Runloop vs Unikraft Cloud
Runloop is built for coding agents: devboxes with Docker, SSH, agent gateways and built-in agents, billed per second. Unikraft Cloud turns a Dockerfile into a tiny microVM that wakes in milliseconds, sleeps when traffic stops and is sold as a flat monthly pool.
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.
- 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
- Company
- Runloop AI, Inc.
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. “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 | Unikraft Cloud: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Runloop fits a software factory with Docker-in-Docker blueprints, while Unikraft builds your Dockerfile into the VM itself and documents no container runtime inside; boat adds /dev/kvm on every plan. | 20th cheapest of 367 $8,152 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 An assistant that lives on its machine all month needs room for many tools; Runloop sizes each devbox, while Unikraft's Team pool is 8 GiB shared by every running instance. | 32nd cheapest of 366 $10,194 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 Short code runs that sleep between calls suit Unikraft's design, but its self-serve plans cap you at 24 running instances; Runloop fits this fully and ranks above boat here. | 44th cheapest of 345 $525 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 Unikraft Pro holds 5,000 sleeping instances but only 24 running ones, so hundreds of active users need an Enterprise contract; Runloop and boat both fit self-serve. | 26th cheapest of 361 $3,301 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 Runloop is a strong pick for RL rollouts: it starts large waves without published start limits and sells RL fine-tuning on Enterprise. | 4th cheapest of 360 $15,922 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 | 81st cheapest of 364 $2,562 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 that builds Docker images works on Runloop's dnd blueprints but has no documented container runtime on Unikraft; boat's faster CPUs finish builds sooner. | 121st cheapest of 377 $1,554 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 This is the only use case where all three are ranked: Unikraft is a compromise with no SSH today, Runloop fits fully, and boat ranks highest. | 113th cheapest of 368 $410 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 Runloop ships a desktop and a browser an agent can control, Unikraft has none built in, and boat streams its desktop at 60fps. | 39th cheapest of 369 $2,306 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 | 40th cheapest of 367 $1,153 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 | 68th cheapest of 346 $781 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 | 266th of 338, with limits $15,611 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 | 10th cheapest of 360 $770 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 | Runloop | Unikraft Cloud | boat |
|---|---|---|---|
| Isolation | Micro-VM on a custom bare-metal hypervisor, plus a container layer | Minimal Linux microVM on a customized Firecracker VMM; full VMs on Enterprise | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Running at once | No concurrency cap published for paid plans; 3 on the trial | Plan pool shared by all running instances: 2, 8 or 24 instances with 4, 8 or 32 GiB memory in total | 100 to 2,000 sandboxes at once on paid plans; starts above 90 a minute are queued |
| Docker inside | Yes, on the dnd blueprints, as root | Runs as root; the Dockerfile becomes the VM image, with no container runtime inside documented | Yes, with root and systemd, like any Ubuntu machine |
| Nested virtualization | Not documented; Docker-in-Docker blueprints only | Yes, with a per-instance flag and permission, Enterprise only | Yes, /dev/kvm for Android emulators and VMs on every plan |
| SSH | Yes, through a TLS proxy | Not yet; commands and files go through the sandbox plugin and CLI | Yes, into every sandbox |
| Idle sleep and wake | Suspend after idle, wake on an HTTP request to the tunnel (Pro plan) | Standby after a 1 second idle cooldown by default; incoming traffic wakes it in milliseconds | No idle timer; TTL based, and a stopped sandbox is started by API |
| Keeping files | Disk kept through suspend (Pro plan) or manual disk snapshots; shutdown ends the devbox | Stateful standby snapshots memory and resumes with warm caches; volumes available | Disk saved every minute and on stop, on every plan; a stopped sandbox costs nothing |
| Checkpoints and forks | Disk snapshots of a devbox to start new ones from | Checkpoint memory and volumes of a running microVM with a pause of a few milliseconds, then start new instances from it | Fork a running sandbox with its disk; snapshots every minute |
| Inbound access | One HTTPS tunnel per devbox covering its ports, open or bearer token; no public IP | Services on its load balancer: HTTP on 80, HTTPS on 443, TLS-wrapped TCP on other ports; no public IP per instance | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Outbound rules | Hostname allowlist with wildcards, or block all | Network shield filters traffic, Enterprise only, limited access | Open internet, no provider-side allowlist |
| Keeping API keys out of the sandbox | Agent gateways for any API endpoint with bearer, header or basic auth | Network shield can inject secrets into traffic, Enterprise only, limited access | Credentials proxy for model providers and any HTTPS API, on every plan; switch a credential to another account when credits run out |
| Coding agents | Claude Code, Codex, OpenCode, Gemini CLI, DeepAgents, driven through Axons and Broker | None preinstalled; you bring the agent in your own image | Seven agents preinstalled, with a prompt, steer and events API |
| Desktop and browser | A desktop and a browser your agent can control | None built in; you can run your own headless browser from a Dockerfile | Linux desktop streamed at 60fps, Chromium, and a computer-use agent |
| Regions | Not documented or selectable; Deploy to VPC on AWS, GCP or Azure (Enterprise) | Dallas, Frankfurt, San Francisco, Singapore and Washington DC, more metros on request | EU only (Germany, Finland, France), EU data residency |
Every feature Battleships tracks (43)
| Feature | Runloop | Unikraft Cloud | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | 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 | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | Yes | Yes | Yes |
| Secret proxy for any API | Yes | Yes | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | Yes | No | Yes |
| MCP server | Yes | No | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | Yes | Yes | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Not published | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB (run 36498291449, 2026-09-29), boat scored 26.69 runs a second and Runloop 8.29, about 3.2 times apart. Unikraft Cloud is not in that run, so there is no comparable CPU score for it. Unikraft states cold starts under 10 ms, which is its own figure and measures start time, not CPU speed.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Unikraft Cloud 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 | 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 | $113 · Basic | $39 · Hobby | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $429 · Basic | $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 | $5,268 · Basic | 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 | $1,441 · Basic | 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 | $3,184 · Basic | Can't run it | $2,000 · $2000/mo · with limits |
Runloop: Runloop bills per second for the CPU and memory you allocate, and bills 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.
