Daytona vs AWS AgentCore
Daytona is a sandbox cloud: you create long-lived sandboxes through its API, as containers by default or as Linux VM, Windows or GPU classes. AWS AgentCore is an agent platform inside your AWS account, with 2 vCPU microVM sessions that stop after 8 hours and managed Code Interpreter and Browser tools.
The companies and products
Daytona
Daytona is a cloud for running AI-generated code: you create sandboxes from code through its API and SDKs.
By default a Daytona sandbox is a Linux container with its own namespaces and reserved vCPU, memory and disk. You can also pick a Linux VM class (pause, fork, memory snapshots, /dev/kvm), a Windows VM class, or a GPU class with Nvidia and AMD cards. It is built for teams that run agent code, code interpreters and evals through Python, TypeScript, Ruby, Go or Java SDKs.
- Founded
- 2023
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. “15th cheapest of 367” means 14 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 | Daytona: 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 Daytona fits a coding agent fully, while AgentCore is a compromise: a microVM session has 2 vCPU, stops after 8 hours and resets files outside its storage mount; boat gives the agent a full VM with Docker that keeps its whole disk. | 15th cheapest of 367 $4,111 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 | 24th cheapest of 366 $6,104 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 This is what AgentCore Code Interpreter is built for, and AWS AgentCore ranks 7th of 345 here; Daytona also fits fully, and boat's start limits make big bursts a compromise. | 25th cheapest of 345 $271 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 Neither fits fully: 300 sandboxes of 2 vCPU need 600 vCPU, more than Daytona's Tier 4 pool of 500, and AgentCore sessions have no open ports for users to open their app; boat gives each sandbox HTTPS URLs on up to 50 ports. | 154th of 361, with limits $2,000 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 | 130th of 360, with limits $8,261 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 | 189th of 364, with limits $2,000 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 AgentCore fits CI runs, while Daytona caps a sandbox at 4 vCPU by default so an 8 vCPU job needs a raised limit; boat allows 8 vCPU from the $20 plan. | 308th of 377, with limits $805 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 Both are a compromise for a 24/7 dev box, and AgentCore has no SSH and resets everything outside its storage mount after a stop; boat keeps the whole disk and gives you SSH. | 183rd of 368, with limits $245 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 Daytona fits with a VNC desktop and a computer-use API on Linux and Windows, while AgentCore Browser drives only a browser; boat streams a full Linux desktop at 60fps. | 26th cheapest of 369 $1,198 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, and AWS AgentCore ranks 4th of 367 here; boat runs Chromium on a full machine you control. | 93rd of 367, with limits $598 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 | 38th cheapest of 346 $404 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 | 202nd of 338, with limits $8,073 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 | 12th cheapest of 360 $2,000 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 Only Daytona fits of the three: it rents Nvidia and AMD GPUs by the hour, and boat has no GPUs. | 20th cheapest of 98 $1,190 a month | 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 | Daytona | AWS AgentCore | boat |
|---|---|---|---|
| Isolation | Container by default; Linux VM and Windows VM classes with their own kernel | Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment | Every sandbox is a full VM with its own kernel, on dedicated AMD Ryzen 9 9950X hosts |
| CPU speed (Node.js build-and-test, 4 vCPU / 8 GB) | 21.52 runs/s on the Linux VM class; the default container class reported no result | Not measured | 26.69 runs/s |
| Biggest sandbox | 4 vCPU / 8 GiB per sandbox by default, raisable per region | 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 cap; auto-stop can be turned off so a sandbox runs until you stop it | Up to 8 hours per microVM lifecycle, stopped after 15 idle minutes by default; up to 14 days on Instances | No cap on paid plans; you set the time to live |
| Files after a stop | The disk is kept and billed while stopped; archived containers are free | 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 |
| Pause, snapshots and fork | Linux VM and Windows classes pause, resume and fork with memory kept; containers cannot pause or fork | No user snapshots, pause or fork of a session | Snapshots every minute; fork a running sandbox with its disk; resume reboots from disk |
