CodeSandbox SDK vs AWS AgentCore
CodeSandbox SDK gives each sandbox a Firecracker VM up to 16 cores that keeps its disk and hibernates with its memory. AWS AgentCore hosts agent sessions of up to 2 vCPU and 8 hours inside your AWS account, with managed Code Interpreter and Browser tools around them.
The companies and products
CodeSandbox SDK
CodeSandbox SDK is an API from CodeSandbox, now a Together AI company, that starts sandboxed development VMs on the same infrastructure as the CodeSandbox editor.
Each sandbox is a Firecracker microVM built from a template or any Dockerfile. When it goes idle it hibernates with a memory snapshot, and it resumes or forks from that snapshot in seconds. You drive it from a TypeScript SDK through terminals, commands, files and HTTPS hosts. Together's docs now call it the legacy offering and point new users to its successor, the together-sandbox SDK.
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. “46th cheapest of 345” means 45 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 | CodeSandbox SDK: price rank | AWS AgentCore: 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 and keeps only its storage mount, while CodeSandbox SDK keeps the whole disk; boat adds SSH, systemd and /dev/kvm. | 178th of 367, with limits $1,939 a month | 100th of 367, with limits $888 a month | 3rd cheapest of 367 $634 a month |
| Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that runs all month outlasts AgentCore's 8-hour microVM sessions and needs the Instances type; CodeSandbox SDK and boat have no hard session cap. | 215th of 366, with limits $2,478 a month | 64th of 366, with limits $1,300 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 AgentCore Code Interpreter is built for short code runs and bills only for CPU used; CodeSandbox SDK fits too, with VMs that hibernate between runs. | 46th cheapest of 345 $642 a month | 7th cheapest of 345 $114 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 CodeSandbox SDK gives each user's sandbox an HTTPS host that wakes it on request, while AgentCore sessions have no open ports at all. | 140th of 361, with limits $1,707 a month | 210th of 361, with limits $506 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 CodeSandbox SDK can fork a running sandbox that shares memory with its parent, so rollouts branch from one warm state; AgentCore has no fork. | 348th of 360, with limits $3,861 a month | 125th of 360, with limits $8,075 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 | 64th cheapest of 364 $1,335 a month | 33rd cheapest of 364 $650 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 Both run your own image, but CI jobs that build Android apps or VM images need /dev/kvm, which neither documents and boat exposes. | 92nd cheapest of 377 $860 a month | 52nd cheapest of 377 $399 a month | 4th cheapest of 377 $86 a month |
| 24/7 dev boxes 1 machine 24/7 · 4 vCPU / 8 GB | 310th of 368, with limits $240 a month | 228th of 368, with limits $52 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 Neither offers a full desktop: AgentCore drives a browser only and CodeSandbox SDK has none, while boat streams a Linux desktop at 60fps. | 206th of 369, with limits $691 a month | 104th of 369, with limits $202 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 replay; on CodeSandbox SDK you build a headless browser template yourself, and boat ships Chromium on a desktop. | 251st of 367, with limits $443 a month | 4th cheapest of 367 $144 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 | 281st of 346, with limits $508 a month | 27th cheapest of 346 $287 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 | 193rd of 338, with limits $7,390 a month | 165th of 338, with limits $5,458 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 | 240th of 360, with limits $326 a month | 62nd of 360, with limits $294 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 | CodeSandbox SDK | AWS AgentCore | boat |
|---|---|---|---|
| What it is | A sandbox SDK: dev VMs on CodeSandbox's infrastructure, now called legacy by Together AI | An AWS agent platform: hosted agent sessions plus managed Code Interpreter and Browser tools | A sandbox platform: each agent gets its own full Linux machine |
| Isolation | Firecracker microVM with its own kernel | Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment | Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts |
| Biggest machine | Up to 16 cores / 32 GB on Scale, 64 cores / 128 GB on Enterprise | 2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances | Up to 16 vCPU / 32 GB on the $100 plan and above |
| Session length | No hard cap; hibernates after an idle timeout of up to one day | Up to 8 hours per microVM lifecycle, 15 idle minutes by default; up to 14 days on Instances | No cap on paid plans; you set the time to live |
| What survives a stop | The disk, plus memory and running processes through hibernation | Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances | The whole disk, saved every minute and on stop; resume boots the machine again |
