AWS AgentCore vs smol machines
AgentCore is the part of AWS that hosts agents and gives them a managed code interpreter and browser, with short sessions inside your AWS account. smol machines gives each agent a whole microVM with no session cap, built on an open-source engine you can also run on your own laptop or servers.
The companies and products
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.
smol machines
smol machines makes fast, isolated Linux microVMs that run the same way on your laptop, in their hosted cloud, or on your own servers.
The core is smolvm, an open-source microVM engine built on libkrun, where each machine has its own guest kernel. smol cloud is the paid hosted service that runs fleets of those machines behind a REST API and Node, Python and Rust SDKs. It is built for developers who want one VM model from local development to production, with live branching of running machines.
- Uptime SLA
- 99.95% on Pro, Startup and Enterprise
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. “7th cheapest of 345” means 6 of the other 344 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 | AWS AgentCore: price rank | smol machines: price rank | boat: 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 and loses files outside its storage mount; smol machines keeps the filesystem and runs Docker, and boat adds /dev/kvm, SSH and coding agents built in. | 100th of 367, with limits $888 a month | 73rd of 367, with limits $604 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB AgentCore microVM sessions end after 8 hours, so an assistant that runs all month needs the Instances type; smol machines and boat both let a machine keep running, and boat adds a desktop and a credentials proxy. | 64th of 366, with limits $1,300 a month | 148th of 366, with limits $1,038 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 Both fit short code runs well: AgentCore Code Interpreter bills only CPU actually used, and smol machines has a one-minute minimum and a /code endpoint for Python and JavaScript. | 7th cheapest of 345 $114 a month | 12th cheapest of 345 $140 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 AgentCore sessions have no open ports, so your users cannot open what their sandbox runs; smol machines publishes up to 16 ports, and boat gives HTTPS URLs on up to 50. | 210th of 361, with limits $506 a month | 7th cheapest of 361 $531 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 smol machines can branch a running machine with its memory and processes, so many rollouts start from one prepared state; AgentCore has no fork of a session. | 125th of 360, with limits $8,075 a month | 111th of 360, with limits $6,978 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 | 33rd cheapest of 364 $650 a month | 36th cheapest of 364 $670 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 Android apps or boot VMs need /dev/kvm, which boat exposes and neither AgentCore nor smol cloud offers. | 52nd cheapest of 377 $399 a month | 66th cheapest of 377 $514 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 228th of 368, with limits $52 a month | 216th of 368, with limits $29 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 AgentCore Browser drives a browser, not a desktop, and smol cloud has no hosted desktop at all; boat streams a full Linux desktop at 60fps with computer use. | 104th of 369, with limits $202 a month | 90th of 369, with limits $156 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 AgentCore Browser is a managed Chromium with live view and session replay, while on smol machines you install and run your own Chromium inside a machine. | 4th cheapest of 367 $144 a month | 176th of 367, with limits $136 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 | 27th cheapest of 346 $287 a month | 241st of 346, with limits $242 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 | 165th of 338, with limits $5,458 a month | 148th of 338, with limits $4,344 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 | 62nd of 360, with limits $294 a month | 252nd of 360, with limits $377 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 | AWS AgentCore | smol machines | boat |
|---|---|---|---|
| What it is | An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools | Hosted microVMs behind a REST API, built on the open-source smolvm engine | A sandbox platform: each agent gets its own full Linux machine |
| Isolation | Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment | libkrun microVM with its own guest kernel | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Biggest machine | 2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances | Up to 32 vCPU / 32 GB on Startup, 16 vCPU / 24 GB on Pro | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Session length | Up to 8 hours per lifecycle on microVMs, 15 idle minutes by default; up to 14 days on Instances | No provider cap; you can set your own time to live | No cap on paid plans; you set the time to live |
