AWS AgentCore vs Unikraft Cloud
Both run work in Firecracker microVMs, but they are built for different jobs. AgentCore is an AWS platform that hosts agent sessions and gives them a managed code interpreter and browser, while Unikraft Cloud turns a Dockerfile into a tiny microVM that sleeps when idle and wakes on the next request.
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.
Unikraft Cloud
Unikraft Cloud is a microVM cloud from Unikraft Inc. that runs any Dockerfile-based workload as a minimal Linux microVM with millisecond cold starts and scale-to-zero.
Your Dockerfile becomes the VM image at build time, and each instance runs on a heavily customized Firecracker VMM, so it boots in milliseconds and can go into standby when no traffic arrives. It is a general compute platform built for dense, bursty work such as HTTP services, headless browsers and agent fleets, sold as flat self-serve plans plus Enterprise dedicated hosts, on-prem and bring your own cloud. It is not a dev machine you log into: instances are reached through services, the CLI and a sandbox plugin for commands and files.
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 | Unikraft Cloud: 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 needs Docker, a big machine and a disk that keeps its installs; AgentCore stops sessions at 2 vCPU and 8 hours, Unikraft's Team pool is 8 GiB for every running instance, and boat gives a full VM that keeps its whole disk. | 100th of 367, with limits $888 a month | Can't run it | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 64th of 366, with limits $1,300 a month | Can't run it | 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 AgentCore Code Interpreter is made for short code runs billed by CPU actually used; Unikraft can do it with sleeping microVMs but caps self-serve plans at 24 running instances. | 7th cheapest of 345 $114 a month | Can't run it | 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, and Unikraft serves HTTP and HTTPS through its load balancer but needs Enterprise for hundreds of active users; boat gives each sandbox HTTPS URLs on up to 50 ports. | 210th of 361, with limits $506 a month | Can't run it | 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 | 125th of 360, with limits $8,075 a month | Can't run it | 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 | Can't run it | 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 images or run Android emulators need Docker and /dev/kvm; AgentCore does not document either, Unikraft keeps nested virtualization for Enterprise, and boat exposes both on every plan. | 52nd cheapest of 377 $399 a month | Can't run it | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither has SSH: AgentCore resets files outside its storage mount after a stop, and Unikraft's Team pool fits one 4 vCPU / 8 GB box; boat keeps the whole disk and lets you log in. | 228th of 368, with limits $52 a month | 219th of 368, with limits $39 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 Chromium but not a full desktop, and Unikraft has no desktop built in; boat streams a Linux desktop at 60fps. | 104th of 369, with limits $202 a month | Can't run it | 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 replay, Unikraft runs your own headless browser that sleeps between requests, and boat runs Chromium on a full machine. | 4th cheapest of 367 $144 a month | Can't run it | 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 | Can't run it | 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 | Can't run it | 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 | Can't run it | 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 | Unikraft Cloud | boat |
|---|---|---|---|
| What it is | An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools | A microVM cloud that runs any Dockerfile as a minimal Linux microVM with scale-to-zero | 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 | Minimal Linux microVM per instance on a customized Firecracker VMM; full VMs on Enterprise | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Machine size | 2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances | Plan pool shared by all running instances: 2 vCPU / 4 GiB, 8 vCPU / 8 GiB or 24 vCPU / 32 GiB | 4 vCPU / 8 GB by default, up to 16 vCPU / 32 GB per sandbox 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 published maximum; instances run until stopped or go into standby when idle | 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 | Volumes, and standby that can snapshot memory and resume with warm caches | The whole disk, saved every minute and on stop |
| Fork and checkpoints | No user snapshots or fork of a session | Checkpoint memory and volumes of a running microVM, then start new instances from it | Fork a running sandbox with its disk; snapshots every minute |
| Docker, systemd and /dev/kvm | Root inside the microVM; arm64 container images; Docker and /dev/kvm not documented | Root; the Dockerfile becomes the VM image, no container runtime inside documented; nested virtualization Enterprise only | Root, Docker, systemd and /dev/kvm for Android emulators and VMs on every plan |
| SSH | No; sessions are reached through AgentCore APIs with IAM or JWT | Not yet; commands and files go through the sandbox plugin and CLI | Yes, into every sandbox |
| Inbound access | No open ports; traffic goes through AgentCore's invoke and command APIs | Services on its load balancer: HTTP on 80, HTTPS on 443, TLS-wrapped TCP on other ports | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; dedicated IPv4 or IPv6 |
| Idle and wake | Session stops after 15 idle minutes by default; the next call starts a fresh microVM | Standby after a 1 second idle cooldown by default; traffic wakes it in milliseconds | A stopped sandbox costs nothing, keeps its disk and boots again when started by API |
| Browser and desktop | Managed Chromium with live view, session recording and replay, profiles and proxies; no full desktop | None built in; you can run your own headless browser from a Dockerfile | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Coding agents | AWS's own managed harness built on Strands Agents, or your own agent code | None preinstalled; you bring the agent in your own image | Claude Code, Codex and five more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code | Network shield can inject secrets into traffic, Enterprise only, limited access | Credentials proxy for model providers and any HTTPS API on every plan; switch a credential to another account when credits run out |
| Regions and GPUs | 17 commercial AWS regions plus GovCloud; NVIDIA G-series and Inferentia2 on Instances | Dallas, Frankfurt, San Francisco, Singapore and Washington DC; GPUs on Enterprise | EU only (Germany, Finland, France); no GPUs |
Every feature Battleships tracks (43)
| Feature | AWS AgentCore | Unikraft Cloud | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | No | Yes |
| Nested virtualization | No | Yes | Yes |
| Root | Yes | Yes | 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 | Yes | 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 | Yes | Yes |
| Secret proxy for any API | No | Yes | Yes |
| Preinstalled agents | No | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | No | No |
| GPU | Yes | Yes | No |
| Windows | No | No | No |
| Arm64 | Yes | Yes | 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 | Not published | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Yes | Yes | No |
| SSO | Yes | No | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | Yes | Yes | No |
| EU data residency | Yes | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for either AWS AgentCore or Unikraft Cloud: neither was 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. Unikraft states cold starts under 10 ms, which is its own figure for start time, 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 Unikraft Cloud 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 | Unikraft Cloud, 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 | $39 · Hobby | $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 | $39 · Hobby | $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 | Can't run it | $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 | Can't run it | $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) | Can't run it | $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.