| Fork | Fork a hibernated sandbox from its snapshot, or a running one sharing its memory | No snapshots or fork of a session | Fork a running sandbox with its disk |
| Docker, systemd and /dev/kvm | Docker and root, built from any Dockerfile; nested virtualization not documented | Root inside the microVM, arm64 container images; Docker and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Shell access | Terminals, commands and files through the SDK; no SSH | Invoke and command APIs with IAM or JWT; no SSH | SSH, plus exec and files over the API |
| Inbound access | HTTPS host per port, public by default, wakes the VM on request; no raw TCP | No open ports; sessions are reached only through AgentCore APIs | HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; a dedicated IPv6 or IPv4 |
| Network controls | No egress allowlist or fixed outbound IP | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet, no provider-side allowlist |
| Browser and desktop | No desktop; a headless Chromium template | Managed Chromium with live view, session recording and replay; no full desktop | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Coding agents | Run your own agent through the command API | AWS's managed harness built on Strands Agents, or your own agent code | Claude Code, Codex and others preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets passed in as environment variables | AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code | Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| GPUs and regions | No GPUs; a country hint steers scheduling but placement is not guaranteed | GPUs on Instances; 17 commercial AWS regions plus GovCloud | No GPUs; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | CodeSandbox SDK | AWS AgentCore | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | No | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | No | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | Yes | Yes |
| SSH | No | No | Yes |
| Persistent disk | Yes | Yes | Yes |
| Pause/resume | Yes | No | Yes |
| Automatic snapshots | Yes | No | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | Yes | No | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | No | Yes |
| Idle auto-stop | Yes | Yes | No |
| Wake on request | Yes | Yes | No |
| HTTPS preview URLs | Yes | No | Yes |
| Raw TCP inbound | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | No | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | No | Yes | No |
| GPU | No | Yes | No |
| Windows | No | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | No | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Not published | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for CodeSandbox SDK or AWS AgentCore: neither was part of the hpc-sandbox-benchmarks run. boat did 26.69 runs per second on its Node.js loop at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. CodeSandbox SDK and AWS AgentCore 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 | CodeSandbox SDK, a month | AWS AgentCore, 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 | $193 · Scale | $26 · Pay-as-you-go (Instances) · with limits | $20 · $20/mo |
| One agent that never stops 4 vCPU / 8 GB, 50 GB disk, running 24/7 all month | $341 · Scale | $107 · Pay-as-you-go (Instances) · 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 | $2,500 · Scale | $1,286 · Pay-as-you-go (Instances) · with limits | $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 | $815 · Scale · with limits | $423 · Pay-as-you-go · 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 | $1,632 · Scale · with limits | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
CodeSandbox SDK: You buy VM credits and each size burns a fixed number per hour, billed per started minute while the VM runs, including idle time before it hibernates. The Scale plan adds a $170 monthly platform fee, and a hibernated VM costs nothing.
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 on top.
AWS AgentCore: 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 is lower on price in every scenario here, but only the 1,000-job burst fits it: in the others, files outside the storage mount reset after a stop and the always-on agent hits the 14-day Instances cap. CodeSandbox SDK fits the three single-machine and fleet scenarios, but its Scale plan allows 250 VMs at once, so the user-sandboxes and 1,000-job scenarios need Enterprise. boat fits four of the five, and its start limits queue the 1,000-job burst even on the $2,000 plan.
| Scenario | CodeSandbox SDK | AWS AgentCore | 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 CodeSandbox SDK when
your sandboxes sleep between visits and should wake on the next HTTP request with their memory intact, or when you want to fork many runs from one warm state, and you are fine building on what Together now calls its legacy SDK.
