Replit vs Google Agent Runtime
Replit is an AI app builder: you describe an app, Replit Agent writes it, and Replit hosts it. Google Agent Runtime, once called Vertex AI Agent Engine, hosts agent code you write on Google Cloud and gives it code, shell and browser sandboxes that run as an unprivileged user in a container.
The companies and products
Replit
Replit is an AI app builder and hosting platform: you describe an app in chat, Replit Agent writes it, and Replit publishes it.
You work in a browser workspace where Replit Agent sets up the project, writes the code, tests it and fixes problems, with system packages managed by Nix. When the app is ready you publish it as an Autoscale, Static, Scheduled or Reserved VM deployment, with Postgres and object storage next to it. It is built for people and teams who want a working app, not for programs that need to create many machines by API, so this page compares the parts where the two overlap.
Google Agent Runtime
Google Agent Runtime is the agent hosting part of Gemini Enterprise Agent Platform on Google Cloud, renamed from Vertex AI Agent Engine in April 2026.
It is a hyperscaler service, not a sandbox company. Agent Runtime deploys agents you build with ADK, LangGraph, LangChain, AG2 or LlamaIndex and bills them only while they work on a turn. Next to it, Agent Sandbox gives those agents a place to run code: a Code Execution sandbox, a shell or custom container sandbox, and a Computer Use browser. All of them run as secure containers inside your Google Cloud project.
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. “181st cheapest of 367” means 180 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 | Replit: price rank | Google Agent Runtime: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Neither fits a software factory well: Replit drives only Replit Agent through its MCP server, and Google's sandboxes have no root or Docker, while bochka gives every agent a full VM. | 181st of 367, with limits $2,000 a month | 295th of 367, with limits $5,801 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB Google hosts long-lived agent code with Agent Runtime and skips billing for idle time between turns, while Replit needs a Reserved VM, one published app that bills all month; bochka has no session cap on paid plans. | 202nd of 366, with limits $2,033 a month | 28th cheapest of 366 $7,519 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 Short code runs suit Google's Code Execution sandbox, a ready Python interpreter with no network, and Replit's Autoscale bills only while it serves, though it is a web host, not a code runner. | 228th of 345, with limits $146 a month | 254th of 345, with limits $275 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 Replit does not publish how many apps can run at once, and Google gives your users a shell through its API but no public URL; on bochka each sandbox can serve HTTPS on up to 50 ports. | 233rd of 361, with limits $825 a month | 280th of 361, with limits $1,916 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 | 258th of 360, with limits $4,226 a month | 128th of 360, with limits $8,240 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 | 265th of 364, with limits $685 a month | 79th cheapest of 364 $2,060 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 CI jobs that build containers need Docker, which Replit does not document and Google's unprivileged sandboxes do not offer; bochka runs Docker and systemd on every VM. | 275th of 377, with limits $425 a month | 98th cheapest of 377 $989 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Replit is the better place to code by hand, with SSH into the workspace on paid plans, while Google has no SSH into a sandbox; bochka gives you SSH and a desktop. | 165th of 368, with limits $109 a month | 311th of 368, with limits $241 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 Google gives an agent a browser with a click, type and screenshot API, Replit's VNC pane shows a desktop to a person only, and bochka streams a full 60fps desktop with computer use. | 190th of 369, with limits $619 a month | 283rd of 369, with limits $1,648 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 Google runs a real Chromium you can drive over CDP with Playwright, which Replit does not offer as an API; bochka has Chromium and browser control on every sandbox. | 229th of 367, with limits $317 a month | 102nd of 367, with limits $824 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 | 234th of 346, with limits $217 a month | 53rd cheapest of 346 $515 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 | 150th of 338, with limits $4,378 a month | 210th of 338, with limits $8,240 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 | 208th of 360, with limits $215 a month | 260th of 360, with limits $412 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 | Replit | Google Agent Runtime | bochka |
|---|---|---|---|
| Kind of product | AI app builder with browser workspaces and app hosting | Managed agent hosting plus code, shell and browser sandboxes on Google Cloud | Sandboxes you create, stop and fork by API, SDK or CLI |
| Isolation | Not documented; the security page says strong logical separation between users | Secure container sandboxing inside Google Cloud | Every sandbox is a full VM with its own kernel |
