Runloop vs Agent 37

Runloop gives each coding agent a micro-VM devbox, with hostname egress rules, arm64 and deploys into your own cloud. Agent 37 gives each user a lighter gVisor sandbox that sleeps when idle, keeps its memory and costs far less per hour.

The companies and products

Runloop

Runloop is a US platform of sandboxes, called devboxes, for building, running and testing AI coding agents.

You get Linux devboxes built from Dockerfile-style blueprints, disk snapshots, HTTPS tunnels, agent gateways that hide API keys, and Axons, event streams that drive agents such as Claude Code. Each devbox runs in a micro-VM on Runloop's own bare-metal hypervisor, with a container layer inside. It is built for teams shipping coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.

Isolation: Micro-VM on a custom bare-metal hypervisor, with a container layer on top
Compliance: SOC 2 Type 2
Architectures: x86_64 and arm64 base blueprints
Own-cloud deploy: Deploy to VPC on AWS, GCP and Azure (Enterprise)
Regions: Not documented or selectable
Plans: Basic (usage only), Pro ($250/month plus usage), Enterprise (custom)
Company: Runloop AI, Inc.

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. “20th cheapest of 367” means 19 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	Runloop: price rank	Agent 37: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Agent 37 ranks 2nd and Runloop ranks 20th; bochka ranks 3rd and gives every agent Docker, systemd and /dev/kvm on a full VM without an extra instance type.	20th cheapest of 367 $8,152 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: an always-on assistant per user sleeps when idle, keeps its memory and wakes on the next message, while Runloop's suspend needs the Pro plan.	32nd cheapest of 366 $10,194 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; bochka's start limits make very large bursts a poor fit.	44th cheapest of 345 $525 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 bochka ranks 1st; Agent 37 is a compromise because its cap of 200 instances counts sleeping and stopped ones, and Runloop fits at a higher bill.	26th cheapest of 361 $3,301 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 Runloop ranks 4th for RL rollouts: it starts large waves without published start limits, while Agent 37's self-serve tiers stop at 200 instances.	4th cheapest of 360 $15,922 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	81st cheapest of 364 $2,562 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 Agent 37 ranks 2nd and bochka 4th; Docker builds on Agent 37 need its VM type, and Runloop's CPU ran about three times slower than bochka's in the same benchmark.	121st cheapest of 377 $1,554 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	113th cheapest of 368 $410 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 All three ship a desktop and a browser an agent can control; bochka streams its desktop at 60fps and you can embed it in your app.	39th cheapest of 369 $2,306 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	40th cheapest of 367 $1,153 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	68th cheapest of 346 $781 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	266th of 338, with limits $15,611 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 Agent 37 ranks 1st and bochka 2nd; Runloop can lock each devbox to a hostname allowlist, which neither of the others offers.	10th cheapest of 360 $770 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	Runloop	Agent 37	bochka
Isolation	Micro-VM on a custom bare-metal hypervisor, plus a container layer	gVisor by default; full VM as an opt-in instance type	Every sandbox is a full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Docker inside	Yes, on the Docker-in-Docker blueprints, as root	Only on the VM type, at 2.5x the default compute rate	Yes, in every sandbox, with root and systemd
Nested virtualization	Not documented	/dev/kvm on the VM type, with a ready Android template	/dev/kvm in every sandbox; Android emulators and VMs run inside
CPU speed (Node.js benchmark, 4 vCPU / 8 GB)	8.29 runs a second	No published result; shared cores by default, dedicated cores on the Performance type at 4x	26.69 runs a second
CPU architecture	x86_64 and arm64	linux/amd64 images	x86_64 only
Images	Blueprints built from Dockerfiles, plus disk snapshots	Your own linux/amd64 Docker image as a template	Templates from named snapshots of a running sandbox, no Dockerfile builds
Sleep when idle	Suspend after idle, wake on an HTTP request (Pro plan)	Auto-sleep after a quiet period, memory checkpointed, wakes on the next request	No idle timer; a time limit you set (default 1 hour), or no limit
Keeping files	Disk kept through suspend (Pro) or manual disk snapshots; shutdown ends the devbox	Disk kept while stopped or asleep; daily backups plus one on-demand backup	Snapshot every minute and on stop, on every plan; resume with the same disk
Long runs	Fixed lifetime 1 hour by default, 48 hours max; an idle policy replaces it	Runs until you stop it or it sleeps	No session cap on paid plans
Fork a running machine	Disk snapshots of a devbox to start new ones from	No fork; backups restore in place only	Fork a running sandbox; named snapshots as shareable templates
Inbound networking	One HTTPS tunnel per devbox; SSH through a TLS proxy; no public IP	HTTPS URL per port, custom domains; no public IP; SSH through a WebSocket tunnel	HTTPS URLs for up to 50 ports, raw TCP, dedicated IPv6 or IPv4
Egress rules	Hostname allowlist with wildcards, or block all	Open internet, no allowlist	Open internet, no provider-side allowlist
Keys kept out of the sandbox	Agent gateways for any API endpoint	Managed LLM, search and Composio; your own keys go in as env vars	Credentials proxy for model providers and any HTTPS API; switch to another account when one runs out of credits
Where it runs	Regions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise)	Dedicated servers in the United States	EU only (Germany, Finland, France), EU data residency