- Hibernation with memory and wake on request. For sandboxes that sleep between visits: an HTTP request wakes a hibernated VM with its processes still running.
- Forks that share memory. For branching many runs, such as rollouts or test variants, from one warm running state.
- Bigger machines that keep their disk. For agents that need more than 2 vCPU without running EC2 yourself: up to 16 cores on Scale and 64 on Enterprise.
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. For teams on AWS that want agents behind their own IAM, VPC, security groups and PrivateLink, in 17 commercial regions.
- Managed tools billed for what they use. For short code runs and browser tasks: Code Interpreter and Browser charge only for CPU actually used.
- GPUs and two-week sessions on Instances. For agents that need a GPU or a session of up to 14 days, running on EC2 in your account.
Where boat fits
CodeSandbox SDK is built for VMs that sleep and wake, and AgentCore for agent sessions inside AWS. If your agents do hours of real work on one machine, with builds, Docker, emulators, a browser and servers people open, boat gives each one a full VM that already has those pieces.
A whole machine with SSH and /dev/kvm
Neither documents nested virtualization, so Android emulators and VM-based tests cannot start, and neither has SSH. AgentCore also caps a microVM at 2 vCPU; boat gives SSH, systemd, Docker and /dev/kvm up to 16 vCPU.
Runs for as long as the work takes
An AgentCore session stops after 8 hours and keeps only a 1 GB mount, so setup repeats; the fix is Instances on EC2 in your account. boat has no session cap on paid plans and saves the whole disk every minute.
Agents, desktop and links you can open
On both you build the agent harness yourself, neither has a full desktop, and AgentCore has no open ports. boat ships Claude Code and Codex, a 60fps desktop, HTTPS on 50 ports and a credentials proxy for any HTTPS API.
Use boat when your agents do real work on a machine for hours: installs, builds, Docker, emulators and a browser, with a disk that keeps everything, links you can open and the agent and its keys already set up. Compare it one to one: boat vs CodeSandbox SDK and boat vs AWS AgentCore.
Questions people ask
Is CodeSandbox SDK cheaper than AWS AgentCore?
No. AgentCore comes out lower in all five scenarios on this page, for example $26 against $193 a month for one coding agent on workdays. But AgentCore only fits the 1,000-job burst, because files outside its storage mount reset after a stop; CodeSandbox SDK fits three of the five.
Which is faster?
There is no comparable CPU measurement for either. Neither was part of the hpc-sandbox-benchmarks run, where boat did 26.69 runs per second at 4 vCPU / 8 GB.
Can CodeSandbox SDK or AWS AgentCore run Docker?
CodeSandbox SDK runs Docker with root and builds sandboxes from any Dockerfile. AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker works inside a session. boat runs Docker and systemd and exposes /dev/kvm.
How long can a session run on each?
CodeSandbox SDK has no hard cap and hibernates after an idle timeout of up to one day. An AgentCore microVM session lasts up to 8 hours, or up to 14 days on the Instances type. boat has no session cap on paid plans.
Is CodeSandbox SDK still maintained?
CodeSandbox is now part of Together AI. Together's docs call the CodeSandbox-based SDK deprecated and name together-sandbox as its successor, while self-serve sign-up still runs through CodeSandbox.
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 CodeSandbox SDK
- boat vs AWS AgentCore
- E2B vs CodeSandbox SDK
- Daytona vs CodeSandbox SDK
- Modal vs CodeSandbox SDK
- Vercel Sandbox vs CodeSandbox SDK
- Cloudflare Sandbox vs CodeSandbox SDK
- Blaxel vs CodeSandbox SDK
- Runloop vs CodeSandbox SDK
- Tensorlake vs CodeSandbox SDK
- Morph Cloud vs CodeSandbox SDK
- CodeSandbox SDK vs Northflank