Ona vs Claude Managed Agents
Ona, formerly Gitpod and now part of OpenAI, gives your engineers and its Codex agent isolated cloud dev VMs, sold through sales. Claude Managed Agents is Anthropic's hosted agent: you send a task as events, and Claude works in a small container that Anthropic runs.
The companies and products
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 bochka: a dev-environment platform, not a sandbox API. Each task or developer gets an isolated VM built from a Dev Container config, which people open in a browser IDE, VS Code or JetBrains, and where Ona's Codex Agent can plan, code, test and open pull requests. It is built for engineering teams who want the same governed environment for every developer and agent; new customers run it in their own AWS or GCP account on an Enterprise contract.
Claude Managed Agents
Claude Managed Agents is Anthropic's ready-made agent harness: Claude runs as an autonomous agent in a cloud sandbox that Anthropic manages, and you talk to it through an events API.
This is an agent platform, not a sandbox you rent. You define an agent (model, prompt, tools, MCP servers, skills) and an environment, then start sessions, send messages as events and stream back what Claude does; the harness handles tool calls, prompt caching and compaction. Each session gets its own Ubuntu container, or runs its tools on a worker you host yourself. It is built for teams that want Claude doing long tasks without building their own agent loop or sandbox.
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. “324th cheapest of 367” means 323 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 | Ona: price rank | Claude Managed Agents: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent on Ona gets a whole dev VM but no documented /dev/kvm, and on Managed Agents it gets a container with up to 8 GB of memory and Docker only in limited availability; bochka gives it a full VM with both. | 324th of 367, with limits $7,315 a month | 106th of 367, with limits $964 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Managed Agents sessions sleep for free between messages but lose their sandbox 30 days after it is created, while Ona stops an agent after 30 idle minutes unless auto-stop is set to Never. | 83rd of 366, with limits $8,504 a month | 219th of 366, with limits $2,511 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 Managed Agents bills runtime only while the agent is working, which suits short bursts of code with long gaps; Ona is built for longer dev sessions, not quick runs. | 335th of 345, with limits $5,320 a month | 163rd of 345, with limits $756 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 Neither is built to hand machines to your users: Ona is made for your own engineers, and a Managed Agents sandbox has no inbound ports for a user to open; bochka gives each sandbox HTTPS URLs on up to 50 ports. | 330th of 361, with limits $5,988 a month | 231st of 361, with limits $823 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 | 283rd of 360, with limits $9,773 a month | 252nd of 360, with limits $3,978 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 | 334th of 364, with limits $5,768 a month | 244th of 364, with limits $320 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 | 365th of 377, with limits $5,461 a month | 227th of 377, with limits $96 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Ona is a real dev box with browser, VS Code and JetBrains IDEs, while Managed Agents has no SSH; bochka is a full VM you reach over SSH, HTTPS or a desktop. | 368th of 368, with limits $5,140 a month | 224th of 368, with limits $48 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 Neither has a graphical desktop: Ona offers IDEs and Managed Agents ships headless Chromium, while bochka streams a 60fps Linux desktop for computer use. | 353rd of 369, with limits $5,691 a month | 127th of 369, with limits $288 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 | 150th of 367, with limits $5,346 a month | 126th of 367, with limits $288 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 | 146th of 346, with limits $5,468 a month | 127th of 346, with limits $390 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 | 261st of 338, with limits $14,360 a month | 155th of 338, with limits $4,798 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 Neither Ona nor Managed Agents can copy a prepared machine, so each attempt starts fresh; bochka can fork one running sandbox into many. | 93rd of 360, with limits $5,228 a month | 179th of 360, with limits $160 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 | Ona | Claude Managed Agents | bochka |
|---|---|---|---|
| Isolation | Isolated VM per environment with dedicated compute, storage and networking, built from a Dev Container config | Isolated Linux container per session on Anthropic-managed infrastructure | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | Classes such as 4 vCPU / 16 GB; Core goes up to 32 vCPU / 128 GB | Up to 8 GB memory and 10 GB disk; vCPU count not published; not configurable | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Docker, systemd and /dev/kvm | Docker and root inside the Dev Container; nested virtualization not documented | Docker listed as limited availability; root, systemd and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm on every machine |
