AWS AgentCore vs Azure Container Apps Sandboxes
AgentCore is an AWS agent platform: short 2 vCPU microVM sessions that stop after 8 hours, plus a managed Code Interpreter and Browser. Azure Container Apps Sandboxes are microVMs with no documented session cap that keep their disk and can suspend with their memory, inside your Azure account.
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. You reach a session through AgentCore APIs, an interactive shell API and authenticated HTTPS session endpoints. Around it sit managed tools (Code Interpreter, Browser) and services for memory, identity, gateways and evaluations. 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.
Azure Container Apps Sandboxes
Azure Container Apps Sandboxes is a service inside Microsoft Azure that gives each agent or user an isolated microVM you create, suspend and resume through an SDK.
It is part of Azure Container Apps, the hyperscaler's serverless container platform, and lives in your Azure subscription as a sandbox group resource. Each sandbox boots from an OCI image or a snapshot and has its own kernel. A stop keeps the disk, or the disk and the memory, and a memory-mode sandbox resumes in under a second. It is built for teams already on Azure that want stateful code execution with Azure networking, identity and billing.
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. “11th cheapest of 336” means 10 of the other 335 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 | Azure Container Apps Sandboxes: 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 stops after 8 hours on a microVM and keeps only files under /mnt mounts. Azure keeps the sandbox's disk and runs Docker on its azure-dev image, but documents no SSH or /dev/kvm; boat has both on every sandbox. | 132nd of 365, with limits $888 a month | 33rd cheapest of 365 $5,276 a month | 5th cheapest of 365 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB | 109th of 361, with limits $1,300 a month | 52nd cheapest of 361 $6,780 a month | 6th cheapest of 361 $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. Our default ranking puts AWS AgentCore at #9, with a managed Code Interpreter billed for CPU actually used, and Azure at #32, with sandboxes that suspend and resume in under a second. boat is at #130, because its start limits do not fit large bursts. | 11th cheapest of 336 $114 a month | 39th cheapest of 336 $354 a month | 189th of 336, 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 Azure fits: each user gets a sandbox with public HTTPS routes, though 300 at once needs a quota raise. AgentCore session endpoints need an AWS signature or OAuth token on every request. Our default ranking puts boat at #2 and Azure at #27. | 205th of 349, with limits $506 a month | 32nd cheapest of 349 $2,260 a month | 3rd cheapest of 349 $209 a month |
| RL rollouts 1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month | 129th of 349, with limits $8,075 a month | 158th of 349, with limits $10,740 a month | 39th of 349, with limits $2,000 a month |
| Agent evals 250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month | 46th cheapest of 359 $650 a month | 85th cheapest of 359 $1,728 a month | 10th cheapest of 359 $200 a month |
| CI runners 40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month Both run CI jobs that fit their limits, but neither documents /dev/kvm for Android or VM builds. Our default ranking puts boat at #2; it exposes /dev/kvm, and each job counts against its plan's start limits. | 51st cheapest of 374 $399 a month | 108th cheapest of 374 $1,046 a month | 2nd cheapest of 374 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB Neither offers SSH: AgentCore has an interactive shell API and keeps only /mnt mounts after a stop, and Azure gives a shell through its own CLI, SDK and portal. Our default ranking puts boat at #13, with SSH and a disk saved every minute. | 242nd of 371, with limits $52 a month | 327th of 371, with limits $262 a month | 19th cheapest of 371 $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. Azure's public images have no desktop; you can build one into your own image and publish it on an HTTPS port. Our default ranking puts boat at #8 and Azure at #40. | 146th of 367, with limits $202 a month | 58th cheapest of 367 $1,573 a month | 7th cheapest of 367 $200 a month |
| Browser-use agents 50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month Our default ranking puts AWS AgentCore at #4, thanks to its managed Chromium with live view and replay, and boat at #6 with Chromium on a full desktop. Azure's public images have no browser; you build one into your own image. | 4th cheapest of 356 $144 a month | 129th of 356, with limits $795 a month | 7th cheapest of 356 $200 a month |
| Scraping & bots (startup scale) 50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month Our default ranking puts boat at #6, AWS AgentCore at #33 with its managed browser and proxy support, and Azure at #62. | 32nd cheapest of 343 $287 a month | 112th cheapest of 343 $561 a month | 6th cheapest of 343 $90 a month |
| Mass scraping & bots (undetectable) 1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month | 164th of 327, with limits $5,458 a month | 240th of 327, with limits $10,956 a month | 73rd of 327, with limits $1,800 a month |
