Agent 37 vs Unikraft Cloud
Agent 37 gives each of your users an agent on its own gVisor sandbox, metered per minute from a prepaid wallet. Unikraft Cloud turns a Dockerfile into a tiny Firecracker microVM that wakes in milliseconds, sold as flat pools of running capacity.
The companies and products
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
Unikraft Cloud
Unikraft Cloud is a microVM cloud from Unikraft Inc. that runs any Dockerfile-based workload as a minimal Linux microVM with millisecond cold starts and scale-to-zero.
Your Dockerfile becomes the VM image at build time, and each instance runs on a heavily customized Firecracker VMM, so it boots in milliseconds and can go into standby when no traffic arrives. It is a general compute platform built for dense, bursty work such as HTTP services, headless browsers and agent fleets, sold as flat self-serve plans plus Enterprise dedicated hosts, on-prem and bring your own cloud. It is not a dev machine you log into: instances are reached through services, the CLI and a sandbox plugin for commands and files.
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. “2nd cheapest of 367” means 1 of the other 366 providers runs 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 | Agent 37: price rank | Unikraft Cloud: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory needs Docker inside: Agent 37 has it on its VM type at 2.5x the compute rate, Unikraft documents no container runtime inside, and boat has Docker in every sandbox. | 2nd cheapest of 367 $551 a month | Can't run it | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Agent 37 is built for one always-on assistant per user that sleeps and keeps its memory; Unikraft's self-serve pools cap you at 24 running instances, so it has no self-serve fit here. | Cheapest of 366 $279 a month | Can't run it | 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 sleep between calls, but Unikraft's self-serve plans stop at 24 running instances, while Agent 37's small default sandboxes cover the whole scenario. | Cheapest of 345 $22 a month | Can't run it | 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 Agent 37 holds up to 200 instances on its top self-serve tier, counting sleeping ones; Unikraft Pro runs only 24 at once; boat plans go up to 2,000 at once. | 30th of 361, with limits $79 a month | Can't run it | 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 | 6th of 360, with limits $363 a month | Can't run it | 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 | 90th of 364, with limits $58 a month | Can't run it | 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 images or run emulators need Docker and /dev/kvm: Agent 37 has both on its VM type, Unikraft keeps nested virtualization for Enterprise. | 2nd cheapest of 377 $84 a month | Can't run it | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Both can keep a box all month: Agent 37 gives you SSH and costs less to keep, Unikraft has no SSH yet and needs its Team pool for a 4 vCPU / 8 GB box. | 3rd cheapest of 368 $12 a month | 219th of 368, with limits $39 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, Unikraft has no desktop built in, and boat streams a 60fps desktop in every sandbox. | Cheapest of 369 $53 a month | Can't run it | 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 | 48th of 367, with limits $29 a month | Can't run it | 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 | Cheapest of 346 $32 a month | Can't run it | 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 | 36th of 338, with limits $648 a month | Can't run it | 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 boat can fork a running sandbox to try many paths at once; Agent 37 has no fork, and Unikraft's checkpoints start new instances from a running one. | Cheapest of 360 $43 a month | Can't run it | 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 | Agent 37 | Unikraft Cloud | boat |
|---|---|---|---|
| Isolation | gVisor by default; full VM with its own kernel as an opt-in type | Minimal Linux microVM on a customized Firecracker VMM | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Docker inside | Only on the VM type, at 2.5x the default compute rate | The Dockerfile becomes the VM image; no container runtime inside documented | Yes, in every sandbox |
| systemd | Your entrypoint is PID 1 with no init system, even on the VM type | Not documented; instances run as root | systemd runs as in any Linux server |
| Nested virtualization | /dev/kvm on the VM type, with a ready Android template | Per-instance flag, Enterprise only | /dev/kvm in every sandbox on every plan |
| Idle and wake | Opt-in auto-sleep after a quiet period, memory checkpointed, wakes on the next request | Standby after a 1 second idle cooldown, wakes on traffic in milliseconds | No idle timer; disk saved every minute, a stopped sandbox costs nothing and boots again on start |