| Creating machines from code | MCP server tools to create, update and publish apps; no API to start many machines | API to create, pause and delete sandboxes, with templates | API, SDK and CLI to create, stop, resume and fork many sandboxes |
| Root, Docker and nested virtualization | System packages come from Nix; Docker, systemd and /dev/kvm are not described | Runs as appuser with no sudo; images must not need root; no Docker or /dev/kvm | Root, systemd, Docker and /dev/kvm on every machine |
| Shell access | SSH into the workspace on paid plans | execute_bash() API calls; each command runs in a new shell; no SSH | SSH, plus an API for commands |
| Files over time | Workspace files and Agent checkpoints; published apps should not rely on their filesystem | Pause keeps the file system; the sandbox is deleted when its TTL ends | Snapshots every minute and on stop; a stopped sandbox costs nothing |
| Memory snapshots and branching | No memory snapshots | Snapshots keep memory and files; start many sandboxes from one snapshot | Fork a running sandbox; resume reboots from disk (no memory snapshots) |
| How long a machine lives | Reserved VM runs continuously at a fixed monthly price per size | TTL of up to 7 days for a custom container and 14 days for Code Execution | No session cap on paid plans; stopping ends the bill |
| Desktop and computer use | VNC pane that streams a desktop to your browser; no computer-use API | A browser in a container with a VNC view, a click, type and screenshot API, and CDP | 60fps desktop and Chromium, computer use and browser control, embeddable stream |
| Reaching the machine | Published apps on HTTPS domains, custom domains and private deployments | Through Google's API, or a private endpoint in your own VPC; no public URL documented | HTTPS URLs for up to 50 ports, token-protected; raw TCP; dedicated IPv6 or IPv4 |
| Coding agents | Replit Agent, which you can also drive from an MCP client | Managed Agents API (Preview) runs Google's Antigravity harness | Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API |
| Keeping keys out of the sandbox | Replit manages keys for some AI models, billed to credits; other keys are app secrets | You provision and scope the credentials the agent uses | AI credentials proxy for model providers and any HTTPS API you register |
| Hosting finished work | Autoscale apps that sleep when idle, with Postgres and App Storage built in | Agent Runtime hosts ADK, LangGraph and other agents; idle time between turns is not billed | No hosted databases or wake on request; you run services inside a sandbox |
| Regions | North America, Europe, Asia, South America and Australia for published apps on Core and up | 23 locations in the US, Europe, Asia, Canada, Australia and Brazil | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Replit | Google Agent Runtime | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | No | Yes |
| Docker inside | No | No | Yes |
| Nested virtualization | No | No | Yes |
| Root | Not published | No | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | Yes | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | No | Yes | Yes |
| Automatic snapshots | Yes | Yes | Yes |
| Fork/clone | Yes | Yes | Yes |
| Live fork (no pause) | No | 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 | No | No |
| Wake on request | Yes | No | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | Not published | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | Yes | Yes | Yes |
| Agent harness API | Yes | Yes | Yes |
| MCP server | Yes | No | No |
| GPU | No | No | No |
| Windows | No | No | No |
| Arm64 | Not published | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | No | 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 | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for Replit or Google Agent Runtime. In StarSling's public run of 2026-09-29, bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB, but neither Replit nor Google was in that run, so we cannot say which is faster.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Replit and Google Agent Runtime 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 | Replit, a month | Google Agent Runtime, 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 | $122 · Pro $100 (annual) · with limits | $73 · Pay as you go | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $122 · Pro $100 (annual) · with limits | $301 · Pay as you go | $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 | $1,330 · Pro $1,000 (annual) · with limits | $3,626 · Pay as you go · 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 | $403 · Pro $250 (annual) · with limits | $1,030 · Pay as you go | $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 | $825 · Pro $1,000 (annual) · with limits | $2,060 · Pay as you go | $2,000 · $2000/mo · with limits |
Replit: Replit plans (Core $20, Pro from $100) turn into monthly credits for Agent work and hosting, then usage goes to pay-as-you-go. A Reserved VM has a fixed monthly price per size, such as $130 for 4 vCPU / 16 GB, and our bills price agents that way, leaving out Agent usage.
Google Agent Runtime: Google bills $0.085 per vCPU-hour and $0.009 per GiB-hour allocated, with the first 50 vCPU-hours and 100 GiB-hours free each month. Sandboxes are billed while they exist, and disk and egress rates are not published.