| Parallel red teaming 200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month | 108th of 351, with limits $294 a month | 30th cheapest of 351 $517 a month | 3rd cheapest of 351 $200 a month |
| GPU eval jobs 10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
| macOS agents 5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month | Not ranked: misses a requirement | Not ranked: misses a requirement | Not ranked: misses a requirement |
Key features
| Feature | AWS AgentCore | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| What it is | An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools | A compute type inside Azure Container Apps: microVM sandboxes you create, suspend and resume through an SDK | 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 | MicroVM per sandbox with its own kernel | Full VM with its own kernel, on AMD Ryzen 7 9700X and Ryzen 9 9950X hosts dedicated to boat; vCPUs are shared |
| Biggest machine | 2 vCPU / 8 GB per microVM session, not adjustable; on Instances, the EC2 type you pick sets the size | Seven tiers from 0.25 cores / 0.5 GiB to 16 cores / 32 GiB with 320 GiB disk | 8 vCPU / 16 GB on the $20 plan; 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 documented cap; auto-suspends after an idle timeout, 5 minutes by default | Auto-stop defaults to 1 hour; set up to 30 days, or turn it off on a paid plan for no cap |
| What survives a stop | Mounts under /mnt only: a 1 GB per-session storage mount (preview), your own EFS or S3 Files mounts in a VPC, or EBS volumes on Instances; the rest of the microVM resets | Stop keeps disk only, or disk and memory; a memory-mode resume takes under a second with processes running | The disk, saved every minute and at each stop, kept at least 14 days after a stop; memory is not saved, so a resume is like a reboot |
| Snapshots and fork | No snapshot or fork of a session; on Instances you can seed new EBS volumes from your own EBS snapshots | Snapshot a running sandbox with its memory and create new sandboxes from it | Disk saved every minute; fork a running sandbox from its last 1-minute snapshot; memory is not copied |
| Docker, systemd and /dev/kvm | Root inside the microVM; Docker and /dev/kvm not documented | Depends on the image: azure-dev ships Docker on systemd; the default ubuntu image has only Buildah; nested virtualization not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs on every sandbox |
| Inbound access and shell | Authenticated HTTPS session endpoint per microVM session for 1 to 5 ports in 8000-12000 (IAM or OAuth on every request, not on Instances); interactive shell API; no SSH | Public HTTPS routes per published port; private endpoint from your VNet at extra cost; shell through the aca CLI, SDK or portal; no SSH or public IP | HTTPS URLs on up to 50 ports, token-protected by default or public; SSH; raw ports over IPv6 only on sandboxes with no IPv4 of their own |
| Network controls | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Egress policy with allow, deny, rewrite and header rules by host, path and method; VNet integration | Open internet, no provider-side allowlist; the IP changes at each resume |
| Browser and desktop | Managed Chromium with live view, session recording and replay, profiles and proxies; no desktop beyond the browser window | No desktop or browser in the public images; you can build one into your own OCI image and publish it on an HTTPS port | Full Linux desktop and Chrome streamed at 60fps, with computer-use tools |
| Custom image | Your own container image (arm64 on microVMs; x86_64 or arm64 on Instances) | Any OCI image from a public or private registry, imported as a disk image | Start from boat's Ubuntu 24.04 image or a saved snapshot; you cannot boot your own Docker image |
| Coding agents | AWS's own managed harness built on Strands Agents, or your own agent code in any framework | Copilot CLI and Claude Code images, run through the exec API | Claude Code, Codex and five more installed, 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 | You set it up: an egress Transform rule adds a group secret or managed-identity token as a header, outside the sandbox, one rule per API host; the built-in Copilot and Claude connections put tokens inside | Optional paid proxy ($1 a day plus $1 per 1,000 requests) for model providers and HTTPS APIs you register; other secrets still enter the sandbox |
| GPUs | NVIDIA G-series and Inferentia2 on the Instances type | No | No |
| Regions | 21 commercial AWS regions plus GovCloud (Instances in 9) | 40 Azure regions, 9 of them in the EU | Germany, Finland and France; no region choice, no US or Asia region; snapshot copies can be stored outside the EU |
Every feature Battleships tracks (43)
| Feature | AWS AgentCore | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | Yes | Yes |
| Nested virtualization | No documented way | Not published | Yes |
| Root | Yes | Yes | Yes |
| Systemd | No documented way | Yes | Yes |
| Desktop GUI | No documented way | With your own setup | Yes |
| Browser | Yes | With your own setup | Yes |
| Computer-use API | Yes | No documented way | Yes |
| SSH | No documented way | No documented way | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | No documented way | Yes | Yes |
