Freestyle vs AWS AgentCore
Freestyle gives each agent a full Linux VM with Docker and systemd that can pause with its memory, fork and wake on the next request. AgentCore is the part of AWS that hosts agent code in short microVM sessions and adds a managed code interpreter and browser, all inside your AWS account.
The companies and products
Freestyle
Freestyle sells full Linux virtual machines for AI agents, built for long running, complex tasks.
Each Freestyle VM is a KVM virtual machine with its own kernel, booted from an Ubuntu base snapshot with systemd, Docker and coding agent CLIs preinstalled. VMs can be paused with their memory, snapshotted while running, forked and woken by the next request, and every VM starts behind a default-deny firewall. It is built for teams that give each agent or each user its own machine, driven from a TypeScript SDK, a CLI or an API.
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. “40th cheapest of 345” means 39 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 | Freestyle: price rank | AWS AgentCore: price rank | bochka: price rank |
|---|---|---|---|
| Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month Freestyle gives a coding agent a full VM with Docker that keeps its disk, while an AgentCore microVM session stops at 2 vCPU and 8 hours; bochka adds CPUs that did 2.8 times Freestyle's benchmark work. | 241st of 367, with limits $3,311 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 | 263rd of 366, with limits $4,195 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 AgentCore's home ground: Code Interpreter runs short code in a managed session and bills only the CPU used, and Freestyle fits too with VMs that pause and wake. | 40th cheapest of 345 $482 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 Freestyle wakes a paused user VM on its next request and serves it on HTTPS, while AgentCore sessions have no open ports; bochka gives each user HTTPS URLs on up to 50 ports. | 16th cheapest of 361 $1,358 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 Freestyle can snapshot a running VM with its memory and boot copies from it; AgentCore has no snapshot or fork, and bochka forks a running sandbox with its disk. | 107th of 360, with limits $6,600 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 | 53rd cheapest of 364 $1,046 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 Freestyle's docs send CPU-heavy jobs like kernel builds elsewhere, and AgentCore does not document /dev/kvm; bochka exposes /dev/kvm for Android and VM builds. | 168th of 377, with limits $625 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: Freestyle and bochka have both, while AgentCore has no SSH and resets everything outside its storage mount. | 98th cheapest of 368 $151 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, not a whole desktop, and on Freestyle you install the desktop and VNC yourself; bochka streams a full Linux desktop at 60fps. | 234th of 369, with limits $940 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, Freestyle has a guide to install Chromium yourself, and bochka has Chromium ready in every sandbox. | 257th of 367, with limits $482 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 | 278th of 346, with limits $482 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 | 183rd of 338, with limits $6,560 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 | 272nd of 360, with limits $482 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 | Freestyle | AWS AgentCore | bochka |
|---|---|---|---|
| What it is | A sandbox platform: full Linux VMs for agents, driven from an SDK, CLI or 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 |
| Isolation | Full KVM VM 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 |
| CPU benchmark (4 vCPU / 8 GB) | 9.64 runs/s | Not measured | 26.69 runs/s |
| Biggest machine | Up to 32 vCPU / 64 GiB on Pro, 64 / 128 with custom limits | 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 provider cap; a VM runs until you pause it or set a timeout | 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 |
| What survives a stop | The whole disk; a pause also keeps memory, so the same processes resume | 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 |
| Snapshots, fork and wake | Memory snapshots, clone a running VM, wake a paused VM on the next request | No user snapshots or fork of a session | Automatic snapshots every minute; fork a running sandbox with its disk |
| Docker, systemd and /dev/kvm | Yes; systemd is pid 1, Docker runs from boot, full KVM support | Root inside the microVM; arm64 container images; Docker and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Inbound access | HTTPS on free style.dev names or your own domain, forward auth, other public protocols | 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 by default; raw TCP; SSH |
| Network controls | Default-deny firewall with allow rules by IP, VM, VPC or exact domain | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet, no provider-side allowlist |
| Browser and desktop | Guides to install GNOME or Xvfb, VNC and Chromium yourself | Managed Chromium with live view, session recording and replay; no full desktop | Linux desktop streamed at 60fps, with Chromium and computer use built in |
| Coding agents | claude, codex, opencode and openclaw preinstalled, driven through exec or a terminal | AWS's own managed harness built on Strands Agents, or your own agent code | Seven agents preinstalled, with a prompt, steer and events API |
| GPUs | Private GPU sandboxes on Enterprise | NVIDIA G-series and Inferentia2 on the Instances type | No |
| Regions | Not listed; the docs name a San Jose, US data center | 17 commercial AWS regions plus GovCloud | EU only (Germany, Finland, France), zero data retention |
Every feature Battleships tracks (43)
| Feature | Freestyle | AWS AgentCore | bochka |
|---|---|---|---|
| Full VM (own kernel) | Yes | Yes | Yes |
| Docker inside | Yes | Not published | Yes |
| Nested virtualization | Yes | No | Yes |
| Root | Yes | Yes | Yes |
| Systemd | Yes | No | Yes |
| Desktop GUI | No | No | Yes |
| Browser | No | Yes | Yes |
| Computer-use API | No | 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) | 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 | Yes | 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 | No | Yes | No |
| GPU | Yes | 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 | Yes | Not published | Yes |
| Spend limits | Not published | Yes | Yes |
| Usage per sandbox (API) | No | No | Yes |
| Audit logs | Yes | Yes | No |
| SSO | Yes | Yes | No |
| SOC 2 | Not published | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | No | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
On the hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB, bochka did 26.69 runs per second and Freestyle did 9.64, so bochka finished about 2.8 times as much CPU work. AgentCore has no comparable measurement: it was not part of that run, and its microVM sessions stop at 2 vCPU. Freestyle advertises VM starts in about 65 ms, which this test does not measure.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. 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 | Freestyle, a month | AWS AgentCore, a month | bochka, 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 | $27 · Free | $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 | $159 · Free | $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 | $2,139 · Pro | $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 | $581 · Pro | $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 | $1,305 · Pro · with limits | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Freestyle: Freestyle bills per second for the vCPU, RAM and disk allocated to a VM, busy or idle, after monthly allowances of 200 vCPU-hours, 400 GiB-hours of RAM and 60,000 GiB-hours of storage. On Free those allowances are hard stops; Hobby and Pro set a $50 or $500 monthly minimum that counts as usage, and a paused VM bills only for storage.