| Files after a stop | Disk persists across stops; in your own cloud it is billed while stopped, and Core archives a stopped environment after 3 days | Sandbox is checkpointed when a session goes idle; state is kept only 30 days after the sandbox is created | Disk saved every minute and on stop; a stopped sandbox keeps its disk and costs nothing |
| Fork | No environment copy; you can create a project from an environment's config | No fork or clone of a session or sandbox | Fork a running sandbox into copies with its files |
| Idle behavior | Stops after 30 minutes without SSH, IDE or agent activity by default; background work does not count; can be set to Never | An idle session is not billed and resumes from its checkpoint on the next message | Runs until you stop it; no session cap on paid plans; started again by API |
| Driving it from code | Python, TypeScript and Go SDK on the Enterprise plan only | Sessions and events API, enabled by default on Claude API accounts (beta) | API and SDK on every plan, including the trial |
| Agents | Codex Agent started from chat, a Linear issue or an automation; Claude Code you install yourself | Anthropic's harness with Claude models only, with steering, memory stores, multiagent threads and webhooks | Claude Code, Codex, OpenCode and more preinstalled, driven from outside with a prompt, steer and events API |
| Desktop and browser | Browser IDE plus VS Code and JetBrains; no graphical desktop | Headless Chromium with Playwright; no desktop or computer-use tool | 60fps Linux desktop with Chromium, computer use and browser control |
| Reaching the machine | HTTPS URL per port for you, your organization or everyone; SSH; no raw TCP or public IP documented | No inbound ports or SSH; reached only through the sessions and events API | HTTPS URLs for up to 50 ports, token-protected; raw TCP; SSH |
| Keeping keys out of the sandbox | Secrets are injected as environment variables or files | Vault secrets sit in the sandbox as placeholders and are swapped in at egress, per host | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| Your own infrastructure | Enterprise runners create environments in your own AWS or GCP account | Self-hosted sandboxes run tool calls on your own workers while Anthropic keeps the orchestration | No; runs only on bochka's own hosts |
| GPUs | GPU instance types on Enterprise runners, such as one NVIDIA A10G with 16 vCPU and 64 GB | None | None |
| Where it runs | Your own AWS or GCP account in many regions; Ona Cloud in Frankfurt and North Virginia for existing Core subscribers | US workspace geo only; not eligible for Zero Data Retention | EU only (Germany, Finland, France), with a zero data retention option |
Every feature Battleships tracks (43)
| Feature | Ona | Claude Managed Agents | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | Not published | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | No | No | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | Yes | Yes |
| Automatic snapshots | No | Yes | Yes |
| Fork/clone | No | No | Yes |
| Live fork (no pause) | No | No | 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 | No | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | No | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | No | Yes | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | No | No | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | Yes | 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 | No | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | No | Yes |
Performance
There is no comparable measurement for either one: Ona and Claude Managed Agents were not in the public benchmark runs we use, and Anthropic does not publish how many vCPUs a sandbox gets. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run of 2026-09-29, on dedicated AMD Ryzen 9 9950X hosts.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Ona and Claude Managed Agents 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 | Ona, a month | Claude Managed Agents, 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 | $5,030 · Enterprise (AWS Marketplace 12-month contract) · with limits | $13 · Claude API (pay-as-you-go, usage tiers) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $5,140 · Enterprise (AWS Marketplace 12-month contract) · with limits | $53 · Claude API (pay-as-you-go, usage tiers) · 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 | $6,521 · Enterprise (AWS Marketplace 12-month contract) · with limits | $634 · Claude API (pay-as-you-go, usage tiers) · 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 | $5,432 · Enterprise (AWS Marketplace 12-month contract) · with limits | $360 · Claude API (pay-as-you-go, usage tiers) · 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 | $5,955 · Enterprise (AWS Marketplace 12-month contract) · with limits | $796 · Claude API (pay-as-you-go, usage tiers) · with limits | $2,000 · $2000/mo · with limits |
Ona: New Core subscriptions are closed, so the prices here use Ona's Enterprise listing on AWS Marketplace: a 12-month, $60,000 contract, plus compute that runs on your own AWS bill. Real Enterprise prices are negotiated with sales.
Claude Managed Agents: Managed Agents bills model tokens at API rates plus a session runtime fee that accrues only while a session is running, including time waiting on the model. The table shows runtime only; tokens come on top and usually cost more.
Claude Managed Agents: Plans start at $20 a month, and the whole fee is usage credit spent per second while a sandbox runs. A stopped sandbox costs nothing and keeps its disk; model tokens are paid to your model provider.