| Automatic snapshots | No documented way | Yes | Yes |
| Fork/clone | No documented way | Yes | Yes |
| Live fork (no pause) | No documented way | Yes | Yes |
| Memory fork | No documented way | Yes | No documented way |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | No documented way | Yes | Yes |
| Idle auto-stop | Yes | Yes | No documented way |
| Wake on request | Yes | Yes | No documented way |
| HTTPS preview URLs | Yes | Yes | Yes |
| Raw TCP inbound | No documented way | No documented way | Yes |
| Public IPv4 | No documented way | No documented way | No documented way |
| Egress allowlist | Yes | Yes | No documented way |
| Secret proxy | No documented way | Yes | Yes |
| Secret proxy for any API | No documented way | Yes | Yes |
| Preinstalled agents | No documented way | Yes | Yes |
| Agent harness API | No documented way | No documented way | Yes |
| MCP server | Yes | No documented way | No documented way |
| GPU | Yes | No documented way | No documented way |
| Windows | No documented way | No documented way | No documented way |
| Arm64 | Yes | No documented way | No documented way |
| Self-hosting | No documented way | No documented way | No documented way |
| BYOC | Yes | No documented way | No documented way |
| Open source | No documented way | No documented way | No documented way |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | With your own setup | Yes | Yes |
| Usage per sandbox (API) | No documented way | Yes | Yes |
| Audit logs | Yes | Yes | No documented way |
| SSO | Yes | Yes | No documented way |
| SOC 2 | Yes | Yes | No documented way |
| HIPAA | Yes | Yes | No documented way |
| EU data residency | Yes | Yes | No documented way |
| Zero data retention | Not published | Not published | Yes |
Performance
AWS AgentCore and Azure Container Apps Sandboxes are not in the public benchmarks we use, so we cannot say which is faster. In StarSling's run of 3 October 2026 (run 37073680030), boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. This page makes no speed claim between the three.
V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. AWS AgentCore and Azure Container Apps Sandboxes are not in the public benchmarks we use, so we cannot say which is faster.
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. Start limits, per-start fees and plan minimums are in the price, boat's included.
| Scenario | AWS AgentCore, a month | Azure Container Apps Sandboxes, 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 | $68 · Pay-as-you-go | $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 | $262 · Pay-as-you-go · with limits | $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 | $3,421 · Pay-as-you-go | $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 | $989 · 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 | $1,615 · Pay-as-you-go (Instances) | $2,148 · Pay-as-you-go | $8,800 · $2000/mo · with limits |
AWS AgentCore: No monthly fee. Runtime v1 microVMs, Code Interpreter and Browser bill per second: $0.0895 per vCPU-hour for CPU actually used and $0.00945 per GB-hour for peak memory. The 4 vCPU shape in these scenarios is the Instances type: the EC2 on-demand price plus a 12% management fee (7.8% on G-series GPUs), with EBS storage and data transfer billed on top. The scenario prices leave out EBS storage.
Azure Container Apps Sandboxes: Azure bills per second on the Container Apps Consumption meters for the vCPU and memory of the sandbox's tier while it runs, idle time before auto-suspend included. The XL tier (4 cores / 8 GiB) is $0.432 an hour at the East US rates. Stopped sandboxes pay no CPU or memory, and there is no plan fee. Storage for images, snapshots and volumes is announced as billed per GiB later.
Azure Container Apps Sandboxes: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, per second while it runs. The $20 plan includes 12 starts a minute and 200 a day; extra starts cost $0.03 to $0.07. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; extra saved snapshots and the AI credentials proxy still charge. A card is required, also for the 7-day trial.
Limits in those scenarios
AgentCore costs less than Azure in every scenario on this page, but fits only the burst of 1,000 short jobs: a 4 vCPU agent needs the Instances type, files outside /mnt mounts reset after a stop, and sessions end at 14 days. Azure fits four of the five. Its always-on price ($262 a month) needs a 3-year savings plan, and Azure does not state that the plan covers Sandboxes. Azure also caps active cores at 300 per region and subscription by default, so 300 user sandboxes and 1,000 short jobs need a support request first. boat fits all but the burst: its $2,000 plan includes 90 starts a minute, charges for extra starts and refuses starts above 270 a minute.
| Scenario | AWS AgentCore | Azure Container Apps Sandboxes | boat |
|---|---|---|---|
| One coding agent, workdays |
| None for this scenario | None for this scenario |
| One agent that never stops |
|
| None for this scenario |
| 50 agents in parallel |
| None for this scenario | None for this scenario |
| Sandboxes for your users |
| None for this scenario | None for this scenario |
| 1,000 short jobs at once |
| None for this scenario |
|
Which one should you use?
