boat vs AWS AgentCore
AgentCore is the part of AWS that hosts agents and gives them a code interpreter and a browser. boat gives each agent a whole Linux machine that keeps its disk, runs as long as you want and can serve a preview URL, while AgentCore fits best when your agents already live inside AWS.
Where boat stands out
A whole machine, for as long as the work takes
A boat sandbox is a full VM with root, Docker, systemd and /dev/kvm, up to 16 vCPU / 32 GB, with no session cap on paid plans. An AgentCore microVM session tops out at 2 vCPU / 8 GB and stops after 8 hours, or after 15 idle minutes by default.
The whole disk stays, with snapshots and fork
boat saves the full disk every minute and when a sandbox stops, and you can fork a running sandbox with its disk. On AgentCore only one storage mount under /mnt, up to 1 GB and still in preview, survives a stop, and there is no snapshot or fork.
Open the app your agent is building
boat gives each sandbox HTTPS URLs on up to 50 ports, token-protected by default, plus raw TCP and SSH. AgentCore sessions have no open ports; you reach them only through AgentCore's invoke and command APIs.
The companies and products
boat
boat.dev runs sandboxes for AI agents: each one is a full Linux VM with its own kernel.
You start a machine with one command or one API call, then SSH in, run Docker, open a desktop, or let a built-in agent (Claude Code, Codex, OpenCode and others) work in it. The disk stays between sessions, and a stopped sandbox costs nothing.
- Isolation
- Full VM per sandbox, own kernel
- Regions
- EU: Germany, Finland, France
AWS AgentCore
Amazon Bedrock AgentCore is a set of AWS services to deploy and run AI agents: a Runtime that hosts your agent code, plus built-in Code Interpreter and Browser tools.
AgentCore is not a sandbox product first. It is a hyperscaler's agent platform: you push a container image or code, and each Runtime session gets its own Firecracker microVM that you reach through AgentCore APIs. Around it sit managed tools (Code Interpreter, Browser) and services for memory, identity, gateways and evaluations, and an Instances compute type runs longer sessions on EC2 in your own account. It is built for teams who already build on AWS and want agents to stay inside their account, IAM and VPC.
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. “3rd cheapest of 367” means 2 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 | boat: price rank | AWS AgentCore: price rank |
|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent on AgentCore gets 2 vCPU per microVM session, stops after 8 hours, and keeps only the files in its storage mount; boat gives it a full machine with Docker that keeps its whole disk. | 3rd cheapest of 367 $634 a month | 100th of 367, with limits $888 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that lives on one machine all month outlasts AgentCore's 8-hour microVM lifecycle, so it needs the Instances type on EC2 in your account; on boat it simply keeps running. | 5th cheapest of 366 $657 a month | 64th of 366, with limits $1,300 a month |
| Code interpreter bursts 100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month AgentCore Code Interpreter is built for this: short code runs in a managed session, billed only for the CPU actually used. | 186th of 345, with limits $2,000 a month | 7th cheapest of 345 $114 a month |
| Sandboxes for your users 300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month AgentCore sessions have no open ports, so your users cannot open the app their sandbox is running; boat gives each one HTTPS URLs on up to 50 ports. | Cheapest of 361 $209 a month | 210th of 361, with limits $506 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 34th of 360, with limits $2,000 a month | 125th of 360, with limits $8,075 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 10th cheapest of 364 $200 a month | 33rd cheapest of 364 $650 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month CI jobs that build Android apps or VM images need /dev/kvm, which boat exposes and AgentCore does not document. | 4th cheapest of 377 $86 a month | 52nd cheapest of 377 $399 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB A dev box needs SSH and a disk that keeps installed packages; AgentCore has no SSH and resets everything outside its storage mount after a stop. | 18th cheapest of 368 $26 a month | 228th of 368, with limits $52 a month |
| Computer-use agents 50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month AgentCore Browser drives a browser, not a whole desktop; boat streams a full Linux desktop at 60fps for agents that use other apps too. | 6th cheapest of 369 $200 a month | 104th of 369, with limits $202 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Both fit well: AgentCore Browser is a managed Chromium with live view and session replay, and boat runs Chromium on a full machine you control. | 7th cheapest of 367 $200 a month | 4th cheapest of 367 $144 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month | 6th cheapest of 346 $90 a month | 27th cheapest of 346 $287 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 71st of 338, with limits $1,800 a month | 165th of 338, with limits $5,458 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 2nd cheapest of 360 $200 a month | 62nd of 360, with limits $294 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 |
| 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 |
Key features
Every feature Battleships tracks (43)
| Feature | boat | AWS AgentCore |
|---|---|---|
| Full VM (own kernel) | Yes | Yes |
| Docker inside | Yes | Not published |
| Nested virtualization | Yes | No |
| Root | Yes | Yes |
| Systemd | Yes | No |
| Desktop GUI | Yes | No |
| Browser | Yes | Yes |
| Computer-use API | Yes | Yes |
| SSH | Yes | No |
| Persistent disk | Yes | Yes |
| Pause/resume | Yes | No |
| Automatic snapshots | Yes | No |
| Fork/clone | Yes | No |
| Live fork (no pause) | Yes | No |
| Memory fork | No | No |
| Custom image (Docker or snapshot) | Yes | Yes |
| ≥24 h sessions | Yes | No |
| Idle auto-stop | No | Yes |
| Wake on request | No | Yes |
| HTTPS preview URLs | Yes | No |
| Raw TCP inbound | Yes | No |
| Public IPv4 | No | No |
| Egress allowlist | No | Yes |