| What survives a stop | Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances | The filesystem survives; /tmp and memory paths are emptied; stopped disk keeps billing | The whole disk, saved every minute and on stop; a stopped sandbox costs nothing |
| Fork | No snapshot or fork of a session | Branch a running machine with its memory and processes; checkpoints capture RAM to a file | Fork a running sandbox with its disk; the fork boots fresh |
| Docker and /dev/kvm | Root inside the microVM; Docker and /dev/kvm not documented | Docker inside the VM; nested virtualization not exposed in the cloud | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Shell access | No SSH; sessions are reached through AgentCore APIs with IAM or JWT | Command API and a WebSocket terminal capped at one hour per connection; no SSH | SSH, plus a command API and terminal |
| Inbound access | No open ports | Up to 16 published ports through a returned URL; no dedicated IP | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Network controls | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Outbound blocked, open, or an allowlist of hosts and CIDR ranges | Open internet, no provider-side allowlist |
| Browser and desktop | Managed Chromium with live view, session recording and replay; no full desktop | No hosted desktop or browser; a guide shows running your own Chromium | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Keeping API keys out of the sandbox | AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code | Cloud secrets are environment variables the guest can read | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| GPUs | NVIDIA G-series and Inferentia2 on the Instances type | Not in the hosted cloud; local smolvm can remote GPU work | No |
| Where it runs | 17 commercial AWS regions plus GovCloud | No region choice in the cloud API; open-source smolvm runs on your own laptop or servers | EU only (Germany, Finland, France), with EU data residency |
Every feature Battleships tracks (43)
| Feature | AWS AgentCore | smol machines | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | Yes | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Not published | Yes |
| Systemd | No | Not published | Yes |
| Desktop GUI | No | No | Yes |
| Browser | Yes | No | Yes |
| Computer-use API | Yes | No | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | No | Yes | Yes |
| Automatic snapshots | No | No | Yes |
| Fork/clone | No | 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 | No | Yes | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | No | Yes | Yes |
| Raw TCP inbound | No | Not published | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | Yes | Yes | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | Yes | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | Yes | No | No |
| Windows | No | No | No |
| Arm64 | Yes | Yes | No |
| Self-hosting | No | Yes | No |
| BYOC | Yes | Yes | No |
| Open source | No | Yes | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Yes | Yes | Yes |
| Usage per sandbox (API) | No | Yes | Yes |
| Audit logs | Yes | Not published | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | No | No |
| HIPAA | Yes | No | No |
| EU data residency | Yes | No | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable measurement for either: neither AgentCore nor smol cloud was part of the StarSling hpc-sandbox-benchmarks run. boat did 26.69 runs per second on that Node.js build-and-test loop at 4 vCPU / 8 GB. smol machines publishes a boot time under 200ms for smolvm, which is a start-time figure, not CPU speed.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. AWS AgentCore and smol machines 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 | AWS AgentCore, a month | smol machines, 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 | $26 · Pay-as-you-go (Instances) · with limits | $25 · Standard | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $107 · Pay-as-you-go (Instances) · with limits | $93 · Standard | $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 | $1,286 · Pay-as-you-go (Instances) · with limits | $1,139 · Pro | $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 | $423 · Pay-as-you-go · with limits | $465 · Startup | $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 | $1,615 · Pay-as-you-go (Instances) | $1,389 · Startup | $2,000 · $2000/mo · with limits |
AWS AgentCore: Runtime microVMs, Code Interpreter and Browser bill per second for CPU actually used and for peak memory. The 4 vCPU shape in these scenarios is the Instances type: the EC2 on-demand price plus a 12% management fee, with storage and data transfer billed by AWS on top.
smol machines: smol cloud charges a base fee for every hour a machine runs, plus the CPU and memory the guest actually uses, with a one-minute minimum and disk billed even while stopped. Pro ($20 a month) and Startup ($150 a month) are fees on top of usage, not credit.
smol machines: 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.
