Morph Cloud vs AWS AgentCore
Morph Cloud gives each agent a full VM that you can pause, branch and wake with its memory. AWS AgentCore hosts agent code in short microVM sessions with managed Code Interpreter and Browser tools, and fits best when your agents already live inside AWS.
The companies and products
Morph Cloud
Morph Cloud sells full virtual machines for AI agents that can be snapshotted, branched and restored with their memory, which it calls Infinibranch.
You get MorphVM instances as low-level building blocks and Devboxes as ready workspaces on top of them, with SSH, preview URLs and a tmux API for running coding agents you install yourself. Everything is billed in MCUs, where one MCU is 1 vCPU, 4 GB of RAM or 16 GB of disk for an hour. It is built for teams that fan agents out from one saved state, and it also sells managed GitHub Actions runners and a shared filesystem.
- Regions
- Not published
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. “16th cheapest of 345” means 15 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 | Morph Cloud: 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 Morph runs Docker and full builds but you install and drive the coding agent yourself; AgentCore stops at 2 vCPU and 8 hours per microVM session; bochka ships seven coding agents on a full VM. | 198th of 367, with limits $2,288 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 lives on one machine all month fits Morph's uncapped VMs but outlasts AgentCore's 8-hour microVM lifecycle; bochka keeps it running with its disk saved every minute. | 235th of 366, with limits $3,014 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 runs: AgentCore Code Interpreter bills only for CPU actually used, and a Morph VM can pause with its memory and wake on the next request. | 16th cheapest of 345 $154 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 Morph fits, since each user's VM can pause and wake on demand; AgentCore sessions have no open ports, so users cannot open what their sandbox runs, while bochka gives each one HTTPS on up to 50 ports. | 12th cheapest of 361 $905 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 Morph's memory branching suits rollouts that all start from the same running state; AgentCore has no snapshot or fork. | 86th of 360, with limits $4,847 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 | 38th cheapest of 364 $675 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 | 39th cheapest of 377 $355 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: Morph has both, while AgentCore has no SSH and resets everything outside its storage mount. | 85th cheapest of 368 $116 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 Morph's remote desktop needs you to install the agent tooling; bochka streams a full Linux desktop at 60fps with a computer use API. | 182nd of 369, with limits $595 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 here with a managed Chromium that has live view and replay; on Morph you run the browser yourself, and bochka has Chromium ready on a full desktop. | 214th of 367, with limits $250 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 | 239th of 346, with limits $234 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 | 154th of 338, with limits $4,750 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 | 214th of 360, with limits $228 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 | Morph Cloud | AWS AgentCore | bochka |
|---|---|---|---|
| Isolation | Full 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 |
| Session length | No cap; a VM runs until you stop it or its optional time to live ends | Up to 8 hours per lifecycle on microVMs, 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 | Disk and memory when you pause or snapshot; a plain stop deletes the instance | 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 every stop; a stopped sandbox is free |
| Pause with memory and wake on request | Yes; a paused VM bills only its snapshot and resumes on the next HTTP request, SSH or exec call | No pause; after a session stops, the next call starts a fresh microVM | No; disk is saved and resume boots the machine again |
| Fork a running machine | Yes, with its memory, as many copies as you ask for, in under 250 ms | No user snapshots or fork of a session | Yes, with its disk |
| Docker, systemd and /dev/kvm | Root, Docker in Docker and local Kubernetes; nested virtualization is experimental | 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 | Named HTTP services with optional API key auth; SSH through Morph's gateway; no raw TCP | 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 |
| Browser and desktop | Browser-based remote desktop; you install the browser and any computer use agent yourself | Managed Chromium with live view, session recording and replay, profiles and proxies; no full desktop | Full Linux desktop streamed at 60fps, with Chromium and a computer use API |
| Coding agents | You install the agent, then drive it through a tmux API that sends keys and reads the screen | AWS's own managed harness built on Strands Agents, or your own agent code in any framework | Claude Code, Codex and five more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Responses Proxy for model APIs; other secrets are handed to the machine | 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 | HTTP service auth for inbound traffic; no egress allowlist documented | VPC mode with security groups, PrivateLink and a NAT gateway for a fixed outbound IP | Open internet, no provider-side allowlist |
| Guest systems | Linux, with experimental Windows and macOS (x86) | arm64 Linux containers on microVMs; x86_64 or arm64 on Instances | Linux |
| GPUs | No | NVIDIA G-series and Inferentia2 on the Instances type | No |
| Where data lives | Regions not published | 17 commercial AWS regions plus GovCloud | EU only (Germany, Finland, France), with zero data retention |
Every feature Battleships tracks (43)
| Feature | Morph Cloud | 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 | Yes | 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 | No | No | Yes |
| Public IPv4 | No | No | No |
| Egress allowlist | No | Yes | No |
| Secret proxy | Yes | No | Yes |
| Secret proxy for any API | No | No | Yes |
| Preinstalled agents | No | No | Yes |
| Agent harness API | Yes | No | Yes |
| MCP server | No | Yes | No |
| GPU | No | Yes | No |
| Windows | Yes | 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) | Yes | No | Yes |
| Audit logs | Yes | Yes | No |
| SSO | Not published | Yes | No |
| SOC 2 | Not published | Yes | No |
| HIPAA | Not published | Yes | No |
| EU data residency | Not published | Yes | Yes |
| Zero data retention | Not published | Not published | Yes |
Performance
There is no comparable CPU measurement for Morph Cloud or AWS AgentCore: neither is in the hpc-sandbox-benchmarks 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. Morph's under 250 ms snapshot restore measures start time, not CPU speed.