Use AWS AgentCore when
your agents must stay inside your AWS account, need a GPU, or are short code and browser tasks that fit its managed tools.
- Managed browser and code tools. For short code runs and browser tasks, Code Interpreter and Browser are ready to use, with live view, replay and CPU-only billing.
- 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 own AWS account.
- It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC, security groups and PrivateLink, with a fixed outbound IP.
Use Azure Container Apps Sandboxes when
your team runs on Azure and wants sandboxes from its own images that suspend and fork with their memory, wake on traffic and sit behind strict egress rules.
- Suspend with memory, fork with memory. An idle sandbox suspends with its memory and resumes in under a second, and a snapshot with memory starts new sandboxes.
- Fine-grained outbound rules. Its egress policy can allow, deny or rewrite each outbound HTTP request by host, path and method, and can add secrets outside the sandbox.
- Your own image, inside Azure, in 40 regions. Teams already on Azure get Entra ID, Azure billing, VNets and their own OCI images, in 40 regions on six continents.
Where boat fits
Both are hyperscaler services built for teams who want agents inside their AWS or Azure account. If your agents do real work on a machine for hours, with installs, Docker, emulators, a browser and a URL you can open, boat gives each one a whole Linux computer with these ready. boat has no US region, no GPU and no pause with memory.
A whole computer you can SSH into
Neither AgentCore nor Azure offers SSH or documents /dev/kvm, so Android emulators and nested VMs have no documented way to run. AgentCore does not document Docker, and on Azure you pick the azure-dev image or your own image to get it.
A screen for computer-use agents
AgentCore Browser drives Chromium but no other app. Azure's public images have no desktop, so you build a browser, virtual display and streaming stack into your own image. boat streams a 60fps desktop in every sandbox.
URLs a browser can open
AgentCore session endpoints need an AWS signature or an OAuth token on every request. Azure publishes public HTTPS routes. boat gives up to 50 URLs per sandbox, token-protected by default or public.
Use boat when your agents need a whole computer for hours: SSH, Docker, emulators, a desktop and a browser, with a disk saved every minute and coding agents installed. Compare it one to one: boat vs AWS AgentCore and boat vs Azure Container Apps Sandboxes.
boat's own limits
- Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
- Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
- A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
- Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
- boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
- Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
- Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
- Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source
Questions people ask
Is AWS AgentCore cheaper than Azure Container Apps Sandboxes?
In this page's scenarios AgentCore costs less every time, for example $1,615 against $2,148 a month for 1,000 short jobs at once. But AgentCore fits only that burst scenario, while Azure fits four of the five, so for long-running agents the lower AgentCore price comes with real limits. boat costs $20, $26, $317 and $200 in the four scenarios it fits.
Which is faster, AgentCore or Azure Container Apps Sandboxes?
Neither is in the public benchmarks we use, so we cannot say. boat did 28.06 runs/s on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB in StarSling's run of 3 October 2026, on an AMD Ryzen 9 9950X host.
Can AgentCore or Azure Container Apps Sandboxes run Docker?
AgentCore runs your container image as root in a microVM, but its docs do not say Docker works inside a session. On Azure, the azure-dev image ships Docker on systemd, while the default ubuntu image has only Buildah. boat runs Docker on every sandbox 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. Azure documents no cap, but suspends a sandbox after an idle timeout, 5 minutes by default. On boat, auto-stop defaults to 1 hour; on a paid plan you can turn it off for no cap.
Can I SSH into either one?
No, but both give a shell another way. AgentCore has an interactive shell API, and Azure gives a shell through the aca CLI, the SDK or the portal. Every boat sandbox has SSH, so editors and tools that connect over SSH work as on any server.
Is boat SOC 2 compliant?
SOC 2 is in progress. Azure holds a SOC 2 Type 2 report for its cloud services, and AgentCore is listed as a HIPAA eligible AWS service. Live status is 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 Azure Container Apps Sandboxes
- 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