Beam vs Agent 37
Beam is a serverless GPU platform whose sandboxes are short-lived gVisor containers you start from code. 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
Beam
Beam is a serverless cloud for GPU inference, sandboxes and background jobs, built on its open-source runtime Beta9.
Beam runs functions, REST endpoints, task queues, pods, sandboxes and VMs on CPUs and GPUs, all from a Python or TypeScript SDK. A sandbox is a container isolated with gVisor that starts in a second or two, lives until you terminate it or its time to live runs out, and can be saved as a filesystem image or a memory snapshot. Beam VMs are a separate CPU product: a microVM with its own kernel, systemd and a root disk that stays when it stops. Much of Beam is a GPU serverless platform for AI teams.
- Bring your own cloud
- Management fee per vCPU and GB of RAM, on top of your own cloud bill
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. “8th cheapest of 345” means 7 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 | Beam: 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 Beam sandboxes run Docker with docker_enabled but have no systemd, and Agent 37 needs its VM type for Docker, which has no init system; bochka gives every sandbox Docker, systemd and /dev/kvm. | 69th of 367, with limits $551 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 is built for this: one always-on assistant per user that sleeps when idle, keeps its memory and wakes on the next message, while a Beam sandbox ends with its time to live. | 115th of 366, with limits $651 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 Both suit short code runs: Beam sandboxes cold-boot in 1 to 3 seconds and bill per second, and Agent 37's small default instances bill per minute. | 8th cheapest of 345 $117 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 Beam's Team plan runs 1,000 CPU containers at once, while Agent 37 stops at 200 instances on its top self-serve tier, counting sleeping and stopped ones; bochka plans go up to 2,000 at once. | 3rd cheapest of 361 $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 | 341st of 360, with limits $939 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 | 13th cheapest of 364 $251 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 Builds that need /dev/kvm, such as Android emulators, work on Agent 37's VM type and in every bochka sandbox; Beam documents no /dev/kvm. | 12th cheapest of 377 $171 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 | 13th cheapest of 368 $21 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 adds a noVNC desktop through a template build, Beam has no desktop or browser product, and bochka streams a 60fps desktop with Chromium in every sandbox. | 111th of 369, with limits $237 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 | 195th of 367, with limits $176 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 | 200th of 346, with limits $131 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 | 42nd of 338, with limits $923 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 | 175th of 360, with limits $155 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 Only Beam fits here, with GPUs from T4 up to H100, H200 and B200; Agent 37 and bochka are CPU only. | Cheapest of 98 $458 a month | 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 | Beam | Agent 37 | bochka |
|---|---|---|---|
| Isolation | gVisor container by default for sandboxes; separate Beam VMs are CPU microVMs with their own kernel | gVisor sandbox by default; full VM with its own kernel 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, in sandboxes with docker_enabled | Only on the VM type, at 2.5x the default compute rate | Yes, in every sandbox |
| systemd | Only in Beam VMs, not in sandboxes | No init system; your entrypoint is PID 1, even on the VM type | systemd and root, like a normal Ubuntu server |
| Nested virtualization | Not documented | /dev/kvm on the VM type, with a ready Android template | /dev/kvm in every sandbox, Android emulators work |
| GPUs | GPU sandboxes and serverless GPUs, from T4 up to H100, H200 and B200 | No GPUs | No, CPU only |
| Lifetime and idle | Default time to live 10 minutes; set -1 to run until you terminate it; no sleep on idle | Runs until you stop it; opt-in auto-sleep after a quiet period, wakes on the next request | No session cap on paid plans; a time limit you set (default 1 hour), or no limit |
| State between runs | Save a filesystem image or memory snapshot, or attach a volume; a Beam VM keeps a 50 GiB root disk while stopped | Memory checkpointed on auto-sleep; disk kept and billed while stopped or asleep | Disk saved every minute and on stop; a stopped sandbox keeps it for free |
| Fork and snapshots | Memory snapshot of a running sandbox with its processes, restored into new sandboxes | No fork; daily backups plus one on-demand backup, restored in place only | Fork a running sandbox with its disk; named snapshots as shareable templates |
| Built-in agents | None preinstalled; you install and run them through process exec | Templates for Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode and Pi, with a chat API per instance | Seven agents preinstalled, including Claude Code and Codex, with a prompt, steer and events API |
| Desktop and browser | No desktop or browser product | noVNC desktop through a template build or the Ubuntu VM template | Linux desktop streamed at 60fps with Chromium and computer use |
| Inbound access | Public HTTPS URL per exposed port with no built-in auth; no raw TCP or dedicated IP | 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 by default; raw TCP; dedicated IPv4 or IPv6 |
| Keeping API keys out of the sandbox | Secrets are exposed as environment variables inside the sandbox | Managed models, 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; switch a credential to another account when credits run out |
| Machines at once | 30 CPU containers on Developer, 1,000 on Team | 1 to 200 instances by lifetime top-ups, counting sleeping and stopped ones; email for more | Set by plan, up to 2,000 at once |
| Regions | United States only | Dedicated servers in the United States | EU only (Germany, Finland, France), EU data residency |
Every feature Battleships tracks (43)
| Feature | Beam | Agent 37 | bochka |
|---|---|---|---|
| Full VM (own kernel) | No | No | Yes |
| Docker inside | Yes | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | No | Yes | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | No | Yes | Yes |
| Automatic snapshots | No | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | Yes | Yes | Yes |
| Memory fork | Yes | 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 | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | No | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | No | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | Yes | No | No |
| BYOC | Yes | No | No |
| Open source | Yes | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Not published | Not published | No |
| SSO | No | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | No | No |
| EU data residency | Not published | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Beam or Agent 37: neither has a result on the StarSling hpc-sandbox-benchmarks CPU test, so we cannot say which is faster at CPU work. bochka did 26.69 runs per second on that test at 4 vCPU / 8 GB. Beam says its sandboxes cold-boot in 1 to 3 seconds, and Agent 37's default instances share host resources, with 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. Beam 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 | Beam, 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 | $5 · Developer | $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 | $22 · Developer | $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 | $410 · Team | $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 | $191 · Team | $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 | $259 · Team | $73 · Wallet ($250 lifetime top-ups) · with limits | $2,000 · $2000/mo · with limits |
Beam: Beam sandboxes bill per second for each CPU core (one core is two vCPU) and each GiB of RAM until you terminate them or their time to live ends, so an idle tail is billed too. Developer has no fee; Team costs $89 a month plus usage, with no usage credit, and egress is free.