| Docker and /dev/kvm | Docker in all classes; /dev/kvm only on Linux VMs, with KVM turned on for your organization | Root inside the microVM with arm64 container images; Docker and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm on every machine |
| Reaching the sandbox | HTTPS preview URLs on any port, token-protected or public; SSH; no raw TCP or public IP | No open ports or SSH; sessions are reached only through AgentCore APIs with IAM or JWT | HTTPS URLs for up to 50 ports, token-protected; raw TCP; SSH; dedicated IPv6 or IPv4 |
| Network controls | Tier 1 and 2 reach only package registries, git hosts and AI APIs; Tier 3 and up get open internet plus per-sandbox domain or CIDR allowlists | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet on every plan; no provider-side allowlist |
| Desktop and browser | VNC desktop (xfce4) and a computer-use API on Linux and Windows | Managed Chromium with live view, session recording and replay, profiles and proxies; no full desktop | Full Linux desktop streamed at 60fps with Chromium, computer use and browser control, embeddable |
| Coding agents | Guides install agents and run them through process exec | AWS's managed harness built on Strands Agents, or your own agent code in any framework | Claude Code, Codex, OpenCode and more preinstalled, driven from outside with a prompt, steer and events API |
| Keeping keys out of the sandbox | Secrets proxy swaps placeholders in HTTPS request headers for allowed hosts | AgentCore Identity stores OAuth tokens and API keys and hands them to your agent code | AI credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out |
| GPUs and Windows | Nvidia and AMD GPUs from RTX 4090 to B300, on demand or preemptible; Windows VM sandboxes | NVIDIA G-series and Inferentia2 on the Instances type; no Windows | No GPUs; no Windows guests, Wine for Windows apps |
| Regions | US and EU, plus dedicated regions or your own machines | 17 commercial AWS regions plus GovCloud | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Daytona | AWS AgentCore | boat |
|---|---|---|---|
| Full VM (own kernel) | No | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Not published | No | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | Yes | Yes |
| SSH | Yes | 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) | 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 | Yes | 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 | Yes | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | Yes | No | Yes |
| Preinstalled agents | Yes | No | Yes |
| Agent harness API | No | No | Yes |
| MCP server | Yes | Yes | No |
| GPU | Yes | Yes | No |
| Windows | Yes | No | No |
| Arm64 | No | Yes | No |
| Self-hosting | No | No | No |
| BYOC | Yes | Yes | No |
| Open source | No | No | No |
| Scoped API keys | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | Yes | No | Yes |
| Audit logs | Yes | Yes | No |
| SSO | Yes | Yes | 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
In StarSling's public run of 2026-09-29 at 4 vCPU / 8 GB, boat did 26.69 Node.js build-and-test runs per second and Daytona's Linux VM class did 21.52. Daytona's default container class reported no result in that run. AgentCore was not measured, and its microVM sessions stop at 2 vCPU, so a like-for-like test would need the Instances type on EC2.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Daytona measured on: Linux VM sandbox (same rates; KVM / nested virt per-org feature). AWS AgentCore has 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 | Daytona, 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 | $56 · Tier 3 ($500 top-up) | $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 | $245 · Tier 3 ($500 top-up) | $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 | $2,682 · Tier 3 ($500 top-up) | $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 | $2,000 · Tier 4 ($2,000 top-up every 30 days) · 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 | $2,000 · Tier 4 ($2,000 top-up every 30 days) · with limits | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Daytona: Daytona bills per second for the vCPU, memory and disk you reserve, and keeps billing the disk while a sandbox is stopped. You pay from a prepaid wallet: open internet needs a $500 top-up (Tier 3), and the biggest pool needs $2,000 every 30 days (Tier 4).
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 EBS storage and data transfer billed on top.
AWS AgentCore: Plans start at $20 a month, and the whole fee is usage credit spent per second on running sandboxes. A stopped sandbox costs nothing and keeps its disk.
