E2B vs AWS AgentCore
E2B is a sandbox API: each agent gets a Firecracker microVM that can pause with its memory and serve a public URL. AWS AgentCore is an agent platform inside your AWS account, with 2 vCPU microVM sessions, managed Code Interpreter and Browser tools, and IAM and VPC controls.
The companies and products
E2B
E2B calls itself the AI agent cloud: an API that gives each agent session its own isolated Linux machine.
Every E2B sandbox is a Firecracker microVM that boots from a snapshot, so it starts fast and can be paused and resumed with its memory. You build custom sandboxes from templates based on a Docker image, and drive them from Python or JavaScript SDKs. It is built for teams that run many short code, data or agent jobs, and its runtime is open source.
- Isolation
- Firecracker microVM per sandbox
- Bring your own cloud
- Enterprise data plane in your AWS, GCP or Azure account
- Compliance
- SOC 2 Type II; HIPAA BAA on request
- Machine size
- 1 to 8 vCPU and 1 to 8 GiB RAM, CPU only
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 367” means 15 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 | E2B: 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 E2B fits a coding agent with 4 vCPU and a disk it keeps, while an AgentCore microVM session stops at 2 vCPU and 8 hours; bochka adds no session cap and a CPU about twice as fast as E2B's. | 16th cheapest of 367 $4,143 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 hits E2B's 24-hour cap and AgentCore's 8-hour microVM lifecycle, so both need workarounds; bochka simply keeps running. | 51st of 366, with limits $5,348 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 are built for short code runs: E2B starts fast and pauses with memory, and AgentCore Code Interpreter bills only for CPU actually used. | 37th cheapest of 345 $421 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 E2B gives each user's sandbox a public HTTPS URL and wakes it on the next request; AgentCore sessions have no open ports, so users cannot open the app they build. | 23rd cheapest of 361 $2,354 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 E2B's memory forks and high start rate suit many short rollouts from the same state; AgentCore has no snapshot or fork. | 2nd cheapest of 360 $9,384 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 | 78th cheapest of 364 $1,975 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 AgentCore fits CI runners well on its meter for CPU actually used, while E2B bills the CPU and RAM you set, idle time included; neither offers /dev/kvm, which bochka does. | 337th of 377, with limits $1,429 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 | 192nd of 368, with limits $358 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 E2B has a full Linux desktop for computer use, while AgentCore Browser drives only a browser; bochka streams a full desktop at 60fps. | 32nd cheapest of 369 $1,342 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, which E2B does not ship itself; bochka runs Chromium on a full machine you control. | 100th of 367, with limits $746 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 | 57th cheapest of 346 $554 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 | 227th of 338, with limits $9,223 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 | 11th cheapest of 360 $1,043 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 | E2B | AWS AgentCore | bochka |
|---|---|---|---|
| What it is | A sandbox API: each agent session gets its own Linux machine | 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 |
| CPU benchmark (4 vCPU / 8 GB) | 12.61 runs/s | Not measured | 26.69 runs/s |
| Biggest machine | Up to 8 vCPU / 8 GiB self-serve, more on request | 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 | Up to 1 hour on Hobby, 24 hours on Pro; pausing resets the clock | Up to 8 hours per microVM lifecycle, 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 | Memory and disk when paused; resume takes about 1 second with processes running | 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; resume boots the machine again |
| Fork | Fork a running sandbox with its memory, up to 20 copies per call | No snapshots or fork of a session | Fork a running sandbox with its disk |
| Docker, systemd and /dev/kvm | Docker, root and systemd; no nested virtualization | 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 URL per port, public by default unless you turn on a token; no dedicated 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 by default; raw TCP; SSH; dedicated IPv4 or IPv6 |
| Network controls | Allow and deny lists by IP, CIDR or 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 | Linux desktop for computer use | Managed Chromium with live view, session recording and replay; no full desktop | Full Linux desktop streamed at 60fps, with Chromium and computer use |
| Coding agents | Templates and guides for many agents, run through the command API | AWS's own managed harness built on Strands Agents, or your own agent code | Claude Code, Codex and five more preinstalled, with a prompt, steer and events API |
| Keeping API keys out of the sandbox | Secrets injected into outbound HTTPS headers (private beta) | 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 |
| Regions, GPUs and self-hosting | US, EU and APAC; no GPUs; open-source runtime and bring your own cloud on Enterprise | 17 commercial AWS regions plus GovCloud; GPUs on Instances; runs in your AWS account | EU only (Germany, Finland, France); no GPUs; no self-hosting |
Every feature Battleships tracks (43)
| Feature | E2B | 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 | Yes | No | Yes |
| Desktop GUI | Yes | No | Yes |
| Browser | Yes | Yes | Yes |
| Computer-use API | Yes | 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 | 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 | Yes | No | No |
| BYOC | Yes | Yes | No |
| Open source | Yes | 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 | No | 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
E2B and bochka were measured in the same StarSling hpc-sandbox-benchmarks run at 4 vCPU / 8 GB: E2B did 12.61 runs per second and bochka did 26.69, about twice the CPU work in the same time. AWS AgentCore has no comparable measurement: it was not part of that run, and a microVM session stops at 2 vCPU, so a like-for-like test would need the Instances type on EC2.
