Vercel Sandbox vs AWS AgentCore
Vercel Sandbox gives you Firecracker microVMs up to 8 vCPU on Pro that you drive with an SDK, open ports on, and keep for up to 24 hours. AWS AgentCore hosts agents inside your AWS account, with 2 vCPU microVM sessions of up to 8 hours and managed Code Interpreter and Browser tools.
The companies and products
Vercel Sandbox
Vercel is a cloud platform for web apps and agents, and Vercel Sandbox is its product for running untrusted or agent-written code in isolated Linux microVMs.
Each sandbox is a Firecracker microVM with its own kernel, started from a Vercel image, your own OCI image, or a saved snapshot. You drive it with the JavaScript or Python SDK or the sandbox CLI: run commands, move files, open ports, and set network rules. It is aimed at code interpreters, app builders, test runs and agent tools, and Vercel's docs say it is not meant to run nonstop.
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. “22nd cheapest of 345” means 21 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 | Vercel Sandbox: 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 Both are compromises for a coding agent: Vercel stops each session at 24 hours and AgentCore at 8 hours with 2 vCPU, while bochka ranks 3rd with a full machine that keeps its disk. | 244th of 367, with limits $3,351 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: Vercel restarts every 24 hours and AgentCore needs its Instances type on EC2, while bochka ranks 5th and simply keeps running. | 257th of 366, with limits $3,657 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 Both fit short code bursts and bill CPU only while it is used; AWS AgentCore ranks 7th and Vercel Sandbox ranks 22nd, while bochka's start limits make it a compromise here. | 22nd cheapest of 345 $216 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 Vercel Sandbox fits and ranks 15th because each sandbox can open public URLs; AgentCore sessions have no open ports, and bochka ranks first with HTTPS URLs on up to 50 ports. | 15th cheapest of 361 $1,267 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 Vercel Sandbox ranks 3rd for many short parallel rollouts thanks to high concurrency and fast starts; AgentCore and bochka are both compromises here. | 3rd cheapest of 360 $15,761 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 | 69th cheapest of 364 $1,508 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 | 107th cheapest of 377 $1,144 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 | 276th of 368, with limits $145 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 Neither gives an agent a full desktop: Vercel Sandbox is headless and AgentCore Browser drives only a browser, while bochka streams a 60fps Linux desktop. | 235th of 369, with limits $952 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 AWS AgentCore ranks 4th with its managed Chromium, live view and replay; Vercel Sandbox has no browser feature, and bochka ranks 7th with Chromium on a full machine. | 259th of 367, with limits $486 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 AgentCore Browser fits startup-scale scraping and ranks 27th; Vercel Sandbox has no browser, and bochka ranks 6th. | 277th of 346, with limits $468 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 | 234th of 338, with limits $9,960 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 | 283rd of 360, with limits $554 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 | Vercel Sandbox | AWS AgentCore | bochka |
|---|---|---|---|
| What it is | A sandbox product: isolated Linux microVMs you drive with an SDK or 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 |
| Isolation | Firecracker microVM 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 |
| Biggest sandbox | 8 vCPU / 16 GB on Pro, 32 vCPU / 64 GB on Enterprise | 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 |
| Longest session | 24 hours on Pro and Enterprise, 45 minutes on Hobby; resume starts a new session | 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 |
| What survives a stop | Filesystem snapshot on stop, kept 30 days after last use by default, billed per GB a month | Only one storage mount under /mnt, up to 1 GB, in preview; EBS volumes on Instances; no snapshots | The whole disk, saved every minute and on stop; fork a running sandbox with its disk |
| Docker and /dev/kvm | Docker with sudo; no nested virtualization | Root inside the microVM; Docker and /dev/kvm not documented | Root, Docker, systemd and /dev/kvm for Android emulators and VMs |
| Custom images | Your own OCI images from a Dockerfile, via Vercel Container Registry | Your own arm64 container image for Runtime sessions | Named snapshots (templates), shareable by code; no Dockerfile builds |
| Inbound access | Public URLs for up to 15 ports, no built-in auth; no raw TCP or public IP | No open ports or SSH; 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 | Allow-all, deny-all or a domain and CIDR allowlist, changeable while running; static IPs and VPC peering on Enterprise | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet, no provider-side allowlist; firewall inside the VM |
| Browser and desktop | None; headless Linux only | 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 APIs |
| Coding agents | Claude Code, Codex, OpenCode and pi preinstalled; you start them as commands | AWS's own managed harness built on Strands Agents, or your own agent code | Claude Code, Codex and five more preinstalled, with an API to prompt, steer and stream events |
| Keys kept outside the sandbox | Credentials brokering injects headers for any HTTPS domain you allow | 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 | No | NVIDIA G-series and Inferentia2 on the Instances type | No |
| Regions | 19 regions across the US, Europe, Asia, South America, Africa and Australia | 17 commercial AWS regions plus GovCloud | EU only: Germany, Finland, France |
Every feature Battleships tracks (43)
| Feature | Vercel Sandbox | 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 | No | 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 | No | 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 | 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 | 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 | Not published | 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
Vercel Sandbox and bochka were measured on the same hpc-sandbox-benchmarks Node.js build-and-test loop at 4 vCPU / 8 GB: bochka did 26.69 runs per second and Vercel Sandbox did 12.96, so bochka finished about twice as many runs. AWS AgentCore was not part of that run, so there is no comparable score; its microVM sessions stop at 2 vCPU, so a like-for-like test would need the Instances type.
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 | Vercel Sandbox, 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 | $57 · Pro | $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 | $236 · Pro · 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 | $2,884 · 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 | $828 · 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 | $3,152 · Pro | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Vercel Sandbox: Vercel charges for CPU only while your code uses it, but for memory the whole time the sandbox runs, plus a small fee per sandbox created and a monthly fee per GB of snapshots. The $20 Pro credit is shared with your other Vercel usage.
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: bochka charges a flat price per size, per second, only while the machine runs; a stopped sandbox costs nothing and keeps its disk. Plans start at $20 a month, and the whole fee is usage credit.
Limits in those scenarios
For one agent that never stops, Vercel ends each session at 24 hours and AgentCore's Instances type ends it at 14 days, so neither fits. On AgentCore, files outside the session storage mount reset when a session stops, so the workday, 24/7 and 50-agent scenarios do not fit, and sandboxes for your users do not fit because sessions have no open ports. For 1,000 short jobs at once, both fit, while bochka does not: even its $2,000 plan allows 600 starts an hour and queues bursts above 90 starts a minute.
| Scenario | Vercel Sandbox | AWS AgentCore | bochka |
|---|---|---|---|
| One coding agent, workdays | None that bite |
| None that bite |
| One agent that never stops |
|
| 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 | None that bite |
|
|
Which one should you use?
Use Vercel Sandbox when
you run many short bursts of untrusted code, want bigger sandboxes or public URLs without managing EC2, or already build on Vercel.
- Bigger sandboxes with no EC2 to manage. A Pro sandbox can be 8 vCPU / 16 GB, while an AgentCore microVM session stops at 2 vCPU.
- Open a port and get a URL. Each sandbox can serve public URLs on up to 15 ports, so users can open what it runs.
- Images from your Dockerfile. Teams with a Dockerfile can build it into an image and boot sandboxes straight into it.
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 its managed tools.
- It lives inside your AWS account. Teams built on AWS keep agents behind their own IAM, VPC, security groups and PrivateLink.
- A managed browser for agents. AgentCore Browser gives agents a Chromium with live view, session recording, replay, saved profiles and proxies.
- 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 your agents work for hours on one machine, installing packages, running Docker and checking the app they built, both products make you work around their session caps. bochka gives each agent a full VM that keeps its whole disk, runs with no session cap on paid plans, and comes with a desktop, a browser and an API to drive the agents inside from outside.
Work is not cut off mid-task
Vercel ends each session at 24 hours and running processes start over; an AgentCore microVM stops at 8 hours. The AgentCore workaround is its Instances type, which means running and paying for EC2 in your own account.
The whole disk stays, and you can fork it
AgentCore keeps only a 1 GB mount under /mnt, so packages installed elsewhere are gone after each stop. Vercel snapshots on stop and bills for every kept snapshot. bochka saves the disk every minute and forks a running sandbox.
A screen the agent can use
Vercel Sandbox is headless, and AgentCore Browser drives a browser but not a desktop, so an agent cannot test other apps. bochka streams a 60fps Linux desktop with Chromium and computer-use APIs.
Use bochka when your agents work for hours on one machine: installs, builds, tests, Docker, emulators and a desktop with a browser, with a disk that keeps everything and an API to drive the agents inside from outside. Compare it one to one: bochka vs Vercel Sandbox and bochka vs AWS AgentCore.
Questions people ask
Is Vercel Sandbox cheaper than AWS AgentCore?
AgentCore is lower in every scenario in the table, but often it does not fit. For 1,000 short jobs at once, where both fit, AgentCore costs $1,615 a month against $3,152 on Vercel. For one workday agent it is $26 against $57, but AgentCore resets files outside its storage mount after each stop.
Which is faster?
Only Vercel Sandbox has a comparable score: 12.96 runs per second on the hpc-sandbox-benchmarks Node.js loop at 4 vCPU / 8 GB, against 26.69 for bochka. AWS AgentCore was not measured, and its microVM sessions stop at 2 vCPU.
How long can a session run on each?
Vercel Sandbox sessions last up to 24 hours on Pro and Enterprise, then resume from a snapshot with processes started over. AgentCore microVM sessions last up to 8 hours and stop after 15 idle minutes by default, or up to 14 days on the Instances type. bochka has no session cap on paid plans.
Can they run Docker?
Vercel Sandbox runs Docker with sudo, but has no nested virtualization. AgentCore runs your container image as root in a microVM, but its docs do not say Docker or /dev/kvm work inside a session. bochka runs Docker with systemd and exposes /dev/kvm.
Which one has a browser for agents?
AWS AgentCore does: its Browser tool is a managed Chromium with live view, recording and replay. Vercel Sandbox has no browser or desktop. bochka streams a full 60fps desktop with Chromium and computer-use APIs.
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
More comparisons
- bochka vs Vercel Sandbox
- bochka vs AWS AgentCore
- E2B vs Vercel Sandbox
- Daytona vs Vercel Sandbox
- Modal vs Vercel Sandbox
- Vercel Sandbox vs Cloudflare Sandbox
- Vercel Sandbox vs Blaxel
- Vercel Sandbox vs Runloop
- Vercel Sandbox vs Tensorlake
- Vercel Sandbox vs Morph Cloud
- Vercel Sandbox vs CodeSandbox SDK
- Vercel Sandbox vs Northflank