Google Agent Runtime: You pick a monthly plan from $20, and all of it becomes usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Replit does not fit any scenario as is, because one Reserved VM is one published app that runs all month, and it does not publish how many can run at once. Google fits four of the five, but the 50-agent fleet fails because its sandboxes have no Docker, and every Google row leaves disk and egress unpriced. On bochka, the 1,000-job burst is queued above 90 starts a minute and needs more starts per day than the $2,000 plan allows.
| Scenario | Replit | Google Agent Runtime | 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 Replit when
you want Replit Agent to build a web app from a description and host it for you, with databases, sleeping when idle and regions on five continents.
- An app built and hosted for you. Useful if you want a working app from a description: Replit Agent builds, tests and publishes it with a domain and Postgres.
- Hosting that costs nothing when idle. Useful for web apps with uneven traffic: Autoscale wakes on the first request and costs nothing while idle.
- A workspace people code in. Useful for people who build by hand in a browser, with SSH into the workspace on paid plans.
Use Google Agent Runtime when
you build agents with ADK or LangGraph on Google Cloud and want them hosted inside your own project and network, with short code runs in a locked sandbox.
- A managed home for your agent code. Useful if you build agents with ADK or LangGraph: Agent Runtime hosts them and skips billing for idle time between turns.
- Inside your Google Cloud network. Useful if agents must stay in a Google Cloud perimeter, with egress off by default and routed through your own firewall.
- Memory snapshots. Useful if you branch work: a Google sandbox snapshot keeps memory and files, and many sandboxes can start from one.
Where bochka fits
If what you are really running is coding agents that need a real computer, neither one is built for it: Replit is an app builder and Google's sandboxes are locked containers. bochka gives every agent a full VM with root, Docker, a desktop and public URLs, started by your own code.
Root, Docker and a real kernel
Agents reach for sudo apt install and docker compose. Google's sandboxes run as appuser with no sudo, and Replit's Nix setup does not describe Docker. bochka has root, systemd, Docker and /dev/kvm on every VM.
Machines that stay and are reachable
A Google sandbox is deleted after its TTL, 7 days at most for a custom container, with no public URL. A Replit Reserved VM bills all month. bochka keeps the disk, has no session cap and serves HTTPS on 50 ports.
Your coding agents, driven from outside
Replit drives only Replit Agent and Google runs its own Antigravity harness in Preview. bochka ships Claude Code, Codex and OpenCode with a prompt, steer and events API, and its credentials proxy keeps keys outside the sandbox.
Use bochka when your own code needs to start machines for agents: full VMs with root, Docker, SSH, a desktop and public URLs, with Claude Code, Codex and other coding agents built in. Compare it one to one: bochka vs Replit and bochka vs Google Agent Runtime.
Questions people ask
Is Replit cheaper than Google Agent Runtime?
It depends on the job. For one agent running all month, Replit comes to $122 against $301 on Google, but for one coding agent on workdays Google is lower at $73 against $122. On bochka those two come to $26 and $20 a month.
Which is faster, Replit or Google Agent Runtime?
We cannot say: neither is in StarSling's public benchmark. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in that run.
Can Replit or Google Agent Runtime run Docker?
Replit sets up environments with Nix packages and does not describe running Docker. Google's sandboxes run as the unprivileged user appuser with no sudo, so Docker is not available. Every bochka sandbox is a VM with root, Docker and /dev/kvm.
Is Google Agent Runtime the same as Vertex AI Agent Engine?
Yes. Google renamed Vertex AI Agent Engine to Agent Runtime in April 2026, as part of Gemini Enterprise Agent Platform. Its code, shell and browser sandboxes are a separate part called Agent Sandbox.
Can I drive the agents from my own code?
Partly on both. Replit's MCP server lets an MCP client create and update apps through Replit Agent, and Google's Managed Agents API in Preview runs its own Antigravity harness. On bochka you prompt, steer and stream events from Claude Code, Codex and other agents in each sandbox.
Where does my data run?
Replit hosts data mainly on Google Cloud in the United States and publishes apps on five continents. Google runs in 23 locations inside your own project. bochka runs only in the EU (Germany, Finland and France), with EU data residency.
Try bochka
Install the CLI, then run bochka new.
Product preview