Unikraft Cloud: Unikraft charges a flat monthly fee for a pool of running capacity: free for 2 vCPU / 4 GiB, $39 for 8 vCPU / 8 GiB, $199 for 24 vCPU / 32 GiB, with sleeping instances not counted. It publishes no per-hour rate, so anything bigger is an Enterprise quote.
Unikraft Cloud: 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 every 4 vCPU scenario here uses the Instances type on EC2, and files outside the storage mount reset after a stop. Unikraft's self-serve pools are small: Team has 8 vCPU and 8 GiB in total, so one 4 vCPU / 8 GB agent fills it, and 50 agents, user sandboxes or 1,000 short jobs fit no self-serve plan. AgentCore is the only one of the three that fits 1,000 short jobs at once, at $1,615 a month, while boat's $2,000 plan queues starts above 90 per minute.
| Scenario | AWS AgentCore | Unikraft Cloud | boat |
|---|---|---|---|
| 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 GPUs or one of 17 AWS regions, 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 for CPU used, with live view and replay.
- GPUs and two-week sessions. The Instances type runs sessions for up to 14 days on EC2 in your account, with NVIDIA G-series or Inferentia2.
Use Unikraft Cloud when
you run many small services or headless browsers that sleep most of the time and must wake in milliseconds, or want on-prem or your own cloud under an Enterprise contract.
- Millisecond starts and scale-to-zero. Best for many small services that sleep most of the time and must answer the next request in milliseconds.
- Checkpoints of a running microVM. You can checkpoint memory and volumes of a running instance and start new ones from it with warm state.
- Your own hardware on Enterprise. Enterprise customers can run on dedicated hosts, on-prem or in their own cloud, with GPUs and arm64 hosts.
Where boat fits
AgentCore is shaped around AWS-hosted agent calls and Unikraft around tiny services that sleep. If your agents do real work on a machine for hours, with installs, Docker, builds and a browser, boat gives each one a full VM that keeps its disk, opens URLs you can click and runs fleets without a sales call.
A whole machine with Docker and /dev/kvm
AgentCore caps a microVM session at 2 vCPU and documents no Docker or /dev/kvm; Unikraft documents no container runtime inside and keeps nested virtualization for Enterprise. boat gives root, Docker, systemd and /dev/kvm up to 16 vCPU / 32 GB.
The whole disk stays, with no 8-hour cutoff
On AgentCore only a 1 GB preview mount survives a stop, and longer sessions mean running EC2 Instances in your account. Unikraft has no SSH to set up a box by hand. boat saves the full disk every minute and has no session cap.
Agents, keys and preview URLs built in
Neither ships coding agents, and Unikraft's secret injection is Enterprise only. boat preinstalls Claude Code, Codex and five more you drive from outside, keeps real keys in a credentials proxy, and serves HTTPS on up to 50 ports.
Use boat when your agents need a real machine to work in for hours: Docker, emulators, a desktop and a browser, a disk that keeps everything, URLs you can open, and coding agents you drive from outside. Compare it one to one: boat vs AWS AgentCore and boat vs Unikraft Cloud.
Questions people ask
Is AWS AgentCore cheaper than Unikraft Cloud?
It depends on the shape. For one agent that never stops, Unikraft's $39 Team pool costs less than AgentCore's $107 a month on Instances. For 50 agents, user sandboxes or 1,000 short jobs, no self-serve Unikraft plan is big enough, so only AgentCore has a listed price.
Which is faster, AgentCore or Unikraft Cloud?
Neither has a comparable CPU measurement. Unikraft is built to start fast: its microVMs cold boot in milliseconds and wake on the next request. AgentCore starts a fresh microVM when a stopped session is called again.
Can AgentCore or Unikraft Cloud run Docker?
AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker works inside a session. Unikraft builds your Dockerfile into the VM image and documents no container runtime inside. A boat sandbox runs Docker, systemd and /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; Instances run for up to 14 days. Unikraft publishes no maximum and puts idle instances into standby. boat has no session cap on paid plans.
Can I SSH into AgentCore or Unikraft Cloud?
No. AgentCore sessions are reached only through its APIs with IAM or JWT, and Unikraft has announced SSH as coming soon, with commands and files going through its sandbox plugin and CLI today. You can SSH into every boat sandbox.
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 Unikraft Cloud
- 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