Runloop vs Ona
Runloop is a sandbox platform you drive from code, with devboxes for building, running and testing AI coding agents. Ona, formerly Gitpod and now part of OpenAI, is a cloud dev environment for engineers and its Codex agent. Since Ona Cloud shut down on October 31, 2026, Ona sells only Enterprise, through sales, on runners in your own AWS or GCP account.
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, browser and computer use, 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 that ship coding agents, plus evaluation and RL fine-tuning work on the Enterprise plan.
- 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.
Ona
Ona, formerly Gitpod, is a platform for cloud dev environments and background coding agents, and is now part of OpenAI.
Ona is a different kind of product from boat: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config. People open it in a browser IDE, VS Code or JetBrains, and Ona's Codex Agent can plan, code, test and open pull requests in it. Ona has a built-in web browser that its AI can drive, prebuilds and Enterprise warm pools. It is built for engineering teams who want the same governed environment for every developer and agent. Since Ona Cloud shut down on October 31, 2026, every customer runs it in their own AWS or GCP account on an Enterprise contract.
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. “24th cheapest of 365” means 23 of the other 364 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 | Ona: price rank | boat: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Runloop fits and is self-serve. Ona can run this on Enterprise, its only plan, with an SDK to start environments from code; it does not document nested virtualization. boat has /dev/kvm on every sandbox. | 24th cheapest of 365 $8,152 a month | 334th of 365, with limits $7,315 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Runloop can suspend an idle devbox and wake it on an HTTP request (Pro). An always-on agent on Ona needs auto-stop set to Never, because background work does not count as activity. On boat, turn auto-stop off (default 1 hour) on a paid plan. | 38th cheapest of 361 $10,194 a month | 147th of 361, with limits $8,504 a month | 6th cheapest of 361 $657 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month Runloop ranks well above boat and Ona for short code runs: it publishes no start-rate limit for paid plans. boat includes 12 / 60 / 200 starts per minute / hour / day on $20, and extra starts cost $0.03 to $0.07. | 52nd cheapest of 336 $525 a month | 326th of 336, with limits $5,320 a month | 189th of 336, 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 Runloop fits. Ona is built for your own engineers, and its per-user policy defaults to 10 running environments (admins can set 1 to 100). | 37th cheapest of 349 $3,301 a month | 325th of 349, with limits $5,988 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month Runloop ranks far higher for RL rollouts: it publishes no start-rate limit for paid plans and sells RL fine-tuning on Enterprise. | 8th cheapest of 349 $15,922 a month | 277th of 349, with limits $9,773 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 91st cheapest of 359 $2,562 a month | 332nd of 359, with limits $5,768 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Ona has no fork, so each CI run starts from a prebuild; Enterprise warm pools hand out a pre-initialized environment in about 10 seconds. In StarSling's run of 3 October 2026, boat did 28.06 runs a second and Runloop 8.93; Ona was not measured. | 125th cheapest of 374 $1,554 a month | 366th of 374, with limits $5,461 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is a full cloud IDE with Dev Containers and prebuilds for people. Runloop reaches devboxes through HTTPS tunnels and SSH. boat is a full VM you reach over SSH, HTTPS or a desktop. | 118th cheapest of 371 $410 a month | 371st of 371, with limits $5,140 a month | 19th cheapest of 371 $26 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month Runloop and boat both ship a desktop and a browser that an agent can control, and boat streams it at 60 fps. Ona's AI can drive a built-in web browser in the environment, but there is no full desktop for other apps. | 41st cheapest of 367 $2,306 a month | 355th of 367, with limits $5,691 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month | 38th cheapest of 356 $1,153 a month | 219th of 356, with limits $5,346 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 73rd cheapest of 343 $781 a month | 220th of 343, with limits $5,468 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 267th of 327, with limits $15,611 a month | 261st of 327, with limits $14,360 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 16th cheapest of 351 $770 a month | 150th of 351, with limits $5,228 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | Runloop | Ona | boat |
|---|---|---|---|
| Kind of product | Sandbox platform of devboxes for building, running and testing AI coding agents | Cloud dev environment platform for engineers and its Codex agent | Sandbox API: full VMs for agents, driven from code |
| Isolation | Micro-VM on a custom bare-metal hypervisor, plus a container layer | Isolated VM per environment with dedicated compute, built from a Dev Container config | Full VM with its own kernel, on physical hosts dedicated to boat (AMD Ryzen 7 9700X and Ryzen 9 9950X); vCPUs are shared |
| Docker and nested virtualization | Docker on the Docker-in-Docker blueprints, as root; nested virtualization not documented | Docker and root inside the Dev Container; nested virtualization not documented on its VM classes | Docker, root, real systemd and /dev/kvm on every sandbox, so Android emulators and VMs run inside |
| Driving it from code | API and SDKs, from the usage-only Basic plan with no sales call | Python, TypeScript and Go SDK and a CLI on Enterprise, Ona's only plan, sold through sales | API, SDK and CLI on every plan, self-serve from $20 a month, including the trial |
