Together Code Sandbox vs AWS AgentCore
Together Code Sandbox starts VMs from Docker-image snapshots that can save their memory, but Together has to turn it on for you. AWS AgentCore hosts agents in 2 vCPU microVM sessions inside your AWS account, with a managed Code Interpreter and Browser.
The companies and products
Together Code Sandbox
Together AI is a cloud for running and training AI models, and Code Sandbox is its product for running code in isolated VMs.
You build a snapshot from a Docker image or Dockerfile on Together's builder, then start sandboxes from it and run commands and file operations through the together-sandbox SDK or CLI. When a sandbox ends you can save its disk, and its memory too, as a new snapshot to start more sandboxes from. It is aimed at model-generated code, agent tool calls and reinforcement learning rollouts, and it must be enabled for your organization by Together. Together also sells Code Interpreter, a separate API that runs Python code in short sessions.
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. “65th cheapest of 367” means 64 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 | Together Code Sandbox: 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 Neither documents Docker or /dev/kvm inside a sandbox, and AgentCore stops microVM sessions after 8 hours; boat gives a coding agent a full machine with Docker and its whole disk kept. | 65th of 367, with limits $528 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 agent that lives all month outlasts AgentCore's 8-hour microVM sessions and Together's 60-minute Code Interpreter sessions; boat keeps the machine running with no session cap on paid plans. | 152nd of 366, with limits $1,095 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 billed only for CPU used, and it fits; Together's Code Interpreter runs only Python and bills per 60-minute session. | 326th of 345, with limits $2,190 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 Together makes every port public and AgentCore opens none, so neither gives your users a private link to their app; boat gives each sandbox token-protected HTTPS URLs on up to 50 ports. | 234th of 361, with limits $900 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 Together can save a sandbox with its memory and start many copies from it, which suits rollouts that branch from one warm state, but the VM product needs Together to enable it. | 315th of 360, with limits $21,900 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 | 258th of 364, with limits $450 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 | 251st of 377, with limits $180 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 A dev box needs SSH and a disk that keeps installed packages; neither Together nor AgentCore offers SSH, and AgentCore resets everything outside its storage mount after a stop. | 210th of 368, with limits $22 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 AgentCore Browser drives a browser and Together has no browser or desktop at all; boat streams a full Linux desktop at 60fps for agents that use other apps too. | 184th of 369, with limits $600 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 session replay, while on Together you install a headless browser in your own image; boat runs Chromium on a full desktop. | 301st of 367, with limits $900 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 | 219th of 346, with limits $180 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 | 124th of 338, with limits $3,600 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 | 167th of 360, with limits $150 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 | Together Code Sandbox | AWS AgentCore | boat |
|---|---|---|---|
| What it is | VM sandboxes started from Docker-image snapshots, plus a separate Python Code Interpreter API | 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 |
| Getting started | The VM SDK and CLI must be enabled for your organization by Together; Code Interpreter is self-serve | Self-serve in any AWS account | Sign up and start a sandbox from the API, CLI or dashboard |
| Isolation | A VM per sandbox on Together's infrastructure | 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 |
| Machine size | 0.1 to 16 cores, 1 to 8 GB of memory per core; disk size fixed | 2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances | 2 to 16 vCPU with 2 GB per vCPU, up to 16 vCPU / 32 GB on the $100 plan and above |
| Session length | VM sandboxes run until you end them or their time to live runs out; Code Interpreter sessions last 60 minutes | Up to 8 hours per lifecycle on microVMs, 15 idle minutes by default; up to 14 days on Instances | No cap on paid plans; you set the time to live |
| Saving state | End a sandbox with a snapshot of its disk, or disk and memory; a new sandbox resumes with its processes running | Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances; the rest resets | The whole disk, saved every minute and on stop; a stopped sandbox costs nothing |
| Fork | No live fork: the parent stops, then you start many sandboxes from its snapshot | No user snapshots or fork of a session | Fork a running sandbox with its disk; the original keeps running |
| Docker, root and /dev/kvm | Commands run as user 1000 by default, root on request; Docker inside and 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 |
| Reaching the sandbox | All ports public; preview URLs coming soon; an experimental inbound allowlist; no SSH | No open ports or SSH; sessions are reached only through AgentCore APIs with IAM or JWT | SSH, HTTPS URLs for up to 50 ports, token-protected by default, and raw TCP |
| Network controls | Experimental inbound allowlist by IP or token | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet, no provider-side allowlist |
| Browser and desktop | None; headless command and file access only | Managed Chromium with live view, session recording and replay, profiles and proxies; no full desktop | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Coding agents | Run your own agent through execs; a Harbor guide for agent evals | AWS's own managed harness built on Strands Agents, or your own agent code | Claude Code, Codex and more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | No credentials proxy documented | 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 in sandboxes; regions not published | NVIDIA G-series and Inferentia2 on Instances; 17 commercial AWS regions plus GovCloud | No GPUs; EU only (Germany, Finland, France) |
Every feature Battleships tracks (43)
| Feature | Together Code Sandbox | AWS AgentCore | boat |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Not published | 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 | No | No | Yes |
| Fork/clone | Yes | No | Yes |
| Live fork (no pause) | No | No | Yes |
| Memory fork | Yes | No | No |
| Custom image (Docker or snapshot) | Yes | Yes | Yes |
| ≥24 h sessions | Yes | No | Yes |
| Idle auto-stop | No | Yes | No |
| Wake on request | No | 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 | Yes | 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 | Yes | Yes | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Not published | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Yes | Yes | No |
| HIPAA | No | Yes | No |
| EU data residency | Not published | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Together Code Sandbox or AWS AgentCore: neither was part of the StarSling hpc-sandbox-benchmarks run. boat did 26.69 runs per second on its Node.js test at 4 vCPU / 8 GB, on dedicated AMD Ryzen 9 9950X hosts. An AgentCore microVM session stops at 2 vCPU, so a like-for-like test would have to use its Instances type.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Together Code Sandbox 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 | Together Code Sandbox, 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 | $5 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $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 | $22 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $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 | $264 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $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 | $900 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · 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 | $6,000 · Together pay-as-you-go (prepaid credits; Code Interpreter only) · with limits | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Together Code Sandbox: Together lists Code Sandbox at $0.0446 per vCPU-hour and $0.0149 per GiB-hour, but the VMs must be enabled for your organization, so the table prices Together with Code Interpreter: $0.03 per 60-minute session from prepaid credits. Code Interpreter runs only Python and keeps no disk, so it fits none of these scenarios.