Limits in those scenarios
AgentCore's serverless sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU and all-day scenarios use the Instances type, and files outside the storage mount reset after a stop, so AgentCore does not fit the coding agent, always-on or 50-agent scenarios. smol machines caps how many machines you hold by plan: 20 on Standard, 100 on Pro and 1,000 on Startup, so 50 agents needs Pro and 1,000 short jobs at once needs Startup. boat's limit that bites is starts: at 1,000 short jobs at once it queues starts above 90 a minute, so it does not fit that scenario while both others do.
| Scenario | AWS AgentCore | smol machines | boat |
|---|---|---|---|
| One coding agent, workdays |
| None that bite | None that bite |
| One agent that never stops |
| None that bite | None that bite |
| 50 agents in parallel |
| None that bite | None that bite |
| Sandboxes for your users |
| None that bite | None that bite |
| 1,000 short jobs at once |
| None that bite |
|
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.
- Managed code and browser tools. For short code runs and browser tasks, Code Interpreter and Browser bill only CPU actually used, and Browser adds live view and replay.
- 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.
Use smol machines when
you want one open-source VM engine from your laptop to your own servers, or you fan out many branches of a running machine with its memory.
- Open source, from laptop to your own servers. Teams that want the same VM locally, in a hosted cloud and on their own servers can use one open-source engine.
- Live branches with memory. For RL and test fan-out, branch a running machine with its memory and processes, and wake stopped machines on the next command.
- A whole VM with no session cap. Agents that run all day keep their filesystem and Docker on machines up to 32 vCPU, with no provider time limit.
Where boat fits
If your agents do real work on a machine for hours, with installs, builds, emulators, a browser and an app you want to open, look at boat. It gives each agent a full VM that keeps its whole disk, serves HTTPS on up to 50 ports, and comes with a desktop and coding agents built in.
A whole machine with /dev/kvm and SSH
AgentCore microVMs stop at 2 vCPU and 8 hours and do not document Docker, and smol cloud hides nested virtualization and has no SSH. An agent that needs an Android emulator cannot start one on either; boat exposes /dev/kvm.
A desktop and a browser, ready to use
AgentCore Browser drives Chromium but has no full desktop, and smol cloud has neither, so you build and maintain your own stack. boat streams a Linux desktop at 60fps with Chromium and computer use built in.
Agents and keys built in
On smol cloud secrets are environment variables the guest can read, and AgentCore Identity hands keys to your agent code. boat keeps real keys in a credentials proxy outside the sandbox and ships coding agents you drive from outside by API.
Use boat when your agents need a whole machine for real work: Docker, emulators, SSH, a desktop and a browser, with a disk that keeps everything and a URL you can open. Compare it one to one: boat vs AWS AgentCore and boat vs smol machines.
Questions people ask
Is AWS AgentCore cheaper than smol machines?
In the scenarios on this page smol machines costs a little less in four of five, for example $93 against $107 a month for one agent that runs all day. AgentCore is cheaper for 10-minute user sandboxes, but that is its code interpreter, a different kind of product. boat costs less than both except for 1,000 short jobs at once.
Which is faster, AgentCore or smol machines?
Neither has a comparable CPU measurement, so we cannot say. boat did 26.69 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB.
Can AgentCore or smol machines run Docker?
smol machines runs Docker inside the VM, with Docker data on the machine's ext4 disk. AgentCore runs your container image as root in a microVM, but its docs do not say Docker works inside a session. boat runs Docker and also exposes /dev/kvm.
How long can a session run on each?
An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default; the Instances type runs up to 14 days. smol machines has no provider cap, and boat has none on paid plans.
Can I self-host AgentCore or smol machines?
smol machines' engine, smolvm, is open source and runs on your laptop or your own servers. AgentCore is an AWS service, though its Instances type runs on EC2 in your own account. boat is a hosted service only.
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.
Try boat
Install the CLI, then run boat new.
7-day free trial
More comparisons
- boat vs AWS AgentCore
- boat vs smol machines
- 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
- Morph Cloud vs AWS AgentCore
- CodeSandbox SDK vs AWS AgentCore