| Fork and checkpoints | No fork; daily backups plus one on-demand backup, restored in place only | Checkpoint memory and volumes of a running microVM, then start new instances from it | Fork a running sandbox with its disk; snapshots every minute; named snapshots as templates |
| SSH | Yes, through a WebSocket tunnel | Not yet; commands and files go through the sandbox plugin and CLI | Yes, into every sandbox |
| Desktop and browser | noVNC desktop through a template build or the Ubuntu VM template | None built in; run your own headless browser from a Dockerfile | 60fps desktop, Chromium and a computer-use agent in every sandbox |
| Built-in agents | Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API | None preinstalled; you bring the agent in your own image | Claude Code, Codex and five more, with a prompt, steer and events API |
| Keys kept out of the sandbox | Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars | Network shield can inject secrets into traffic, Enterprise only, limited access | Credentials proxy for model providers and any HTTPS API, on every plan |
| Inbound access | HTTPS URL per port, signed URLs, custom domains; no public IP | HTTP, HTTPS and TLS-wrapped TCP through its load balancer; no public IP per instance | HTTPS URLs for up to 50 ports, raw TCP, dedicated IPv4 or IPv6 |
| How big it goes self-serve | Up to 200 instances at $250 of lifetime top-ups, sleeping and stopped ones counted | Pro pool: 24 running instances sharing 24 vCPU / 32 GiB | 100 to 2,000 sandboxes at once, up to 16 vCPU / 32 GB each |
| Regions | United States | Dallas, Frankfurt, San Francisco, Singapore, Washington DC, more on request | EU only (Germany, Finland, France), EU data residency |
| GPUs and self-hosting | No | GPUs, arm64, dedicated hosts, on-prem and your own cloud on Enterprise | No |
Every feature Battleships tracks (43)
| Feature | Agent 37 | Unikraft Cloud | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | No | No | Yes |
| Nested virtualization | No | Yes | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | Yes | No | 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 | Yes | 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 | Not published | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | Yes | No | Yes |
| MCP server | No | No | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | Yes | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Not published | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Not published | Yes | No |
| SSO | No | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
Neither Agent 37 nor Unikraft Cloud has a result on the hpc-sandbox-benchmarks Node.js build-and-test loop, so there is no comparable CPU measurement between them. boat scored 26.69 runs per second there at 4 vCPU / 8 GB. Unikraft states cold starts under 10 ms, which measures start time, not CPU speed, and Agent 37 sells a Performance type on dedicated cores for steady speed.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Agent 37 and Unikraft Cloud 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 | Agent 37, a month | Unikraft Cloud, 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 | $6 · Wallet (any top-up) | $39 · Hobby | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $12 · Wallet (any top-up) | $39 · Hobby | $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 | $329 · Wallet ($100 lifetime top-ups) | Can't run it | $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 | $33 · Wallet ($250 lifetime top-ups) · with limits | Can't run it | $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 | $73 · Wallet ($250 lifetime top-ups) · with limits | Can't run it | $2,000 · $2000/mo · with limits |
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 asleep. VM compute costs 2.5x and Performance 4x the default rate.
Unikraft Cloud: A flat monthly fee for a pool of running capacity: free for 2 vCPU / 4 GiB, $39 for 8 vCPU / 8 GiB, $199 for 24 vCPU / 32 GiB, with sleeping instances not counted. There is no per-hour rate, so anything bigger is an Enterprise quote.
Unikraft Cloud: 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
Unikraft's limits are pools every running instance shares: one 4 vCPU / 8 GB agent fills the Team pool, so the 50-agent, user-sandbox and burst scenarios need Enterprise. Agent 37 fits 50 agents in parallel on its VM type, but caps out at 200 instances, counting sleeping and stopped ones, so 300 user sandboxes or 1,000 jobs at once do not fit. boat runs 100 sandboxes at once from its first paid plan, but its start limits queue the 1,000-at-once burst.
| Scenario | Agent 37 | Unikraft Cloud | 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 Agent 37 when
you host one mostly idle assistant per customer in the US that should sleep with its memory kept, and you want to pay per minute with no plan fee.