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.
AWS AgentCore: Plans start at $20 a month, and the whole fee becomes usage credit. You pay per second while a sandbox runs, and a stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
The Together column is Code Interpreter, and its limits decide every row: sessions last 60 minutes, nothing is kept after a session, it runs only Python, and the machine size is not published. AgentCore's microVM sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU rows use Instances, where files outside the storage mount reset after a stop. AgentCore is the only one of the three that fits 1,000 short jobs at once, where boat's plans queue starts above 90 per minute.
| Scenario | Together Code Sandbox | 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 Together Code Sandbox when
you already run models on Together and want light sandboxes, from a tenth of a core, that you can save with their memory and branch from.
- Memory snapshots to branch from. Useful for rollouts and test variants: save a sandbox with its memory and start many copies with processes still running.
- Sandboxes next to your models. Handy if you already run inference or fine-tuning on Together: sandboxes and models share one account and API key.
- Very small and flexible machines. Good for many light jobs: sandboxes start at a tenth of a core, with 1 to 8 GB of memory per core.
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 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.
- 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.
Where boat fits
Both Together Code Sandbox and AgentCore treat the sandbox as a place to run commands, reached only through their SDKs or APIs. If your agents install packages, run Docker, build for hours and serve apps people open, boat gives each one a whole machine you can start today, with the agent and its keys already set up.
A whole machine with Docker and /dev/kvm
Neither Together nor AgentCore documents Docker or /dev/kvm inside a sandbox, so compose stacks, Android emulators and VM tests may not start. boat runs root, Docker, systemd and /dev/kvm on every machine, up to 16 vCPU / 32 GB.
Runs for hours and keeps its whole disk
AgentCore microVMs stop after 8 hours and keep only a 1 GB mount, and Together keeps state only in a snapshot taken when a sandbox ends. boat saves the whole disk every minute, has no session cap on paid plans, and forks a running sandbox.
Links you can open, a desktop and safe keys
Together makes every port public and AgentCore opens none, so you proxy traffic through your own code. boat serves token-protected HTTPS on 50 ports, streams a 60fps desktop, and keeps real API keys outside the sandbox in a credentials proxy.
Use boat when your agents do real work on a machine for hours: installs, builds, Docker, emulators, a browser and servers people open, with a disk that keeps everything. Compare it one to one: boat vs Together Code Sandbox and boat vs AWS AgentCore.
Questions people ask
Is Together Code Sandbox cheaper than AWS AgentCore?
The only self-serve Together price is Code Interpreter, which fits none of the scenarios. It looks cheaper for long agents, $264 against $1,286 a month for 50 agents, but costs more for many short sessions: $900 against $423 for sandboxes for your users, and $6,000 against $1,615 for 1,000 short jobs at once.
Which is faster, Together Code Sandbox or AgentCore?
Neither has a comparable CPU measurement, so there is no fair speed answer. boat did 26.69 runs per second on the StarSling Node.js test at 4 vCPU / 8 GB.
Can Together Code Sandbox or AgentCore run Docker?
Together builds sandboxes from Docker images, and AgentCore runs your arm64 container image as root, but neither documents Docker or /dev/kvm inside a sandbox. boat runs Docker, systemd and root on every machine and 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; Instances run up to 14 days. Together VM sandboxes run until you end them or their time to live runs out, and Code Interpreter sessions last 60 minutes. boat has no session cap on paid plans.
Do files survive when a sandbox stops?
On Together you save the disk, or disk and memory, as a snapshot when a sandbox ends. On AgentCore only a storage mount under /mnt, up to 1 GB and in preview, or EBS volumes on Instances survive. boat keeps the whole disk and saves it every minute.
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 Together Code Sandbox
- boat vs AWS AgentCore
- E2B vs Together Code Sandbox
- Daytona vs Together Code Sandbox
- Modal vs Together Code Sandbox
- Vercel Sandbox vs Together Code Sandbox
- Cloudflare Sandbox vs Together Code Sandbox
- Blaxel vs Together Code Sandbox
- Runloop vs Together Code Sandbox
- Tensorlake vs Together Code Sandbox
- Morph Cloud vs Together Code Sandbox
- CodeSandbox SDK vs Together Code Sandbox