Every feature Battleships tracks (43)

Feature	Runloop	Agent 37	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	Yes	No	Yes
Nested virtualization	No	No	Yes
Root	Yes	Yes	Yes
Systemd	Not published	Not published	Yes
Desktop GUI	Yes	Yes	Yes
Browser	Yes	Yes	Yes
Computer-use API	Yes	Yes	Yes
SSH	Yes	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	Yes	Yes
Automatic snapshots	Yes	Yes	Yes
Fork/clone	Yes	Yes	Yes
Live fork (no pause)	Yes	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	Yes	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	Yes	No	No
Self-hosting	No	No	No
BYOC	Yes	No	No
Open source	No	No	No
Scoped API keys	Yes	Not published	Yes
Spend limits	Not published	Yes	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Not published	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	Not published	No	No
EU data residency	No	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

Runloop8.29 runs/s

Agent 37Not measured

bochka26.69 runs/s

On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB (run 36498291449, 2026-09-29), bochka scored 26.69 runs a second and Runloop 8.29, about 3.2 times apart. Agent 37 has no published result on that benchmark, so there is no comparable measurement. 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. Agent 37 has 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	Runloop, a month	Agent 37, a month	bochka, 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	$113 · Basic	$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	$429 · Basic	$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	$5,268 · Basic	$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	$1,441 · Basic	$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	$3,184 · Basic	$73 · Wallet ($250 lifetime top-ups) · with limits	$2,000 · $2000/mo · with limits

Runloop: Runloop bills per second for the CPU and memory you allocate, while a devbox is starting, running, suspending or resuming, and bills its disk for the devbox's whole life. Basic has no plan fee; Pro adds $250 a month that is not usage credit and unlocks suspend and resume.

Agent 37: Agent 37 uses 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. Performance compute costs 4x and VM compute 2.5x the default rate.

Agent 37: Plans start at $20 a month and the whole fee is usage credit, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Agent 37's instance cap is 10 after your first top-up, 50 at $100 of total top-ups and 200 at $250, and it counts sleeping and stopped instances, so sandboxes for your users and 1,000 jobs at once do not fit. Its 50-agent price uses the VM type, since that scenario needs Docker. Runloop publishes no concurrency cap on paid plans and no egress price, and its fixed lifetime tops out at 48 hours unless an idle policy replaces it. bochka's limit that bites is start rate, which stops it in the 1,000-at-once burst.