- One sleeping agent per user. For assistants idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
- Pay per minute, no plan fee. A prepaid wallet billed per minute, so one small agent costs a few dollars a month instead of a flat pool fee.
- Agents and SSH ready. Hermes, OpenClaw, Claude Code and others come as templates with a chat API, and you can SSH into each instance.
Use Unikraft Cloud when
you run many small services or headless browsers that must wake in milliseconds, need regions in the US or Asia, or want GPUs or on-prem under an Enterprise contract.
- Millisecond starts. For many small services that sleep most of the time and must answer the next request in milliseconds.
- Regions in the US, EU and Asia. Unikraft runs in Dallas, Frankfurt, San Francisco, Singapore and Washington DC, with more metros on request.
- GPUs and your own hardware. On Enterprise you can get NVIDIA GPUs, arm64 hosts, egress filtering, dedicated hosts, on-prem or your own cloud.
Where boat fits
Both Agent 37 and Unikraft Cloud are built around agents or services that sleep most of the time. If your agents do real work for hours, with installs, builds, Docker and emulators, boat gives each one a full VM with all of that on every plan. It also forks running machines and keeps your keys outside.
A whole machine by default
Agents start databases with Docker and run emulators. Agent 37's default type cannot run Docker, and its VM type costs 2.5x with no systemd. Unikraft documents no container runtime inside and keeps /dev/kvm for Enterprise.
Keys stay outside, for any API
On Agent 37 your own API keys sit as env vars inside a machine the agent controls. Unikraft's secret injection is Enterprise only. boat's proxy covers model providers and any HTTPS API on every plan.
Fleets without a sales call
Fifty 4 vCPU / 8 GB agents need 200 vCPU running at once, above every Unikraft self-serve pool. Agent 37 caps at 200 instances, sleeping ones included. boat plans run up to 2,000 at once.
Use boat when your agents need a real machine for hours: Docker, systemd, emulators, a desktop, forks of running machines, keys kept outside for any API, and fleets without a sales call. Compare it one to one: boat vs Agent 37 and boat vs Unikraft Cloud.
Questions people ask
Is Agent 37 cheaper than Unikraft Cloud?
For one agent, yes. One coding agent on workdays costs about $6 a month on Agent 37 and $39 on Unikraft's Team pool, and one that never stops about $12 against $39. For 50 agents or more, no self-serve Unikraft plan is big enough, so it becomes an Enterprise quote.
Which is faster?
Unikraft starts faster: its microVMs cold boot in milliseconds and wake on traffic, while Agent 37 wakes from a checkpoint in a few seconds. Neither has a published CPU benchmark result, so their compute speed is not compared.
Can Agent 37 or Unikraft Cloud run Docker?
Agent 37 runs Docker and Compose on its VM type, at 2.5x the default compute rate; its default gVisor type cannot. Unikraft builds your Dockerfile into the VM image and documents no container runtime inside an instance. Every boat sandbox runs Docker.
Can I SSH into them?
Agent 37 supports SSH through a WebSocket tunnel. Unikraft has announced SSH as coming soon, and today you use its sandbox plugin and CLI. Every boat sandbox has SSH.
Where do they run?
Agent 37 runs on dedicated servers in the United States. Unikraft runs in Dallas, Frankfurt, San Francisco, Singapore and Washington DC. boat runs only in the EU, in Germany, Finland and France.
Is Unikraft Cloud the same as Unikraft?
No. Unikraft Cloud is the commercial platform from Unikraft Inc. that runs Linux-based microVMs, while the Unikraft unikernel project at unikraft.org is a separate open-source project.
Try boat
Install the CLI, then run boat new.
7-day free trial