AWS AgentCore vs Upstash Box

AWS AgentCore is the part of AWS that hosts agents, with microVM sessions of up to 8 hours plus managed Code Interpreter and Browser tools. Upstash Box gives each agent a light container with a coding agent built in that pauses when idle, keeps its files and wakes on the next request.

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 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.

Isolation: Runtime: a dedicated microVM per session; Code Interpreter and Browser run in a containerized environment
Session size: Runtime and Code Interpreter up to 2 vCPU / 8 GB, Browser 1 vCPU / 4 GB, not adjustable
Session length: Up to 8 hours per lifecycle on microVMs, 15 minutes idle by default; up to 14 days on Instances
Compute types: Serverless microVMs (arm64 Linux containers) or Instances: AWS-managed EC2 in your account, x86_64 or arm64, GPUs available
Regions: 17 commercial AWS regions across the US, EU, Asia Pacific, Canada and South America, plus GovCloud
Compliance: Listed as a HIPAA eligible AWS service

Upstash Box

Upstash Box is a cloud computer for AI agents from Upstash, the company known for serverless Redis, Vector and QStash.

Each box is a Docker container with its own filesystem, shell, git and an optional coding agent such as Claude Code, Codex or OpenCode, which you drive from TypeScript or Python SDKs. A box pauses when it sits idle, keeps its files, and you pay for the CPU it actually uses. Upstash built it to run its own Context7 service and opened it to everyone in March 2026.

Isolation: One Docker container per box, with its own filesystem, process tree and network stack
Region: AWS us-east-1 only; more regions planned
Machine sizes: Small 2 vCPU / 4 GB / 5 GB disk, Medium 4 vCPU / 8 GB / 10 GB, Large 8 vCPU / 16 GB / 20 GB
Billing: Per active CPU hour by size, RAM not billed, storage per GB-month; keep-alive boxes at a flat monthly price
Concurrency: 10 boxes on Free, 1,000 on Pay as You Go, raised on request
Compliance: Upstash's trust center lists SOC 2 Type II, GDPR, HIPAA and DPF for the company

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. “7th cheapest of 345” means 6 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	AWS AgentCore: price rank	Upstash Box: price rank	bochka: price rank
Software factory 100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month A coding agent that runs databases in Docker fits neither well: AgentCore stops at 2 vCPU and 8 hours per microVM session, and an Upstash box is itself a container, while bochka gives it a full machine with Docker.	100th of 367, with limits $888 a month	61st of 367, with limits $464 a month	3rd cheapest of 367 $634 a month
Always-on AI employees 50 machines 24/7 · 2 vCPU / 4 GB An assistant that stays on all month outlasts AgentCore's 8-hour microVM lifecycle and needs the Instances type on EC2, while an Upstash keep-alive box stays on for a flat price and bochka simply keeps running.	64th of 366, with limits $1,300 a month	103rd of 366, with limits $475 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 Both fit short code runs well: AgentCore Code Interpreter and a standard Upstash box each bill only the CPU actually used.	7th cheapest of 345 $114 a month	10th cheapest of 345 $119 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 AgentCore sessions have no open ports, so your users cannot open the app their sandbox runs; an Upstash box gets an HTTPS URL that wakes it, and bochka gives each user a full VM with HTTPS on up to 50 ports.	210th of 361, with limits $506 a month	2nd cheapest of 361 $222 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	125th of 360, with limits $8,075 a month	352nd of 360, with limits $8,068 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	33rd cheapest of 364 $650 a month	52nd cheapest of 364 $1,011 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 CI jobs that build containers or Android apps need Docker and /dev/kvm, which neither AgentCore nor Upstash documents and bochka exposes in every sandbox.	52nd cheapest of 377 $399 a month	120th cheapest of 377 $1,520 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; Upstash gives a keep-alive box with SSH through a gateway, while AgentCore has no SSH and resets files outside its storage mount.	228th of 368, with limits $52 a month	10th cheapest of 368 $20 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 AgentCore nor Upstash offers a full desktop, only a browser, while bochka streams a full Linux desktop at 60fps for agents that use other apps too.	104th of 369, with limits $202 a month	73rd of 369, with limits $76 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, Upstash ships a headless Chromium with AI page actions, and bochka runs Chromium on a desktop the agent can see.	4th cheapest of 367 $144 a month	49th of 367, with limits $38 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	27th cheapest of 346 $287 a month	37th cheapest of 346 $400 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	165th of 338, with limits $5,458 a month	200th of 338, with limits $8,000 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	62nd of 360, with limits $294 a month	225th of 360, with limits $259 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	AWS AgentCore	Upstash Box	bochka
Isolation	Firecracker microVM per Runtime session; Code Interpreter and Browser in a containerized environment	Docker container per box on AWS	Full VM with its own kernel on dedicated AMD Ryzen 9 9950X hosts
Biggest machine	2 vCPU / 8 GB per microVM session, not adjustable; bigger EC2 types only on Instances	Large: 8 vCPU / 16 GB	Up to 16 vCPU / 32 GB on the $100 plan and above
Session length	Up to 8 hours per lifecycle on microVMs, stopped after 15 idle minutes by default; up to 14 days on Instances	No maximum documented; a standard box pauses when idle and resumes later, a keep-alive box stays on	No cap on paid plans; you set the time to live
What survives a stop	Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances; the rest resets	The box keeps its files when paused, on a 5, 10 or 20 GB disk by size; storage bills while paused	The whole disk, 50 GB at the default size, saved every minute and on stop; a stopped sandbox costs nothing
Snapshots and fork	No user snapshots or fork of a session	Snapshot a running box and start many new boxes from it	Automatic snapshots every minute; fork a running sandbox with its disk
Docker, systemd and /dev/kvm	Root inside the microVM; arm64 container images; Docker and /dev/kvm not documented	No Docker inside; the box is itself a Docker container, with no VM support documented	Root, Docker, systemd and /dev/kvm for Android emulators and VMs
Inbound access	No open ports or SSH; sessions are reached only through AgentCore APIs with IAM or JWT	HTTPS URL per port, public unless you add a token or basic auth; SSH through a gateway; no raw TCP	HTTPS URLs for up to 50 ports, token-protected by default; raw TCP; SSH
Wake on request	The next call after a stop starts a fresh microVM	A request to a public URL resumes a paused box and waits for the app	No; a stopped sandbox is started by API
Network controls	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP	Allow all, deny all, or allow and deny by domain and CIDR, changeable on a running box	Open internet, no provider-side allowlist
Browser and desktop	Managed Chromium with live view, session recording and replay, profiles and proxies; no full desktop	Managed headless Chromium with AI page actions and CDP; no desktop	Full Linux desktop streamed at 60fps, with Chromium and computer use
Coding agents	AWS's own managed harness built on Strands Agents, or your own agent code in any framework	Claude Code, Codex and OpenCode built in, with run and stream APIs, webhooks and scheduled prompts	Claude Code, Codex and five more preinstalled, 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	Host proxy injects headers into outbound HTTPS on port 443; set when the box is created	Credentials proxy for model providers and any HTTPS API; switch a credential to another account when credits run out
GPUs	NVIDIA G-series and Inferentia2 on the Instances type	No	No
Regions	17 commercial AWS regions plus GovCloud	US only (AWS us-east-1)	EU only (Germany, Finland, France)

