Replit vs Agent 37

Replit is an AI app builder: you describe an app, Replit Agent writes it, and Replit hosts it. Agent 37 is an API that gives each of your users their own agent sandbox, which can sleep when idle and wake on the next message.

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.

Kind of product: AI app builder with workspaces and app hosting, not a sandbox API
Hosting: Data is hosted mainly in Google Cloud data centers in the United States, with an optional India region
Regions for published apps: North America, Europe, Asia, South America and Australia on Core, Pro and Enterprise; the free plan publishes to North America
Isolation: Not documented: the security page promises strong logical separation between users but does not say containers or VMs
Plans: Starter (free), Core $20 a month, Pro from $100 a month, Enterprise custom; plan fees come back as usage credits
Compliance: Says it has a SOC 2 Type 2 attestation

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.

Isolation: gVisor by default; opt-in full VM type with its own kernel and KVM
Where it runs: Dedicated servers in the United States
Billing: Prepaid wallet, metered per minute, no plan fee or seat charge
Instance types: Default (shared), Performance (dedicated cores), VM
Compliance: SOC 2 Type I, Type II in progress
Company: Y Combinator company based in New York

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	Agent 37: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A software factory starts many agents from code, which Agent 37 and bochka do by API, while Replit's MCP server drives Replit Agent one app at a time.	181st of 367, with limits $2,000 a month	2nd cheapest of 367 $551 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB This is what Agent 37 is built for: one always-on assistant per user that sleeps when idle and wakes on the next message, while on Replit each one is a Reserved VM app billed all month.	202nd of 366, with limits $2,033 a month	Cheapest of 366 $279 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 Agent 37's small default sandboxes suit short code runs; Replit's Autoscale is a web host, not a code runner, and bochka's start limits make big bursts a poor fit.	228th of 345, with limits $146 a month	Cheapest of 345 $22 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 Agent 37 holds up to 200 instances on its top self-serve tier, counting sleeping ones, and Replit does not publish how many deployments can run at once; bochka plans go up to 2,000.	233rd of 361, with limits $825 a month	30th of 361, with limits $79 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	6th of 360, with limits $363 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	90th of 364, with limits $58 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 bochka has on every machine, Agent 37 has only on its VM type, and Replit does not document.	275th of 377, with limits $425 a month	2nd cheapest of 377 $84 a month	4th cheapest of 377 $86 a month
24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Replit is a good place to code by hand in the browser, while Agent 37 and bochka keep a full machine and its disk around the clock.	165th of 368, with limits $109 a month	3rd cheapest of 368 $12 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, bochka streams a 60fps desktop out of the box, and Replit's VNC pane is for a person, with no computer-use API.	190th of 369, with limits $619 a month	Cheapest of 369 $53 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	229th of 367, with limits $317 a month	48th of 367, with limits $29 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	Cheapest of 346 $32 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	36th of 338, with limits $648 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 bochka can fork a running VM to try many paths at once; Agent 37 has no fork, and Replit has no API to start many machines.	208th of 360, with limits $215 a month	Cheapest of 360 $43 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	Agent 37	bochka
Kind of product	AI app builder with browser workspaces and app hosting	Agent sandboxes by API, one per user, with a chat API per instance	Sandboxes you create, stop and fork by API, SDK or CLI
Isolation	Not documented; the security page says strong logical separation between users	gVisor by default; full VM as an opt-in instance type	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 instances from templates, with files, exec, SSH and HTTPS URLs	API, SDK and CLI to create, stop, resume and fork many sandboxes
Docker inside	System packages come from Nix; the docs do not describe Docker	Only on the VM type, at 2.5x the default compute rate	Docker, root and systemd in every sandbox
Nested virtualization	Not described in the docs	/dev/kvm on the VM type, with a ready Android template	/dev/kvm in every sandbox, Android emulator works
Sleep when idle	Autoscale apps wake on the first request and go idle after 15 minutes	Opt-in auto-sleep (default 15 minutes) that keeps memory and wakes on the next request	No idle timer; a time limit you set, or no limit; a stopped sandbox costs nothing
Fork and snapshots	Agent checkpoints at milestones in the workspace	No fork; daily backups plus one on-demand backup, restored in place only	Fork a running sandbox; snapshots every minute; named snapshots as templates
Custom images	Nix packages in the workspace	Your own linux/amd64 Docker image as a template	Templates from named snapshots, no Dockerfile builds
Coding agents	Replit Agent, which you can also drive from an MCP client	Hermes, OpenClaw, Claude Code, Codex, Grok, OpenCode, Pi, with a chat API	Claude Code, Codex, OpenCode, pi and more, with a prompt, steer and events API
Keys kept out of the sandbox	Managed keys for OpenAI, Anthropic, Google and OpenRouter models; other keys are app secrets	Managed LLM, search and Composio through a per-instance token; your own keys go in as env vars	Proxy for model providers and any HTTPS API you register, with credential switching when credits run out
Desktop and computer use	VNC pane that streams a desktop to a person; no computer-use API	noVNC desktop through a template build or the Ubuntu VM template	60fps desktop and Chromium in every sandbox, computer use, embeddable stream
Hosting and databases	Published apps on HTTPS domains, with Postgres and App Storage built in	HTTPS URL per port, signed URLs, custom domains; no public IP	HTTPS URLs for up to 50 ports, raw TCP, dedicated IPv6 or IPv4; no hosted databases
Regions	North America, Europe, Asia, South America and Australia for published apps on Core and up	United States	EU only: Germany, Finland, France, with EU data residency

Every feature Battleships tracks (43)

Feature	Replit	Agent 37	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	No	No	Yes
Nested virtualization	No	No	Yes
Root	Not published	Yes	Yes
Systemd	No	Not published	Yes
Desktop GUI	Yes	Yes	Yes
Browser	No	Yes	Yes
Computer-use API	No	Yes	Yes
SSH	Yes	Yes	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	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	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	No	No
Secret proxy	Yes	Yes	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	No	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	Yes	Yes
Usage per sandbox (API)	Yes	Yes	Yes
Audit logs	Yes	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	No	No	No
EU data residency	Yes	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

ReplitNot measured

Agent 37Not measured

bochka26.69 runs/s

There is no comparable measurement for Replit or Agent 37: neither is in StarSling's public hpc-sandbox-benchmarks. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB there. Agent 37 says its default instances share host resources and sells a Performance type on dedicated cores.

Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Replit and Agent 37 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	Agent 37, 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	$6 · Wallet (any top-up)	$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	$12 · Wallet (any top-up)	$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	$329 · Wallet ($100 lifetime top-ups)	$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	$33 · Wallet ($250 lifetime top-ups) · 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	$825 · Pro $1,000 (annual) · with limits	$73 · Wallet ($250 lifetime top-ups) · with limits	$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 on to pay-as-you-go. A Reserved VM, the only kind that stays on, has a fixed monthly price per size and bills whether busy or idle.

Agent 37: Agent 37 uses 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, plus $0.09 per GB of disk per month even while asleep. VM compute costs 2.5x and Performance compute 4x the default rate.

Agent 37: A monthly plan from $20, and all of it is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.

Limits in those scenarios

Replit is marked as not a fit in every scenario because it is an app platform: one Reserved VM is one published app that runs all month, and it does not publish how many deployments can run at once. Agent 37 caps instances at 10 after a first top-up, 50 at $100 of total top-ups and 200 at $250, counting sleeping and stopped ones, so 300 sandboxes for your users or 1,000 jobs at once do not fit. Its 50-agent scenario needs Docker, so it is priced on the VM type. 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	Agent 37	bochka
One coding agent, workdays	different kind of product: app platform monthly / always-on product: priced as 1 machines kept on and reused	egress price not published	None that bite
One agent that never stops	different kind of product: app platform	egress price not published	None that bite
50 agents in parallel	adjacent product, not a like-for-like sandbox missing persistent disk, Docker inside different kind of product: app platform how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)	egress price not published	None that bite
Sandboxes for your users	adjacent product, not a like-for-like sandbox different kind of product: app platform not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	max 200 concurrent egress price not published	None that bite
1,000 short jobs at once	adjacent product, not a like-for-like sandbox different kind of product: app platform not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	max 200 concurrent shared vCPUs on this tier: heavy, sustained CPU use can be slowed by other tenants egress price not published	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

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 Postgres and storage.
Web hosting that costs nothing when idle. Useful for web apps with uneven traffic: Autoscale wakes on the first request and costs nothing while idle.
Regions on five continents. Useful if your users are spread out: Replit publishes apps in North America, Europe, Asia, South America and Australia.

Use Agent 37 when

you host one mostly idle assistant per customer in the US that should sleep with its memory kept and wake on the next message.

One agent sandbox per user, by API. Useful if you give each customer an agent: your code creates instances from templates and talks to them through a chat API.
Sleeps when idle and keeps its memory. Useful for assistants idle most of the day: an instance sleeps, keeps its memory and wakes on the next message.
Bring a Dockerfile, pick dedicated cores. Agent 37 builds templates from your own Docker image, and sells a Performance type on dedicated cores.

Where bochka fits

If your own code needs to start machines for agents that do real work, look at bochka. Every sandbox is a full VM with Docker, systemd and a desktop, you can fork one while it runs, and keys stay outside for any API. Replit is built for people who want an app, and Agent 37 is built around light sandboxes that sleep.

A full VM by default

Agents run docker compose, start services and boot emulators. Replit's docs do not describe Docker or systemd, and on Agent 37 Docker needs the VM type at 2.5x the compute rate, still with no init system.

Fork a machine while it runs

Without a fork, you cannot split one half-done task into several tries at once. Agent 37 backups restore only onto the same instance, and Replit has no API to start many machines.

Keys stay outside, for any API

On Replit, keys other than its managed AI models are app secrets, and on Agent 37 your own keys are env vars inside the instance. Code the agent runs can read them; bochka's proxy keeps them outside for any HTTPS API.

Use bochka when your agents do real work for hours: Docker, systemd and emulators on a full VM, forks of running machines, a 60fps desktop and keys kept outside for any API. Compare it one to one: bochka vs Replit and bochka vs Agent 37.

Questions people ask

Is Replit cheaper than Agent 37?

No, not for agent machines. One agent that never stops comes to $122 a month on Replit and $12 on Agent 37 (bochka: $26), and 50 agents in parallel come to $1,330 on Replit against $329 on Agent 37 (bochka: $317). Replit prices an always-on agent as a Reserved VM that bills all month.

Is Replit an agent sandbox like Agent 37?

No. Replit is an app builder where Replit Agent writes and publishes apps, and its machines are workspaces and published deployments. Agent 37 gives your code one sandbox per user by API, and so does bochka.

Which is faster, Replit or Agent 37?

We cannot say: neither has a result on StarSling's public benchmark. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB there. Agent 37 sells a Performance type on dedicated cores for steady speed.

Can Replit or Agent 37 run Docker?

Replit's docs set up environments with Nix packages and do not describe Docker. Agent 37 runs Docker only on its VM type, which bills compute at 2.5x; the default gVisor type cannot run a Docker daemon. Every bochka sandbox runs Docker.

Where do Replit and Agent 37 run?

Replit hosts data mainly on Google Cloud in the United States, and on Core and up publishes apps in North America, Europe, Asia, South America or Australia. Agent 37 runs on dedicated servers in the United States. bochka runs only in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview