GitHub Codespaces vs AWS AgentCore

GitHub Codespaces is a cloud dev environment for people working on a GitHub repository: a dev container on its own VM that stops after 12 hours at most. AWS AgentCore is an AWS platform that hosts agent code in short microVM sessions of up to 2 vCPU and 8 hours, with managed Code Interpreter and Browser tools.

The companies and products

GitHub Codespaces

GitHub Codespaces is GitHub's cloud development environment: a ready-to-code Linux machine for a repository, opened in the browser, VS Code or the GitHub CLI.

Codespaces is a different kind of product from bochka: a dev environment for people working on a GitHub repository, not a sandbox API for agents. Each codespace is a Docker container built from the repo's dev container config, running on its own newly built VM on Azure, with 2 to 32 cores. It is built for developers and teams who want every contributor to start from the same setup, with prebuilds, port forwarding and GitHub billing.

Isolation: A Docker container on its own newly built VM, with its own virtual network
Operating system: Linux only; Windows and macOS are not supported for the remote container
Machine sizes: 2, 4, 8, 16 or 32 cores, with 4 GB of memory per core
Lifetime: Stops after 30 idle minutes by default (5 to 240), and after 12 hours at most even while in use
Regions: US East, US West, Europe West and Southeast Asia
Free usage: Personal Free accounts get 120 core-hours and 15 GB-month a month, Pro 180 and 20; organizations get no free quota
Compliance: GitHub Enterprise Cloud lists SOC 1, SOC 2 and SOC 3 reports and ISO 27001

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

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. “274th cheapest of 367” means 273 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	GitHub Codespaces: 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 Codespaces gives an agent Docker in a dev container but stops at 12 hours, AgentCore stops microVM sessions at 8 hours and 2 vCPU, and bochka gives a full VM with no session cap on paid plans.	274th of 367, with limits $4,618 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 both: Codespaces needs a restart every 12 hours and AgentCore needs the Instances type on EC2, while a bochka sandbox keeps running.	309th of 366, with limits $6,970 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 CPU actually used, while each codespace builds a dev container on a new VM.	288th of 345, with limits $619 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 GitHub does not publish how many codespaces can run at once and AgentCore sessions have no open ports, while bochka gives each user sandbox HTTPS URLs on up to 50 ports.	281st of 361, with limits $1,964 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	282nd of 360, with limits $9,489 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	295th of 364, with limits $1,519 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 Neither Codespaces nor AgentCore can fork a warm machine or documents /dev/kvm; bochka forks a running sandbox and exposes /dev/kvm for Android and VM builds.	314th of 377, with limits $909 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 Codespaces is a polished VS Code box per repo that stops after 12 hours; AgentCore has no SSH and resets files outside its storage mount; bochka keeps running and keeps its disk.	130th of 368, with limits $270 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 Codespaces has no graphical desktop and AgentCore Browser drives only a browser, while bochka streams a full Linux desktop at 60fps.	267th of 369, with limits $1,367 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, Codespaces has no browser tool, and bochka runs Chromium on a full machine you control.	275th of 367, with limits $678 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	310th of 346, with limits $922 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	280th of 338, with limits $18,637 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	267th of 360, with limits $445 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	GitHub Codespaces	AWS AgentCore	bochka
What it is	A cloud dev environment for a GitHub repository, opened in VS Code, the browser or the GitHub CLI	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, driven from code
Isolation	A Docker container on its own newly built VM, with its own virtual network	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	2, 4, 8, 16 or 32 cores, with 4 GB of memory per core	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
How long it runs	Stops after 30 idle minutes by default and after 12 hours at most, even while in use	Up to 8 hours per microVM lifecycle, 15 idle minutes by default; up to 14 days on Instances	Runs until you stop it; no session cap on paid plans
Files after a stop	Saved files are kept and storage is billed; stopped codespaces are deleted after 30 days by default	Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances; the rest resets	The whole disk, snapshotted every minute and on stop; a stopped sandbox costs nothing
Fork and snapshots	No copy or snapshot endpoint; new codespaces start from a repo, branch, pull request or prebuild	No user snapshots or fork of a session	Fork a running sandbox with its disk; named snapshots as templates
Docker and /dev/kvm	Docker and sudo inside the dev container; /dev/kvm not documented	Root inside the microVM with arm64 container images; Docker and /dev/kvm not documented	Root, Docker, systemd and /dev/kvm on every machine
Reaching it	A URL per forwarded port, private, organization or public; SSH and CLI tunnels; no 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
Browser and desktop	VS Code in the browser, JupyterLab and a terminal; no graphical desktop	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	GitHub Copilot as a VS Code extension; other agents you install yourself	AWS's managed harness built on Strands Agents, or your own agent code in any framework	Claude Code, Codex, OpenCode and more preinstalled, with a prompt, steer and events API
Keeping keys out of the sandbox	Secrets are copied into the codespace 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
Network controls	Open internet; GitHub says there is no way to restrict it	VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP	Open internet, no provider-side allowlist
GPUs	No GPU machine types	NVIDIA G-series and Inferentia2 on the Instances type	No
Regions	US East, US West, Europe West and Southeast Asia	17 commercial AWS regions plus GovCloud	EU only: Germany, Finland, France

Every feature Battleships tracks (43)

Feature	GitHub Codespaces	AWS AgentCore	bochka
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	Yes	No	Yes
Persistent disk	Yes	Yes	Yes
Pause/resume	Yes	No	Yes
Automatic snapshots	No	No	Yes
Fork/clone	No	No	Yes
Live fork (no pause)	No	No	Yes
Memory fork	No	No	No
Custom image (Docker or snapshot)	Yes	Yes	Yes
≥24 h sessions	No	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	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	Yes	Yes	Yes
Usage per sandbox (API)	No	No	Yes
Audit logs	Yes	Yes	No
SSO	Yes	Yes	No
SOC 2	Yes	Yes	No
HIPAA	No	Yes	No
EU data residency	Yes	Yes	Yes
Zero data retention	Not published	Not published	Yes

Performance

GitHub CodespacesNot measured

AWS AgentCoreNot measured

bochka26.69 runs/s

There is no comparable measurement for GitHub Codespaces or AWS AgentCore: neither was in the public benchmark runs we use. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB in StarSling's run of 2026-09-29, 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. GitHub Codespaces 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	GitHub Codespaces, 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	$51 · Personal account: GitHub 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	$270 · Personal account: GitHub Free · 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	$3,019 · Personal account: GitHub Free	$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	$850 · Personal account: GitHub Free · 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	$1,889 · Personal account: GitHub Free · with limits	$1,615 · Pay-as-you-go (Instances)	$2,000 · $2000/mo · with limits

GitHub Codespaces: Codespaces bills $0.09 per core-hour while a codespace is active, plus $0.07 per GB-month for storage while it exists, stopped too. There is no 4-core 8 GB machine, so 4 vCPU jobs are priced on the 4-core 16 GB one; personal accounts get a free monthly quota and organizations do not.

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 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

Codespaces stops every codespace after 12 hours, so it does not fit the always-on scenario, and GitHub does not publish how many can run at once, so 300 user sandboxes and 1,000 short jobs show as not confirmed. AgentCore fits only the 1,000-job burst: elsewhere files outside the storage mount reset after a stop, Instances sessions end at 14 days, and the user-sandbox scenario is a different kind of product. bochka fits every scenario but the burst, where its plans queue starts above 90 per minute.

Scenario	GitHub Codespaces	AWS AgentCore	bochka
One coding agent, workdays	None that bite	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	None that bite
One agent that never stops	Personal account: GitHub Free: sessions capped at 12 h	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	None that bite
50 agents in parallel	how many machines can run at once: limit not published, probably fine at 50 (the typical published limit is 50)	files survive a stop only in the session storage mount: packages installed elsewhere reset disk beyond 0 GiB: price unknown	None that bite
Sandboxes for your users	not confirmed: how many machines can run at once (you need 300; the typical published limit is 50)	different kind of product: code interpreter	None that bite
1,000 short jobs at once	not confirmed: how many machines can run at once (you need 1,000; the typical published limit is 50)	disk beyond 0 GiB: price unknown	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 GitHub Codespaces when

your developers want a ready VS Code environment for a GitHub repository, opened from a branch or pull request, in the US, EU or Asia.

Built into GitHub. Useful if your team lives on GitHub: open a ready dev container from any repo, branch or pull request.
A real editor for people. Useful when humans do the work: VS Code in the browser or on your machine, JupyterLab, and machines up to 32 cores.
Free hours for personal accounts. Useful for occasional personal work: a GitHub Free account includes 120 core-hours and 15 GB-month of storage each month.

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 billed 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 bochka fits

If what you are really running is agents that work on a machine for hours, neither fits cleanly: Codespaces is built for a person in an editor and stops at 12 hours, and AgentCore hosts short 2 vCPU sessions that forget their disk. bochka gives each agent a full VM that keeps running, keeps its whole disk and can be opened from a URL.

No session cap, and the disk stays

A codespace stops at 12 hours and its processes end, and an AgentCore microVM stops at 8 hours and resets everything outside a 1 GB mount. The workarounds are a restart script on Codespaces or paying for EC2 Instances on AWS.

A full VM with /dev/kvm and a desktop

Neither documents /dev/kvm, so Android emulators and microVMs are not a supported setup, and neither has a graphical desktop. bochka has root, Docker, systemd, /dev/kvm and a 60fps desktop on every machine.

Fork, open ports and agents driven from outside

Neither can fork a running machine, so every parallel try rebuilds its state. AgentCore has no open ports, and on Codespaces you script each agent over SSH; bochka forks, serves HTTPS on 50 ports and has a prompt, steer and events API.

Use bochka when your agents do real work on a machine for hours or days: Docker, /dev/kvm, a desktop and open ports, a disk that keeps everything, and machines that fork while running. Compare it one to one: bochka vs GitHub Codespaces and bochka vs AWS AgentCore.

Questions people ask

Is GitHub Codespaces cheaper than AWS AgentCore?

No, AgentCore costs less in every scenario we priced: one coding agent on workdays is $26 a month on AgentCore against $51 on Codespaces, and 50 agents in parallel are $1,286 against $3,019. But AgentCore only fits the 1,000 short jobs scenario, because files outside its storage mount reset after a stop. bochka comes in at $20 and $317 for those two.

Which is faster, Codespaces or AgentCore?

We have no comparable CPU measurement for either one. An AgentCore microVM session tops out at 2 vCPU, while Codespaces offers up to 32 cores. bochka did 26.69 Node.js build-and-test runs per second at 4 vCPU / 8 GB.

Can I run an AI agent 24/7 on Codespaces or AgentCore?

Not without workarounds. A codespace stops after 12 hours even while in use, and an AgentCore microVM session stops after 8 hours, or up to 14 days on the Instances type. A bochka sandbox runs until you stop it, with no session cap on paid plans.

Can Codespaces or AgentCore run Docker?

Docker works inside a codespace through dev container features. AgentCore runs your arm64 container image as root in a microVM, but its docs do not say Docker works inside a session. Neither documents /dev/kvm; bochka has Docker, systemd and /dev/kvm on every machine.

Do files survive a stop?

On Codespaces, saved files are kept until the stopped codespace is deleted, after 30 days by default. On AgentCore, only one storage mount under /mnt, up to 1 GB, survives, or EBS volumes on Instances. bochka keeps the whole disk and saves it every minute.

Is bochka SOC 2 compliant?

SOC 2 is in progress. We're open about where we stand: live status at status.bochka.xyz and our data retention policy at docs.bochka.xyz/data-retention.

Try bochka

Install the CLI, then run bochka new.

Product preview