Limits in those scenarios
Daytona limits the total vCPU running at once, from 10 to 500 vCPU by tier, so 300 sandboxes for your users (600 vCPU) and 1,000 short jobs at once (2,000 vCPU) do not fit even Tier 4, and Tier 1 and 2 reach only an allowlist of services. AgentCore microVM sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU scenarios use the Instances type, where files outside the storage mount reset after a stop; only the 1,000-job burst fits there. boat has no session cap, but at 1,000 short jobs at once its $2000 plan queues starts above 90 per minute.
| Scenario | Daytona | 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 Daytona when
your agents need GPUs, Windows desktops or sandboxes that pause and fork with memory, and run for hours outside a big cloud account.
- GPUs and Windows desktops. Useful if agents test models or need Windows: Daytona rents GPUs by the hour and runs Windows VM sandboxes with computer use.
- Sandboxes that last and pause with memory. Daytona sandboxes have no session cap and keep their disk, and its VM classes pause and fork with memory kept.
- A desktop for computer use. For agents that use more than a browser, Daytona gives each sandbox a VNC desktop and a computer-use API.
Use AWS AgentCore when
your agents must stay inside your AWS account and VPC, 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 plus GovCloud.
- 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 session replay.
- Many sessions at once. Runtime allows 5,000 active sessions in us-east-1 and us-west-2, while Daytona's biggest tier caps running sandboxes at 500 vCPU.
Where boat fits
If your agents do real work for hours, like installs, builds, tests, Docker and emulators, look at boat. Every boat sandbox is a full VM with its own kernel and a disk saved every minute, it ran faster than Daytona's VM class in the same benchmark, and you drive coding agents inside it from outside. Daytona is still the pick for GPUs and Windows, and AgentCore for agents that must stay inside AWS.
A full VM with Docker and /dev/kvm
Daytona's default sandbox is a container on a shared kernel, and /dev/kvm needs its VM class with KVM turned on for your organization. AgentCore does not document Docker or /dev/kvm, and a session stops at 2 vCPU.
A disk that stays, with no session cap
AgentCore stops a microVM after 8 hours and resets everything outside a 1 GB mount; the workaround is Instances, which means running EC2 in your own account. Daytona keeps the disk but bills it while stopped.
Open the app and drive the agent
AgentCore sessions have no open ports, so a dev server has to be proxied through your own code. Daytona has preview URLs but no raw TCP, and you install and run each agent yourself as a process.
Use boat when your agents do real work on a machine for hours: installs, builds, tests, Docker and emulators on a full, faster VM with a disk that keeps everything and a URL you can open. Compare it one to one: boat vs Daytona and boat vs AWS AgentCore.
Questions people ask
Is Daytona cheaper than AWS AgentCore?
In our table AgentCore comes out lower: one agent all month is $107 against $245 on Daytona, and 50 agents in parallel are $1,286 against $2,682. But those 4 vCPU prices use AgentCore's Instances type, where files reset outside the storage mount and the disk price is unknown, so only the 1,000 short jobs scenario fits there. boat comes to $26 and $317 for the same two scenarios.
Which is faster, Daytona or AgentCore?
Only Daytona was measured: its Linux VM class did 21.52 runs per second at 4 vCPU / 8 GB, and boat did 26.69 in the same run. AgentCore was not in the benchmark, and its microVM sessions stop at 2 vCPU.
Can Daytona or AgentCore run Docker?
Daytona runs Docker in all classes, and /dev/kvm only on its Linux VM class once KVM is turned on for your organization. AgentCore runs your arm64 container image as root, but its docs do not say Docker or /dev/kvm work inside a session. boat runs Docker and exposes /dev/kvm on every machine.
How long can a session run?
A Daytona sandbox has no session cap if you turn off auto-stop. An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default, or up to 14 days on the Instances type. boat has no session cap on paid plans.
Do files survive a stop?
On Daytona the disk is kept and billed while the sandbox is stopped. On AgentCore only a storage mount under /mnt, up to 1 GB and in preview, or EBS volumes on Instances survive; the rest resets. boat keeps the whole disk, saves it every minute, and a stopped sandbox costs nothing.
Where can each one run?
Daytona runs in the US and EU, plus dedicated regions and your own machines. AgentCore runs in 17 commercial AWS regions plus GovCloud. boat runs only in the EU (Germany, Finland and France), with EU data residency.
Try boat
Install the CLI, then run boat new.
7-day free trial