Railway vs Agent 37
Railway is an app platform whose sandboxes are short-lived VMs, destroyed when they go idle and built to sit next to your apps and databases. Agent 37 hosts one always-on agent per user in a gVisor sandbox that sleeps when idle, keeps its memory and wakes on the next message.
The companies and products
Railway
Railway is a cloud platform for deploying web apps, servers and databases, which now also sells sandboxes and cloud agents.
Railway's main product is app hosting: you deploy services and databases as containers on its own hardware. In 2026 it added Sandboxes, isolated Linux VMs you create from the CLI or a TypeScript SDK, run commands in and destroy, and Cloud Agents, a personal VM for running a coding agent, in early access. It suits teams already hosting on Railway who want throwaway machines next to their apps.
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.
- Where it runs
- Dedicated servers in the United States
- Instance types
- Default (shared), Performance (dedicated cores), VM
- Compliance
- SOC 2 Type I, Type II in progress
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 366” means 15 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 | Railway: 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 Agent 37 ranks 2nd and boat 3rd; Railway is only a compromise because its sandboxes are destroyed when idle, so you save work yourself with checkpoints. | 51st of 367, with limits $342 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: each assistant sleeps when idle, keeps its memory and wakes on the next message, while on Railway an always-on assistant needs the idle timeout set to 0 or a Cloud Agent, and memory bills the whole time. | 16th cheapest of 366 $3,977 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 ranks 1st with small default sandboxes, Railway fits too because it bills for CPU used and destroys the sandbox when the job ends, and boat's start limits make big bursts a poor fit. | 36th cheapest of 345 $413 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 boat ranks 1st: Railway allows 100 sandboxes per environment on Pro, and Agent 37 stops at 200 instances on its top self-serve tier, counting sleeping and stopped ones. | 42nd of 361, with limits $290 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 | 78th of 360, with limits $4,450 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 boat ranks 10th; Railway can fork a running sandbox and boot many from one checkpoint but caps how many run per environment, and Agent 37 has no fork. | 108th of 364, with limits $364 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 build containers need Docker: boat has it on every machine, Agent 37 only on its VM type, and Railway's sandbox docs do not mention it. | 113th cheapest of 377 $1,210 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 | 66th cheapest of 368 $89 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 Railway sandboxes are headless with no desktop, Agent 37 adds a noVNC desktop through a template build, and boat streams a 60fps desktop out of the box. | 77th of 369, with limits $103 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 | 53rd of 367, with limits $93 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 | 60th cheapest of 346 $570 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 | 109th of 338, with limits $2,988 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 boat 2nd; boat can also fork a machine that is already running to try many paths at once, which Agent 37 cannot. | 43rd of 360, with limits $574 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 | Railway | Agent 37 | boat |
|---|---|---|---|
| Kind of product | App platform for web apps and databases, with sandboxes added in 2026 | Hosting for AI agents, one always-on sandbox per user behind one API | Sandboxes for agents, each one a full VM |
| Isolation | Sandboxes are isolated Linux VMs; app services are containers | gVisor by default; a full VM as an opt-in instance type | Every sandbox is a full VM with its own kernel |
| When the sandbox goes idle | Destroyed after the idle timeout (30 minutes by default); files survive only in checkpoints you take | Opt-in auto-sleep after a quiet period (default 15 minutes), memory kept, wakes on the next request | No idle timer; you stop it, the disk is kept with snapshots every minute, and a stopped sandbox costs nothing, but resume reboots |
| Docker and /dev/kvm | Root shell on Ubuntu; the sandbox docs do not mention Docker or /dev/kvm | Only on the VM type, at 2.5x the default compute rate, with no init system | Docker, root, systemd and /dev/kvm on every machine |
| Fork and snapshots | Fork a running sandbox's filesystem; named disk checkpoints to boot new ones | No fork; daily backups plus one on-demand backup, restored in place only | Fork a running sandbox; snapshots every minute; named snapshots as shareable templates |
| Custom images | Templates built from ordered steps (apt packages, env, commands) and cached | Your own linux/amd64 Docker image as a template | Templates from named snapshots, no Dockerfile builds |
| Coding agents | Claude Code, Codex, OpenCode and Pi preinstalled; you run them headless through exec | Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode and Pi, with a chat API per instance | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Keeping keys out of the sandbox | Secrets go in as environment variables, or are signed in and saved in a checkpoint | Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars | Credentials proxy for model providers and any HTTPS API you register; switch to another account when credits run out |
| Desktop and computer use | Headless: terminal, exec and SSH only | noVNC desktop through a template build or the Ubuntu VM template | 60fps desktop and Chromium in every sandbox, computer use, embeddable stream |
| Reaching the sandbox | Up to 10 public HTTPS domains, set only at creation; SSH and port forwarding | HTTPS URL per port, signed URLs, custom domains; no public IP, SSH through a WebSocket tunnel | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 |
| CPU | Railway Metal, hardware Railway owns and runs | Shared by default; a Performance type on dedicated cores at 4x the compute rate | Shared vCPUs on dedicated AMD Ryzen 9 9950X hosts |
| Biggest sandbox | 8 vCPU / 8 GB on Hobby, 32 vCPU / 32 GB on Pro | Up to 16 vCPU / 32 GB after the first top-up | 8 vCPU / 16 GB on the $20 plan, 16 vCPU / 32 GB from $100 |
| Sandboxes at once | 50 per environment on Hobby, 100 on Pro; Enterprise can ask for more | 1, 10, 50 or 200 by lifetime top-ups, counting sleeping and stopped instances | 100 to 2,000 by plan |
| Regions | US West, US East, Amsterdam and Singapore | Dedicated servers in the United States | EU only: Germany, Finland, France, with EU data residency |
Every feature Battleships tracks (43)
| Feature | Railway | Agent 37 | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Not published | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | 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 | No | Yes | No |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | No | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | 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 | No | 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) | No | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Railway or Agent 37: neither has a result in StarSling's hpc-sandbox-benchmarks yet. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in that benchmark. 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. Railway 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 | Railway, 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 | $16 · Hobby · 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 | $70 · Hobby · 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 | $739 · Hobby · 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 | $223 · Pro · 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 | $781 · Pro · with limits | $73 · Wallet ($250 lifetime top-ups) · with limits | $2,000 · $2000/mo · with limits |
Railway: Railway bills sandboxes per second at $50 per vCPU-month on CPU actually used and $50 per GB-month on memory in use, plus $0.05 per GB out, and memory keeps billing while a sandbox waits. The Hobby ($5) and Pro ($20) fees count toward usage, and there is no published price for sandbox disk, so our bills leave disk out.