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 by AWS 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's serverless 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 and a session ends at 14 days, which rules out an agent that never stops. Freestyle fits every agent scenario, but on Free its monthly allowances are hard stops, and Pro allows 400 concurrent VMs, so it cannot run 1,000 short jobs at once, which AgentCore can. bochka has no session cap, but its start limits are lower: the $2,000 plan queues starts above 90 a minute.
| Scenario | Freestyle | AWS AgentCore | bochka |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops | None that bite |
| None that bite |
| 50 agents in parallel | None that bite |
| None that bite |
| Sandboxes for your users | None that bite |
| None that bite |
| 1,000 short jobs at once |
|
|
|
Which one should you use?
Use Freestyle when
your agents need a full VM that keeps its disk, pauses with its memory and wakes on the next request, or more than 16 vCPU in one machine.
- Memory pause, live fork and wake on request. For VMs that sleep between requests: they resume the same processes, clone while running, and wake on the next incoming traffic.
- A full VM with no session cap. Each agent gets a KVM VM with Docker and systemd that keeps its whole disk and runs as long as you let it.
- Big machines and a strict firewall. Pro VMs go up to 32 vCPU / 64 GiB, and every VM starts behind a default-deny firewall you open rule by rule.
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 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 bochka fits
Look at bochka when your agents do hours of real work on a machine: installs, builds, tests, Docker, emulators, a desktop and a browser. Freestyle gives you the full VM but slower CPUs and a desktop you build yourself, and AgentCore gives you short 2 vCPU sessions unless you run EC2 in your own account.
Fast CPUs on a whole machine
Freestyle did 9.64 runs per second on the CPU benchmark against bochka's 26.69, so every build waits almost three times as long. AgentCore microVMs stop at 2 vCPU; more means the Instances type on EC2 in your account.
A desktop and a browser, ready
bochka streams a Linux desktop at 60fps with Chromium and computer use built in. On Freestyle you install and maintain GNOME, VNC and Chromium in your own snapshot, and AgentCore Browser drives a browser only, not other desktop apps.
Agents you drive from outside
bochka preinstalls seven coding agents with an API to prompt, steer and follow them, and a credentials proxy that switches to another account when credits run out. Freestyle leaves you parsing exec output, and AgentCore Identity hands keys to your agent code.
Use bochka when your agents do real work on a machine for hours: builds, tests, Docker, emulators, a desktop and a browser, on fast CPUs, with an API to drive the agents inside from outside. Compare it one to one: bochka vs Freestyle and bochka vs AWS AgentCore.
Questions people ask
Is Freestyle cheaper than AWS AgentCore?
AgentCore is lower in four of the five scenarios on this page, but it does not fit any of those four: 4 vCPU needs the Instances type and files reset outside the storage mount. For 1,000 short jobs at once AgentCore fits at $1,615 a month, while Freestyle Pro caps at 400 concurrent VMs. For one agent running all month it is $159 on Freestyle, $107 on AgentCore (which does not fit) and $26 on bochka.
Which is faster, Freestyle or AgentCore?
Freestyle did 9.64 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB, and bochka did 26.69. AgentCore was not measured, and its microVM sessions stop at 2 vCPU.
Can Freestyle or AgentCore run Docker?
Freestyle can: systemd is pid 1, Docker runs from boot and KVM works inside the VM. AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker or /dev/kvm work inside a session. bochka runs Docker and exposes /dev/kvm.
How long can a session run?
Freestyle sets no cap, so a VM runs and bills until you pause it or set a timeout. An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default, or up to 14 days on Instances. bochka has no session cap on paid plans.
Do files survive when a session stops?
On Freestyle the whole disk survives, and a pause keeps memory too. On AgentCore only a storage mount under /mnt, up to 1 GB and in preview, or an EBS volume on Instances survives. bochka keeps the whole disk and saves it every minute.
Is AgentCore a sandbox like Freestyle?
Partly. AgentCore is an AWS platform for hosting agents, and its Runtime sessions and Code Interpreter are sandboxes you reach through AWS APIs, with no SSH or open ports. Freestyle and bochka give each agent a full Linux machine you can SSH into and serve apps from.
Try bochka
Install the CLI, then run bochka new.
Product preview