Unikraft Cloud: Unikraft charges 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. It publishes 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, billed per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Unikraft's limits are pools that every running instance shares: Team has 8 vCPU and 8 GiB in total, so one 4 vCPU / 8 GB agent fills it, and 50 agents, sandboxes for your users or 1,000 short jobs fit no self-serve plan. Runloop fits all five scenarios, but its fixed lifetime setting tops out at 48 hours unless an idle policy replaces it, and it publishes no egress price. boat fits every scenario except 1,000 short jobs at once, where even the $2,000 plan queues starts above 90 a minute.
| Scenario | Runloop | 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 Runloop when
you are shipping coding agents and want devboxes with Docker, agent gateways and hostname allowlists, large bursts of short jobs, arm64, or deploys into your own AWS, GCP or Azure account.
- Built for coding agents. Runloop devboxes come with Docker-in-Docker, SSH, agent gateways and agents such as Claude Code and Codex driven through Axons.
- Big fleets without a sales call. Runloop bills per second with no published concurrency cap, so 50 agents or 1,000 short jobs fit on the usage-only Basic plan.
- 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.
Use Unikraft Cloud when
you run many small services or headless browsers that sleep most of the time and must wake in milliseconds, or need US or Asia regions on a flat monthly bill.
- Millisecond starts and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
- A flat monthly bill for small setups. Unikraft sells a fixed pool of running capacity, with a free Hobby plan, and sleeping instances do not count against it.
- Regions in the US and Asia. Unikraft runs in Dallas, San Francisco, Washington DC and Singapore as well as Frankfurt, with more metros on request.
Where boat fits
If your agents do real work for hours, installing, building, testing and running Docker or emulators, boat gives each one a whole Linux machine on fast CPUs. It keeps files on every plan and runs fleets of full-size sandboxes without a sales call.
A whole machine with /dev/kvm
Android emulators and VMs need /dev/kvm. Runloop does not document nested virtualization, and Unikraft keeps it for Enterprise and documents no container runtime inside, so the agent cannot start them on either one self-serve.
About three times Runloop's CPU speed
On the same Node.js benchmark boat ran 26.69 loops a second and Runloop 8.29, so every build and test waits about three times longer there. Unikraft has no comparable measurement.
Files kept and real ports, on every plan
On Runloop a devbox's disk is gone at shutdown unless you pay for Pro suspend or write snapshot code. Neither Runloop nor Unikraft gives an instance a public IP or raw TCP, so a database or server that speaks TCP has no way in.
Use boat when your agents need a real machine to work in for hours: Docker, emulators, a desktop and a browser, faster CPUs, files kept on every plan and fleets without a sales call. Compare it one to one: boat vs Runloop and boat vs Unikraft Cloud.
Questions people ask
Is Runloop cheaper than Unikraft Cloud?
For one small setup, no: one coding agent on workdays is $113 a month on Runloop against $39 on Unikraft's pool, and one that never stops is $429 a month against $39. For 50 agents, sandboxes for your users or 1,000 short jobs, Runloop fits and no self-serve Unikraft plan does. On boat those first two cost $20 and $26 a month.
Which is faster, Runloop or Unikraft Cloud?
They have not been measured on the same test. Runloop scored 8.29 runs a second on the hpc-sandbox-benchmarks Node.js loop, and boat 26.69; Unikraft was not in that run. Unikraft wakes from standby in milliseconds, which measures start time, not CPU speed.
Can Runloop or Unikraft Cloud run Docker?
Runloop runs Docker inside devboxes built from its dnd blueprints. Unikraft uses your Dockerfile to build the VM's filesystem, and its docs do not describe running a container runtime inside an instance. A boat sandbox has Docker, systemd and /dev/kvm ready to use.
Can I SSH into Runloop or Unikraft Cloud?
Runloop offers SSH through a TLS proxy. Unikraft has no SSH yet; you run commands and move files through its sandbox plugin and CLI. You can SSH into every boat sandbox.
Which one sleeps when idle?
Both can. Unikraft goes into standby after a 1 second idle cooldown by default and wakes on the next request in milliseconds. Runloop can suspend an idle devbox and wake it on an HTTP request, but suspend needs the Pro plan.
Can I run them in my own cloud?
Both on Enterprise. Runloop deploys into your own AWS, GCP or Azure account, and Unikraft offers dedicated hosts, on-prem and bring your own cloud. boat runs only in its own EU data centers.
Try boat
Install the CLI, then run boat new.
7-day free trial