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 | E2B, 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 | $202 · 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 | $368 · 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 | $2,773 · 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 | $1,395 · Pro+ (600 concurrent) | $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 | $2,797 · Pro++ (1,100 concurrent) | $1,615 · Pay-as-you-go (Instances) | $2,000 · $2000/mo · with limits |
E2B: E2B bills per second for the vCPU and RAM you set, idle time included, until you pause or kill the sandbox. Pro costs $150 a month for higher limits with no usage credit, and more concurrency costs $500 a month per 500 slots.
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 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
E2B caps a Pro session at 24 hours, so it does not fit the always-on agent, and its Pro disk is 20 GiB. AgentCore's lower prices in the tables are for EC2 Instances, but files outside the storage mount reset after a stop and its code interpreter is a different kind of product from per-user sandboxes, so it fits only the 1,000 short jobs scenario. There E2B Pro++ only queues bursts above 300 starts a minute, while bochka's start limits make it a poor fit.
| Scenario | E2B | 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 E2B when
you run many short agent or code jobs that pause between requests, fork from the same state, or need a public URL, in any cloud.
- Pause with memory and wake on request. For jobs that sleep between requests, a paused E2B sandbox comes back in about a second with its processes still running.
- Fork and public URLs. E2B can fork a running sandbox with its memory and give each port a public HTTPS URL, which AgentCore sessions cannot do.
- Open source, outside any one cloud. Its runtime is Apache-2.0 and runs on your own KVM host, or in your AWS, GCP or Azure account on Enterprise.
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. Code Interpreter and Browser charge only for CPU actually used, and Browser adds live view and session 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 your agents do long, heavy work on one machine, both E2B and AgentCore cut them off: E2B at 24 hours, AgentCore at 8 hours and 2 vCPU. bochka gives each agent a full VM with Docker and /dev/kvm that keeps its disk, runs as long as you want and serves a URL you can open.
No session cap and a faster CPU
E2B stops a session at 24 hours on Pro and AgentCore microVMs at 8 hours, so long tasks need your code to pause and resume, or EC2 Instances in your account. bochka has no cap and ran the CPU benchmark at 26.69 runs/s against E2B's 12.61.
A full machine that keeps its disk
AgentCore resets everything outside a 1 GB storage mount, so installed packages are set up again after each stop, and neither offers /dev/kvm for Android emulators. bochka saves the whole disk every minute and runs Docker, systemd and nested VMs.
Agents, keys and hosting built in
On both you build the agent harness yourself, and AgentCore hands real keys to code the agent controls. bochka preinstalls seven coding agents, keeps keys in a credentials proxy for any HTTPS API, and gives HTTPS URLs on 50 ports plus raw TCP.
Use bochka when your agents do real work for hours: installs, builds, tests, Docker, emulators and a browser, on a fast machine that keeps its disk and never cuts them off. Compare it one to one: bochka vs E2B and bochka vs AWS AgentCore.
Questions people ask
Is E2B cheaper than AWS AgentCore?
AgentCore shows lower prices in all five scenarios on this page, but it fits only one of them: 1,000 short jobs at once. In the others its 2 vCPU microVMs, 8-hour sessions or resetting files get in the way, while E2B fits four of the five.
Which is faster, E2B or AgentCore?
E2B did 12.61 runs per second on the hpc-sandbox-benchmarks CPU test at 4 vCPU / 8 GB. AgentCore was not measured, and its microVM sessions stop at 2 vCPU. bochka did 26.69 runs per second in the same run as E2B.
Can E2B or AgentCore run Docker?
E2B runs Docker inside the sandbox but does not support nested virtualization. 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 E2B and AgentCore?
E2B stops a sandbox after 1 hour on Hobby and 24 hours on Pro, and pausing resets the clock. AgentCore microVM sessions last up to 8 hours, or 14 days on the Instances type. bochka has no session cap on paid plans.
Can users open an app running in the sandbox?
On E2B, yes: each port gets an HTTPS URL, public unless you turn on a token. AgentCore sessions have no open ports and are reached only through its APIs. bochka gives HTTPS URLs on up to 50 ports, token-protected by default.
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