Limits in those scenarios
No scenario fits Ona as published, because new customers can only buy Enterprise through sales, and with no published concurrency limit the table assumes 3 environments at once. Ona's per-user policy also defaults to 10 running environments, and an agent stops after 30 idle minutes unless auto-stop is set to Never. Managed Agents sandboxes have up to 8 GB of memory and 10 GB of disk with an unpublished vCPU count, and Anthropic publishes no concurrent-session cap, only 300 creates per minute and usage-tier spend limits. On bochka, the 1,000-job burst is queued above 90 starts per minute and needs more starts a day than the $2,000 plan allows.
| Scenario | Ona | Claude Managed Agents | 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 Ona when
your engineers want a governed cloud IDE shared with a Codex agent, inside your own AWS or GCP account, on big machines or with a GPU.
- A full cloud IDE for your team. Useful if engineers and agents share environments: Ona has browser, VS Code and JetBrains IDEs, Dev Containers and prebuilds.
- Runs in your own cloud. Useful if environments must live in your own AWS or GCP account, in a region you choose.
- Big machines and GPUs. Useful if agents need more than 8 GB or a GPU: Ona's classes reach 32 vCPU / 128 GB, and Enterprise runners offer an A10G.
Use Claude Managed Agents when
you want Claude itself doing long text and code tasks with no harness to build, idle time that costs nothing, and no sales call.
- No agent loop to build. Teams that want Claude doing long tasks get the harness, caching, compaction, memory and webhooks ready to use.
- Idle sessions sleep for free. Agents that wait long between messages pay runtime only while working, and resume on the next message.
- Start today, no contract. Any Claude API account can use it in beta with no plan fee, while new Ona customers must go through sales.
Where bochka fits
Ona is a dev platform for your engineers and its Codex agent, and Claude Managed Agents is Anthropic's hosted Claude in a small container. If what you are really doing is starting and driving agents from your own code, bochka gives each one a full VM with an API on every plan, a disk that lasts, and the agent of your choice.
A whole machine with a screen and open ports
Ona documents no /dev/kvm, desktop or raw TCP, and a Managed Agents container has up to 8 GB, Docker in limited availability and no inbound ports. Emulators, computer use and apps your users click on need another machine.
Work that lasts and forks
Core archives a stopped Ona environment after 3 days and Enterprise bills its disk while stopped; Managed Agents drops sandbox state 30 days after creation. Neither can fork, so every parallel attempt rebuilds from scratch.
Any agent, from your code, on any plan
Ona's SDK needs an Enterprise contract and its managed agent is Codex. Managed Agents runs only Claude in Anthropic's harness. bochka runs Claude Code, Codex, OpenCode and more, all through one API.
Use bochka when your code starts and drives the agents: full VMs with /dev/kvm, a desktop and open ports, disks that last and fork, and Claude Code, Codex or other agents through one API. Compare it one to one: bochka vs Ona and bochka vs Claude Managed Agents.
Questions people ask
Is Ona cheaper than Claude Managed Agents?
No. For runtime, Managed Agents costs less in every scenario we priced: one agent running all month is $53 against $5,140 on Ona's Enterprise listing, and 50 agents in parallel are $634 against $6,521. Managed Agents tokens come on top, and on bochka the same two cost $26 and $317.
Which is faster, Ona or Claude Managed Agents?
We can't say: neither was in the public benchmark runs we use, and Anthropic does not publish a sandbox's vCPU count. Ona lets you pick machine classes up to 32 vCPU on Core, while a Managed Agents sandbox has a fixed size with up to 8 GB of memory.
Can Ona or Claude Managed Agents run Docker?
Ona runs Docker with root inside its Dev Container, and Managed Agents lists Docker as limited availability. Neither documents /dev/kvm for emulators or nested VMs. bochka has root, Docker, systemd and /dev/kvm on every machine.
Can I run Claude Code on Ona or Claude Managed Agents?
On Ona you can install and run Claude Code yourself, but its managed agent is Codex. Managed Agents runs Anthropic's own harness, not Claude Code. bochka ships Claude Code, Codex, OpenCode and others preinstalled, with one API to prompt, steer and watch them.
Is Ona the same as Gitpod?
Yes. Gitpod renamed itself Ona in 2025 and moved toward background coding agents, and Ona is now part of OpenAI. New customers buy its Enterprise plan through sales.
Where does my data run?
New Ona customers run environments in their own AWS or GCP account, and Ona Cloud runs in Frankfurt and North Virginia for existing Core subscribers. Managed Agents stores data and runs code in the US only. bochka runs only in the EU, in Germany, Finland and France.
Try bochka
Install the CLI, then run bochka new.
Product preview