| Secret proxy | Yes | No |
| Secret proxy for any API | Yes | No |
| Preinstalled agents | Yes | No |
| Agent harness API | Yes | No |
| MCP server | No | Yes |
| GPU | No | Yes |
| Windows | No | No |
| Arm64 | No | Yes |
| Self-hosting | No | No |
| BYOC | No | Yes |
| Open source | No | No |
| Scoped API keys | Yes | Not published |
| Spend limits | Yes | Yes |
| Usage per sandbox (API) | Yes | No |
| Audit logs | No | Yes |
| SSO | No | Yes |
| SOC 2 | No | Yes |
| HIPAA | No | Yes |
| EU data residency | Yes | Yes |
| Zero data retention | Yes | Not published |
Performance
There is no comparable measurement: AgentCore was not part of the hpc-sandbox-benchmarks run. boat did 26.69 runs per second on its Node.js build-and-test loop at 4 vCPU / 8 GB. An AgentCore microVM session stops at 2 vCPU, so a like-for-like test would have to use the Instances type on EC2.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. AWS AgentCore 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 | boat, a month | AWS AgentCore, 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 | $20 · $20/mo | $26 · Pay-as-you-go (Instances) · with limits |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $26 · $20/mo | $107 · Pay-as-you-go (Instances) · with limits |
| 50 agents in parallel 50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside | $317 · $20/mo × 3 seats | $1,286 · Pay-as-you-go (Instances) · with limits |
| Sandboxes for your users 2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once | $200 · $100/mo × 2 seats | $423 · Pay-as-you-go · with limits |
| 1,000 short jobs at once 2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month | $2,000 · $2000/mo · with limits | $1,615 · Pay-as-you-go (Instances) |
boat: Plans start at $20 a month, and the whole fee is usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
AWS AgentCore: Runtime microVMs, Code Interpreter and Browser bill per second for CPU actually used and for peak memory, with Runtime v2 reclaiming idle memory at higher rates. The 4 vCPU shape in these scenarios is the Instances type: the EC2 on-demand price plus a 12% management fee, with EBS storage and data transfer billed by AWS on top.
Limits in those scenarios
AgentCore's serverless sessions stop at 2 vCPU / 8 GB and 8 hours, so a 4 vCPU agent or one that runs all day needs the Instances type, which runs EC2 in your account for up to 14 days. Outside the storage mount or an EBS volume, files reset when a session stops, so installed packages have to be set up again. boat has no session cap, but its start limits are lower: at 1,000 short jobs at once, the $2000 plan queues starts above 90 per minute.
| Scenario | boat | AWS AgentCore |
|---|---|---|
| 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 AWS AgentCore when
your agents must stay inside your AWS account and VPC, need a GPU, or are short code and browser tasks that fit the managed tools.
- It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC, security groups and PrivateLink, in 17 commercial regions.
- GPUs and two-week sessions on Instances. Agents that need a GPU or a session of up to 14 days can run on EC2 in your account, with Savings Plans applying.
- Managed tools that bill only for what they use. For short code runs and browser tasks, Code Interpreter and Browser charge only for CPU actually used, with live view and replay.
Use boat when
your agents do real work on a machine for hours: installs, builds, tests, Docker, emulators and a browser, with a disk that keeps everything and a URL you can open.
- A whole machine, for as long as the work takes. A long build or an agent working through a backlog gets cut off at 8 hours. The way around it on AgentCore is the Instances type, which means running and paying for EC2 in your own AWS account.
- The whole disk stays, with snapshots and fork. Packages your agent installed with apt or outside the mount are gone after each stop, so every resume repeats the setup. Trying three fixes from the same state means rebuilding that state three times.
- Open the app your agent is building. When an agent starts a dev server, you or your users want to click a link and see it. On AgentCore you would have to proxy that traffic through your own code.
Questions people ask
Is boat cheaper than AWS AgentCore?
In four of the five scenarios on this page, yes. For 1,000 short jobs at once AgentCore costs less in the table and fits, while boat's plans queue starts above 90 per minute, so boat does not fit that one.
How long can an AgentCore session run?
A microVM session lasts up to 8 hours per lifecycle and stops after 15 idle minutes by default; the next call starts a fresh microVM. The Instances type runs sessions for up to 14 days on EC2 in your account. boat has no session cap on paid plans.
Do files survive when an AgentCore session stops?
Only in a configured storage mount under /mnt, which holds up to 1 GB and is in preview, or in EBS volumes on Instances. Everything else in the microVM is gone. boat keeps the whole disk and saves it every minute.
Can I run Docker or an Android emulator on AgentCore?
AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker or /dev/kvm work inside a session. boat runs Docker and exposes /dev/kvm for Android emulators and VMs.
Is AgentCore a sandbox like boat?
Partly. AgentCore is an AWS platform for hosting agents, and its Runtime sessions and Code Interpreter are sandboxes you reach through AWS APIs. boat is a full Linux machine per agent that you can also SSH into and open ports on.
Is boat SOC 2 compliant?
SOC 2 is in progress. We're open about where we stand: live status at status.ascii.dev and our data retention policy at docs.boat.dev/data-retention.
Start a sandbox
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs Oracle Cloud
- boat vs IONOS Cloud
- boat vs Contabo
- boat vs Azure Virtual Machines
- boat vs AWS Fargate
- boat vs netcup
- boat vs AWS EC2
- boat vs Gcore
- boat vs E2B
- boat vs Daytona
- boat vs Modal
- boat vs Vercel Sandbox
- E2B vs AWS AgentCore
- Daytona vs AWS AgentCore
- Modal vs AWS AgentCore
- Vercel Sandbox vs AWS AgentCore
- Cloudflare Sandbox vs AWS AgentCore
- Blaxel vs AWS AgentCore
- Runloop vs AWS AgentCore
- Tensorlake vs AWS AgentCore