| Keeping files | Disk snapshots on every plan; idle suspend keeps the disk (Pro); shutdown deletes the disk | Disk persists across stops, on your cloud bill; a stopped environment is archived after 3 days by default (1 to 30 days) | Disk saved every minute and at each stop, kept at least 14 days; memory and running programs are not saved |
| Copies of a machine | New devboxes from disk snapshots, files only | No environment copy; you can create a project from an environment's config, and Enterprise warm pools start a new environment in about 10 seconds | Fork a running sandbox into copies from its last 1-minute snapshot |
| Long runs and idle stop | Keep-alive timer 1 hour by default, 48 hours max; an idle policy replaces it, with suspend and wake on HTTP on Pro | Stops after 30 minutes without SSH, IDE or agent activity by default; background processes do not count; can be set to Never | Auto-stop 1 hour by default, up to 30 days, or off on a paid plan (then no session cap); the timer does not watch for idle |
| Desktop and computer use | Desktop and browser that an agent can control | Browser IDE, VS Code and JetBrains; a built-in web browser that Ona's AI can drive; no full graphical desktop for other apps | Desktop and Chrome streamed at 1920x1080, 60 fps, with computer tools; embeddable |
| Reaching the sandbox | One HTTPS tunnel per devbox, open or bearer token; SSH through a TLS proxy; no public IP documented | HTTPS URL per port for you, your organization or everyone; SSH; no raw TCP or public IP documented | Up to 50 HTTPS URLs, token-gated by default; SSH; public IPv6 address with raw ports (some sandboxes have no IPv4 of their own) |
| Egress rules | Hostname allowlist with wildcards, or block all | No egress allowlist documented | Open internet; no provider-side allowlist. You set it up: firewall rules inside the VM, as root |
| Keeping keys out of the sandbox | Agent gateways for any API endpoint with bearer, header or basic auth | Secrets injected as environment variables or files; OIDC can swap them for short-lived cloud credentials | Optional AI credentials proxy, off by default, $1 a day plus $1 per 1,000 requests; keys of supported model providers stay outside; other secrets still enter the sandbox |
| Coding agents | Claude Code, Codex, OpenCode, Gemini CLI and DeepAgents through public agent wrappers | Managed Codex Agent from chat, Slack, a pull request comment, a Linear issue or an automation; Claude Code you install yourself | Seven agents preinstalled, with a prompt, steer and events API |
| Where it runs | Regions not documented; Deploy to VPC on AWS, GCP or Azure (Enterprise) | Enterprise runners in your own AWS or GCP account, in many regions; Ona Cloud shut down on October 31, 2026 | Germany, Finland and France; you cannot pick a region; no US or Asia region |
| GPUs | No GPU | GPU instance types on Enterprise runners, such as one NVIDIA A10G with 16 vCPU and 64 GB | No GPU on any size |
Every feature Battleships tracks (43)
| Feature | Runloop | Ona | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Yes | Yes |
| Nested virtualization | No documented way | No documented way | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | Yes | No documented way | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | No documented way | Yes |
| SSH | Yes | Yes | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | Yes | No documented way | Yes |
| Fork/clone | Yes | No documented way | Yes |
| Live fork (no pause) | Yes | No documented way | Yes |
| Memory fork | No documented way | No documented way | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | No documented way | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | No documented way | No documented way |
| Secret proxy | Yes | No documented way | Yes |
| Secret proxy for any API | Yes | No documented way | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | Yes | No documented way | No documented way |
| GPU | No documented way | Yes | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | Yes | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | Yes | Yes | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Yes | No documented way | Yes |
| Audit logs | Not published | No documented way | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Not published | No documented way | No documented way |
| EU data residency | No documented way | Yes | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
In StarSling's run of 3 October 2026 (run 37073680030), on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, boat did 28.06 runs a second (2nd of 15) and Runloop 8.93 (15th of 15), about 3.1 times apart. Ona is not in the public benchmarks we use, so we cannot say how it compares. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host; boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Providers ran on different hardware in different regions. The test measures CPU work only.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. Ona is not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | Runloop, a month | Ona, 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 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $429 · Basic | $5,140 · Enterprise (AWS Marketplace 12-month contract) · with limits | $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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · with limits | $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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | $8,800 · $2000/mo · with limits |
Runloop: Runloop bills per second for allocated CPU ($0.108 per vCPU-hour) and memory ($0.0252 per GB-hour) while a devbox is initializing, running, suspending or resuming: $0.63 an hour at 4 vCPU / 8 GB. Its disk bills 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. New accounts get $50 of credit with no card.
Ona: Ona Cloud and Core shut down on October 31, 2026, so the Ona prices here use its Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract (about $5,000 a month), plus compute on your own AWS bill. Real Enterprise prices are negotiated with sales.