Every feature Battleships tracks (43)

Feature	AWS AgentCore	Upstash Box	bochka
Full VM (own kernel)	Yes	No	Yes
Docker inside	Not published	No	Yes
Nested virtualization	No	No	Yes
Root	Yes	Not published	Yes
Systemd	No	Not published	Yes
Desktop GUI	No	No	Yes
Browser	Yes	Yes	Yes
Computer-use API	Yes	No	Yes
SSH	No	Yes	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	No	Yes	Yes
Automatic snapshots	No	No	Yes
Fork/clone	No	Yes	Yes
Live fork (no pause)	No	Yes	Yes
Memory fork	No	No	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	No	Yes	Yes
Idle auto-stop	Yes	Yes	No
Wake on request	Yes	Yes	No
HTTPS preview URLs	No	Yes	Yes
Raw TCP inbound	No	No	Yes
Public IPv4	No	No	No
Egress allowlist	Yes	Yes	No
Secret proxy	No	Yes	Yes
Secret proxy for any API	No	Yes	Yes
Preinstalled agents	No	Yes	Yes
Agent harness API	No	Yes	Yes
MCP server	Yes	Yes	No
GPU	Yes	No	No
Windows	No	No	No
Arm64	Yes	Yes	No
Self-hosting	No	No	No
BYOC	Yes	No	No
Open source	No	No	No
Scoped API keys	Not published	Not published	Yes
Spend limits	Yes	Not published	Yes
Usage per sandbox (API)	No	Yes	Yes
Audit logs	Yes	Not published	No
SSO	Yes	No	No
SOC 2	Yes	Yes	No
HIPAA	Yes	No	No
EU data residency	Yes	No	Yes
Zero data retention	Not published	Not published	Yes

Performance

AWS AgentCoreNot measured

Upstash BoxNot measured

bochka26.69 runs/s

There is no comparable measurement for either: neither AWS AgentCore nor Upstash Box was part of the hpc-sandbox-benchmarks CPU run. bochka did 26.69 runs per second on that Node.js build-and-test 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. AWS AgentCore and Upstash Box 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	AWS AgentCore, a month	Upstash Box, 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	$26 · Pay-as-you-go (Instances) · with limits	$21 · 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	$21 · Pay as You Go	$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	$900 · Pay as You Go · 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	$423 · Pay-as-you-go · with limits	$306 · 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)	$1,822 · Pay as You Go	$2,000 · $2000/mo · with limits

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.