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
Agent 37 holds at most 200 instances on its top self-serve tier, counting sleeping and stopped ones, so it cannot fit 300 user sandboxes or 1,000 short jobs at once, while Beam's Team plan fits both. Agent 37's 50-agent scenario needs Docker, so it is priced on the VM type at 2.5x. Beam's Developer plan allows 30 CPU containers, so 50 agents need Team, and Beam publishes no disk price, so no disk cost is counted for it. bochka's start limits queue the 1,000-job burst too.
| Scenario | Beam | Agent 37 | bochka |
|---|---|---|---|
| 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 Beam when
your agents need GPUs, when you run large bursts of short jobs, when sandboxes must be locked to a few networks, or when you want to self-host.
- GPUs in the same platform. For work that needs a GPU, Beam offers GPU sandboxes and serverless GPUs from T4 up to H100, H200 and B200.
- Large bursts and locked-down networks. Beam's Team plan runs 1,000 CPU containers at once, and a sandbox can block outbound traffic or allow only 10 CIDR ranges.
- Open source and your own cloud. Its Beta9 runtime is AGPL-3.0 and free to self-host, and Beam can also run in your own cloud for a fee.
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. For assistants that sit idle most of the day, an instance sleeps, keeps its memory and wakes on the next message.
- One ready agent per customer. Templates for Hermes, OpenClaw, Claude Code and others come with a chat API, so each customer gets an agent quickly.
- Low cost to keep a machine running. Agent 37 meters per minute from a prepaid wallet with no plan fee, and is the cheapest here for one agent that never stops.
Where bochka fits
Beam and Agent 37 both start you in a gVisor container in the US. If your agents do real work for hours, with installs, Docker, services and emulators, bochka gives each one a full VM with a desktop, agents and a credentials proxy built in, hosted in the EU.
A full VM by default
A Beam sandbox has no systemd and documents no /dev/kvm. On Agent 37, Docker needs the VM type at 2.5x the compute rate, and even that has no init system, so services do not start on their own.
A disk that waits for free
A Beam sandbox ends with its time to live, 10 minutes by default, unless you save an image or attach a volume. Agent 37 keeps the disk but bills it while stopped or asleep. bochka saves the disk every minute and a stopped sandbox costs nothing.
Keys stay outside, for any API
On Beam, secrets sit as environment variables inside the sandbox, and on Agent 37 your own keys do too, where one prompt injection can leak them. bochka's proxy keeps real keys outside for model providers and any HTTPS API.
Use bochka when your agents do real work for hours: installs, builds, Docker, emulators and a browser on a full VM whose disk is still there, free, the next time it starts. Compare it one to one: bochka vs Beam and bochka vs Agent 37.
Questions people ask
Is Beam cheaper than Agent 37?
Agent 37's bill is lower in four of the five scenarios, such as $12 against $22 a month for one agent that never stops and $329 against $410 for 50 agents in parallel. But in two of those, 300 user sandboxes and 1,000 short jobs at once, Agent 37's 200-instance cap means it does not fit, while Beam's Team plan does.
Which is faster, Beam or Agent 37?
There is no comparable CPU measurement for either one, so we cannot say. Beam's sandboxes cold-boot in 1 to 3 seconds, and Agent 37 wakes a sleeping instance from its checkpoint in a few seconds. bochka did 26.69 runs per second on the hpc-sandbox-benchmarks CPU test.
Can Beam and Agent 37 run Docker?
Beam runs Docker inside a sandbox with docker_enabled. 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. bochka runs Docker in every sandbox, with systemd and /dev/kvm.
Do Beam or Agent 37 have GPUs?
Beam does, from T4 up to H100, H200 and B200, in sandboxes and serverless endpoints. Agent 37 has no GPUs, and bochka is CPU only too.
What happens when the agent is idle?
Agent 37 can put an instance to sleep after a quiet period, save its memory and wake it on the next request. A Beam sandbox keeps running and billing until you terminate it or its time to live ends. bochka stops a sandbox at the time limit you set and keeps its disk for free.
Where do Beam and Agent 37 run?
Both run in the United States. bochka runs only in the EU, in Germany, Finland and France, with EU data residency.
Try bochka
Install the CLI, then run bochka new.
Product preview