Node.js build-and-test loop at 4 vCPU / 8 GB, higher is better. Measured with the open hpc-sandbox-benchmarks suite. Morph Cloud 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 | Morph Cloud, 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 | $32 · Developer | $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 | $121 · Team | $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 | $1,459 · Scale | $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 | $325 · Scale | $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 | $869 · Scale | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
Morph Cloud: Morph bills MCUs at $0.05 each: per hour, a machine uses the largest of its vCPUs, its RAM in 4 GiB steps or its disk in 16 GiB steps. Team ($40 a month) and Scale ($250 a month) are prepaid MCU bundles at a discount, and a paused VM bills only its snapshot 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, and files outside the storage mount reset on stop, so the workday, always-on and 50-agent scenarios do not fit. Morph fits all five, but more than 16 GiB of disk per vCPU raises its bill, egress prices are not published, and the Developer pool of 64 vCPU holds only 16 machines at 4 vCPU. At 1,000 short jobs at once, both Morph Scale and AgentCore fit, while bochka's $2,000 plan queues starts above 90 per minute.
| Scenario | Morph Cloud | AWS AgentCore | bochka |
|---|---|---|---|
| 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 Morph Cloud when
your agents need a full VM that branches from one running state with its memory, sleeps between requests and wakes on demand, or runs for days with Docker inside.
- Memory snapshots, branching and wake on request. For agents that fan out from one running state or sleep between requests: a paused VM keeps its memory and wakes on demand.
- A full VM with no session cap. For agents that run for days with Docker inside: a Morph VM keeps running until you stop it, with no 8-hour limit.
- Windows, macOS and managed CI runners. For teams that test on other systems or want hosted GitHub Actions runners billed from the same MCU balance.
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.
- 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, with Savings Plans applying.
- Managed tools that bill only 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.
Where bochka fits
Look at bochka when your agents do long, real work on a machine and you would rather not build the setup around them. Every bochka sandbox is a full VM with Docker and /dev/kvm, a disk saved every minute, coding agents you drive from outside, a 60fps desktop, and HTTPS on up to 50 ports, all in the EU.
Coding agents that come ready
On Morph you install Claude Code yourself and drive it by sending keystrokes through tmux; on AgentCore you use AWS's Strands harness or write your own agent code. bochka preinstalls seven agents you prompt and steer by API.
A disk that is never lost
A plain stop deletes a Morph instance unless you pause or snapshot first, which bills snapshot storage. AgentCore keeps only a 1 GB mount, so installs repeat after every stop. bochka saves the whole disk every minute, and a stopped sandbox is free.
Real keys stay outside the machine
Morph's Responses Proxy covers model APIs only, and AgentCore Identity hands keys to your agent code, so GitHub or Stripe keys sit where a prompt-injected agent can read them. bochka's credentials proxy covers any HTTPS API.
Use bochka when your agents do real work on a machine for hours: coding agents you drive by API, Docker and emulators, a desktop with Chromium, a disk that keeps everything, real keys kept outside, and a URL you can open. Compare it one to one: bochka vs Morph Cloud and bochka vs AWS AgentCore.
Questions people ask
Is Morph Cloud cheaper than AWS AgentCore?
It depends on the job. AgentCore's table price is lower for one workday agent ($26 vs $32 a month) and for 50 agents ($1,286 vs $1,459), but it does not fit those because files outside its storage mount reset. Morph costs less for sandboxes for your users ($325 vs $423) and for 1,000 short jobs ($869 vs $1,615).
Which is faster, Morph Cloud or AWS AgentCore?
Neither has a comparable CPU measurement: both are missing from the hpc-sandbox-benchmarks run. bochka did 26.69 runs per second there at 4 vCPU / 8 GB. Morph's under 250 ms snapshot restore is a start time, not a CPU score.
Can Morph Cloud or AWS AgentCore run Docker?
Morph runs Docker inside its VMs, including Docker in Docker and local Kubernetes. 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 on each?
A Morph VM has no cap and runs until you stop it or its optional time to live ends. An AgentCore microVM session lasts up to 8 hours and stops after 15 idle minutes by default; the Instances type allows up to 14 days. bochka has no session cap on paid plans.
Can either branch a running agent?
Morph can snapshot a running VM with its memory and branch it into many copies in under 250 ms. AgentCore has no user snapshots or fork. bochka forks a running sandbox with its disk, so the copy boots fresh.
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