Scenario	Runloop	Agent 37	bochka
One coding agent, workdays	egress price not published	egress price not published	None that bite
One agent that never stops	egress price not published	egress price not published	None that bite
50 agents in parallel	egress price not published	egress price not published	None that bite
Sandboxes for your users	egress price not published	max 200 concurrent egress price not published	None that bite
1,000 short jobs at once	egress price not published	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 Runloop when

you need hostname allowlists, arm64, devboxes inside your own AWS, GCP or Azure account, or very large bursts of short jobs.

Lock down the network. Useful if a sandbox must only reach a fixed list of hosts: Runloop allows listed hostnames, with wildcards, or blocks everything.
Run it in your own cloud. On the Enterprise plan, Runloop can run devboxes inside your own AWS, GCP or Azure account.
arm64 and big bursts. Runloop offers arm64 blueprints and publishes no concurrency cap on paid plans, so 1,000 short jobs at once fit.

Use Agent 37 when

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

Sleeps when idle and keeps its memory. Useful for assistants that sit idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
A low bill for light, steady work. Agent 37 meters per minute from a prepaid wallet with no plan fee, and its default rates are the lowest of the three.
Runs in the United States. Agent 37 runs on dedicated servers in the US, closer to US users.

Where bochka fits

If your agents do real work for hours, installing packages, building, testing and running Docker, look at bochka. Every bochka sandbox is a full VM with Docker, systemd and /dev/kvm, on CPUs that ran about three times faster than Runloop's, with files kept on every plan.

A full Linux machine in every sandbox

Runloop documents Docker-in-Docker but not /dev/kvm, so Android emulators and VMs do not start. Agent 37 runs Docker only on its VM type, at 2.5x the compute rate, and with no init system.

Faster CPUs for builds and tests

bochka scored 26.69 runs a second and Runloop 8.29 on the same benchmark, so every install and test waits about three times longer there. Agent 37 has no published score and shares cores unless you pay 4x for Performance.

Real hosting, not just tunnels

Runloop and Agent 37 give no public IP and reach SSH through a proxy or tunnel, so a database or server speaking raw TCP has no way in. bochka gives HTTPS on up to 50 ports, raw TCP and a dedicated IP.

Use bochka when your agents do real work for hours: installs, builds, tests, Docker and emulators on a full VM with fast CPUs, forks of running machines and raw TCP hosting. Compare it one to one: bochka vs Runloop and bochka vs Agent 37.

Questions people ask

Is Runloop cheaper than Agent 37?

No. In our scenarios Agent 37 is far lower: one coding agent on workdays costs $6 a month on Agent 37 and $113 on Runloop, and one agent that never stops costs $12 versus $429. Runloop fits sandboxes for your users and 1,000 jobs at once, where Agent 37's 200-instance cap does not.

Which is faster, Runloop or Agent 37?

We can't say. Runloop scored 8.29 runs a second on the Node.js build-and-test benchmark at 4 vCPU / 8 GB, and Agent 37 has no published result. bochka scored 26.69 on the same test.

Can Agent 37 or Runloop run Docker?

Runloop runs Docker on its Docker-in-Docker blueprints. Agent 37 runs Docker only on its VM type, which bills compute at 2.5x; the default gVisor type cannot run a Docker daemon. On bochka, Docker works in every sandbox.

Can I run Android emulators on Runloop or Agent 37?

Agent 37's VM type exposes /dev/kvm and has a ready Android template. Runloop does not document nested virtualization. bochka exposes /dev/kvm in every sandbox.

Which one sleeps an idle agent and wakes it?

Both can. Runloop suspends an idle devbox and wakes it on an HTTP request, on the Pro plan. Agent 37 sleeps on idle, keeps the memory, and wakes on the next request on any wallet.

Where do Runloop, Agent 37 and bochka run?

Agent 37 runs on dedicated servers in the United States. Runloop does not document regions, and on Enterprise it can deploy into your own AWS, GCP or Azure account. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview