37?

No. For runtime alone, Agent 37 is lower in every scenario on this page, for example $12 a month against $53 a month for one agent that never stops. Managed Agents also bills model tokens on top, while Agent 37 tops out at 200 instances on self-serve.

Which is faster, Claude Managed Agents or Agent 37?

There is no comparable measurement for either one. Anthropic does not publish a sandbox's vCPU count, and Agent 37 has no result on the hpc-sandbox-benchmarks run, where boat did 26.69 runs per second at 4 vCPU / 8 GB.

Can Claude Managed Agents or Agent 37 run Docker?

Managed Agents lists Docker as limited availability. Agent 37 runs Docker only on its VM type, at 2.5x the default compute rate; the default gVisor type cannot run a Docker daemon. On boat, Docker works in every sandbox.

Can I run Claude Code on Claude Managed Agents or Agent 37?

Not on Managed Agents, which runs Anthropic's own harness with Claude models. Agent 37 offers Claude Code as a template, next to Hermes, OpenClaw, Codex and others. boat has Claude Code, Codex and five more preinstalled.

Can I open a web app my agent built?

On Managed Agents, not directly: the sandbox has no inbound ports and is reached through the sessions API. Agent 37 gives an HTTPS URL per port. boat gives HTTPS URLs on up to 50 ports, raw TCP and SSH.

Where do Claude Managed Agents and Agent 37 run?

Both run in the United States: Managed Agents follows the workspace geo, which is US only today, and Agent 37 uses dedicated US servers. boat runs only in the EU, in Germany, Finland and France.

Try boat

Install the CLI, then run boat new.

7-day free trial