Limits in those scenarios
No Ona scenario fits as published, because Ona sells only Enterprise, through sales. Ona publishes no Enterprise concurrency limit, so the table assumes 3 environments at once, as on its former free plan. Runloop fits every scenario on Basic, but publishes no egress price, tops out disk at 64 GiB, and its keep-alive timer ends at 48 hours unless an idle policy replaces it. boat fits all but 1,000 short jobs at once: even the $2,000 plan charges $0.03 to $0.07 for starts above 90 a minute and refuses them above 270. A stopped boat sandbox has no compute charge, but saved snapshots above the included count and the AI credentials proxy still charge.
| Scenario | Runloop | Ona | boat |
|---|---|---|---|
| One coding agent, workdays |
|
| None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel |
|
| None for this scenario |
| Sandboxes for your users |
|
| None for this scenario |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Runloop when
you want a self-serve sandbox API for coding agents today, with hostname allowlists, arm64, or very large bursts of short jobs.
- Self-serve sandbox API. For teams that want to start building today: Runloop's Basic plan is usage only, with an API and no sales call.
- Lock down the network. For a sandbox that must reach only a fixed list of hosts: Runloop allows listed hostnames, with wildcards, or blocks everything.
- Big bursts and arm64. For waves of short jobs or RL rollouts: Runloop publishes no start-rate limit for paid plans, and it offers arm64 devboxes too.
Use Ona when
your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account or with a GPU.
- A full cloud IDE for your team. For engineers who work in the same environments as their agents: Ona has browser, VS Code and JetBrains IDEs with prebuilds and warm pools.
- Runs in your own cloud. For environments that must run inside your own AWS or GCP account, in many regions: Ona's Enterprise runners do that.
- GPU environments. For agents that need a GPU: Ona's Enterprise runners can use GPU instance types, such as an A10G VM.
Where boat fits
Look at boat if your agents install, build, test and serve things for hours. Each sandbox is a full VM with /dev/kvm, a desktop and open ports, and boat saves its disk every minute and at each stop. You drive it from code on every plan, self-serve from $20 a month.
A full Linux machine
Neither Runloop nor Ona documents /dev/kvm, so Android emulators and nested VMs are not a documented path. Both reach sandboxes over HTTPS and SSH, with no raw TCP documented. boat has /dev/kvm on every sandbox and raw ports over IPv6.
Work kept, forks while running
Runloop deletes the disk at shutdown unless you use $250-a-month Pro suspend or snapshot calls. On Ona a stopped disk stays on your cloud bill, and no API copies a warm environment. boat saves the disk every minute and forks a running sandbox. A boat resume is like a reboot: memory is not kept.
More CPU work than Runloop in one run
In StarSling's run of 3 October 2026, boat did 28.06 runs a second and Runloop 8.93 on the V8 Web Tooling Benchmark. Ona was not measured. Every boat sandbox in that run ran on an AMD Ryzen 9 9950X host; boat also uses other hosts.
Use boat when your code starts and drives agents that do real work for hours: full VMs with /dev/kvm, a desktop and open ports, and a disk saved every minute that forks while running. boat runs only in Germany, Finland and France and has no GPU. Compare it one to one: boat vs Runloop and boat vs Ona.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is Runloop cheaper than Ona?
In every scenario we priced, yes. One coding agent on workdays is $113 a month on Runloop and $5,030 on Ona, using Ona's Enterprise listing on AWS Marketplace. One agent running all month is $429 and $5,140. On boat those are $20 and $26 a month. Ona's real Enterprise price is a sales quote, so yours may differ.
Which is faster, Runloop or Ona?
We cannot say: Ona is not in the public benchmarks we use. In StarSling's run of 3 October 2026, Runloop did 8.93 runs a second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, and boat 28.06.
Can Runloop and Ona run Docker?
Yes. Runloop runs Docker on its Docker-in-Docker blueprints as root, and Ona runs Docker with root inside the Dev Container. Neither documents nested virtualization. boat exposes /dev/kvm on every sandbox, so Android emulators and VMs run inside.
Can I sign up for Ona like I can for Runloop?
No. Ona Cloud and its Core plan shut down on October 31, 2026, and Ona's pricing page is a sales form for Enterprise. Runloop's Basic plan is usage only with no plan fee. boat's plans are self-serve, from a 7-day trial (card required) up.
Can I run Claude Code on Runloop or Ona?
Runloop runs Claude Code, Codex, OpenCode and others through its agent wrappers. Ona's managed agent is Codex; you install and run Claude Code yourself, or drive Ona through its CLI. boat ships seven agents preinstalled, with one API to prompt, steer and watch them.
Can I run Runloop or Ona in my own cloud?
Yes, on Enterprise for both: Runloop deploys into your AWS, GCP or Azure account, and Ona's runners provision environments in your AWS or GCP account. boat runs only on its own machines in Germany, Finland and France.
Try boat
Install the CLI, then run boat new.
7-day free trial