Agent 37: Agent 37 uses a prepaid wallet with no plan fee, metered per minute on what you allocate: $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: A monthly plan from $20, and all of it is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Railway is marked as not a clean fit in every scenario because it is an app platform first and does not price sandbox disk, and its cap of 100 sandboxes per environment on Pro means 300 sandboxes for your users or 1,000 jobs at once need several environments. Agent 37 stops at 200 instances on its top self-serve tier, counting sleeping and stopped ones, so those two scenarios do not fit there either. The 50-agent fleet needs Docker, so Agent 37 is priced on its VM type at 2.5x compute, and Railway's docs do not confirm Docker at all. On boat, the 1,000-job burst is queued above 90 starts a minute and needs more starts per day than the $2,000 plan allows.
| Scenario | Railway | Agent 37 | 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 Railway when
your app and databases already live on Railway and you want short-lived sandboxes on the same private network, or you need regions in the US or Asia.
- Your apps and databases in one place. Useful if your app already runs on Railway: a sandbox can join the private network of your Postgres and services.
- Fork a running sandbox. Useful for trying many paths from one state: Railway can fork a running sandbox's filesystem, which Agent 37 cannot.
- Regions in the US, EU and Asia. Useful if your users are spread out: Railway runs in California, Virginia, Amsterdam and Singapore.
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.
- Bring your own Docker image. Useful if you already ship a Dockerfile: Agent 37 uses your own image as a template.
- Built for one agent per customer. Useful for giving each customer an agent: every instance comes from an agent template and has its own chat API.
Where boat fits
If your agents do real work for hours, like installs, builds, tests, Docker and browsers, look at boat. Every sandbox is a full VM that keeps its disk, can be forked while it runs, has a 60fps desktop, and runs coding agents you drive from outside while their keys stay outside.
Docker on every machine
Railway's sandbox docs do not mention Docker or /dev/kvm. Agent 37's default gVisor type cannot run a Docker daemon, and its VM type costs 2.5 times as much compute and has no systemd.
A disk that stays, and forks of running machines
A Railway sandbox is destroyed after 30 idle minutes unless you set the timeout to 0, and then memory bills until you destroy it. Agent 37 has no fork, and its backups restore only onto the same instance.
Keys outside, agents driven from outside
On both, your own API keys sit inside the machine as env vars, where code the agent runs can read them. boat's proxy covers any HTTPS API, and its prompt, steer and events API replaces parsing exec output.
Use boat when your agents work for hours or days: a full VM with Docker and a desktop that keeps its disk, forks while running, and runs coding agents you drive from outside with keys kept outside. Compare it one to one: boat vs Railway and boat vs Agent 37.
Questions people ask
Is Railway cheaper than Agent 37?
No, Agent 37 comes out lower in every scenario we price. One agent running all month is $70 on Railway against $12 on Agent 37, and 50 agents in parallel are $739 against $329, with boat at $317. Railway's numbers also leave out disk, which it does not price.
Which is faster, Railway or Agent 37?
We cannot say: neither has a result in StarSling's hpc-sandbox-benchmarks. boat did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB there. Agent 37 sells a Performance type on dedicated cores if you need steady speed.
Can Railway or Agent 37 run Docker?
Railway's sandbox docs do not mention Docker. Agent 37 runs Docker and Compose on its VM type, which bills compute at 2.5x, but not on its default gVisor type. On boat, Docker works in every sandbox.
What happens when a sandbox goes idle?
Railway destroys it after the idle timeout, 30 minutes by default, and only your checkpoints survive. Agent 37 can sleep it after a quiet period, keep its memory and wake it on the next request. boat has no idle timer; a stopped sandbox keeps its disk, costs nothing, and reboots on resume.
Are they VMs or containers?
Railway sandboxes are full VMs, while its app services are containers. Agent 37 instances are gVisor containers by default, with a full VM type you can ask for. Every boat sandbox is a full VM.
Where do Railway and Agent 37 run?
Railway has regions in California, Virginia, Amsterdam and Singapore. Agent 37 runs on dedicated servers in the United States. boat runs only in the EU, in Germany, Finland and France, with EU data residency.
Try boat
Install the CLI, then run boat new.
7-day free trial