Upstash Box: A standard box is billed for the CPU it actually uses, at $0.10, $0.20 or $0.40 per active CPU hour for Small, Medium and Large, plus $0.10 per GB-month of storage, and RAM is free. A keep-alive box costs a flat $8, $16 or $32 a month whether it is busy or not.

Upstash Box: 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 microVM sessions stop at 2 vCPU / 8 GB and 8 hours, so the 4 vCPU scenarios use the Instances type, capped at 14 days, and files outside the storage mount reset after a stop; that is why AgentCore fits only the 1,000 short jobs scenario here. Upstash has no Docker inside a box, so the 50-agent scenario does not fit there, and its egress price is not published. Both handle 1,000 short jobs at once, where bochka's plans queue starts above 90 per minute.

Scenario	AWS AgentCore	Upstash Box	bochka
One coding agent, workdays	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	flat pool: the tier is billed whether used or not egress price not published	None that bite
One agent that never stops	Pay-as-you-go (Instances): sessions capped at 336 h files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	flat pool: the tier is billed whether used or not egress price not published	None that bite
50 agents in parallel	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	missing Docker inside flat pool: the tier is billed whether used or not egress price not published	None that bite
Sandboxes for your users	different kind of product: code interpreter	egress price not published	None that bite
1,000 short jobs at once	disk beyond 0 GiB: price unknown	egress price not published	max 2,400 starts/day (needs ~6,667) max 600 starts/hour (needs ~1,000) bursts above 90 starts/min are queued (a burst of 333 takes ~4 min to start)

Which one should you use?

Use AWS AgentCore when

your agents must stay inside your AWS account and VPC, need a GPU or a region outside the US, 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.
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.
Managed browser with replay. For browser tasks, AgentCore Browser gives a managed Chromium with live view, session recording and replay, profiles and proxies.

Use Upstash Box when

your agents mostly wait, should wake on an incoming request, need a coding agent ready to go, and can run in a light container in the US.

Idle costs no CPU, and a request wakes the box. Good for agents that wait a lot: RAM is free, idle CPU costs nothing, and a request to its URL wakes it.
Coding agents built in. Claude Code, Codex and OpenCode come built in, with stream APIs, webhooks and scheduled prompts for teams that want them ready.
Outbound rules by domain. Useful when an agent may only reach a short list of domains or IP ranges, changeable on a running box.

Where bochka fits

If your agents do real work on a machine for hours, with installs, builds, Docker and a browser, both AgentCore and Upstash Box get in the way: one with short, small sessions that forget their files, the other with a container that cannot run Docker. bochka gives each agent a full Linux VM that keeps its whole disk and runs as long as the work takes.

A whole machine with Docker and /dev/kvm

AgentCore microVMs stop at 2 vCPU and do not document Docker or /dev/kvm, and an Upstash box is itself a container. So 50 agents with Docker fit neither; AgentCore's way out is running EC2 Instances in your account.

A disk that keeps everything

On AgentCore only a 1 GB storage mount survives a stop, so installed packages reset each time. Upstash keeps files but caps the disk at 20 GB. bochka saves a 50 GB disk every minute and can fork a running sandbox.

A desktop and a URL you can open

AgentCore sessions have no open ports, so you proxy previews through your own code, and both offer only a browser, no desktop. bochka streams a 60fps Linux desktop and serves HTTPS on up to 50 ports plus raw TCP.

Use bochka when your agents need a real machine for hours: Docker, emulators, a desktop, a big disk that keeps everything and a URL you can open. Compare it one to one: bochka vs AWS AgentCore and bochka vs Upstash Box.

Questions people ask

Is AWS AgentCore cheaper than Upstash Box?

In four of the five scenarios on this page, Upstash Box costs less, for example $21 a month against $107 for one agent that never stops. AgentCore costs less for 1,000 short jobs at once: $1,615 against $1,822 a month.

Which is faster, AWS AgentCore or Upstash Box?

There is no comparable measurement: neither was part of the hpc-sandbox-benchmarks CPU run. bochka did 26.69 runs per second on that test at 4 vCPU / 8 GB.

Can AWS AgentCore or Upstash Box run Docker?

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. An Upstash box is itself a Docker container and does not offer Docker inside. bochka runs Docker and exposes /dev/kvm in every sandbox.

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. Upstash documents no maximum: a standard box pauses when idle and resumes later with its files, and a keep-alive box stays on. bochka has no session cap on paid plans.

Do AWS AgentCore and Upstash Box have a desktop for computer use?

Neither has a full desktop. AgentCore Browser is a managed Chromium with live view and replay, and Upstash gives a headless Chromium with AI page actions and CDP. bochka streams a full Linux desktop at 60fps with computer-use tools.

Where do AWS AgentCore and Upstash Box run?

AgentCore runs in 17 commercial AWS regions plus GovCloud. Upstash Box runs only in AWS us-east-1, with more regions planned. bochka runs in the EU, in Germany, Finland and France.

Try bochka

Install the CLI, then run bochka new.

Product preview